3D SAR imaging can reconstruct the layovers in 2D SAR images, which is one of the important development directions of SAR imaging. Traditional 3D SAR imaging techniques, for example, based on SAR tomography or array InSAR, approach the imaging process purely from a signal processing perspective. Such methodologies, while effective, tend to overlook the vast potential of SAR image information beyond mere cross-track samples.

The concept of "Microwave Vision" represents a physical intelligence for understanding microwave imaging information. It proposes a harmonious merger of visual semantics with the intricate microwave scattering mechanisms intrinsic to SAR imaging. By leveraging the power of computational electromagnetics combined with semantic vision extraction and state-of-the-art deep learning technologies, Microwave Vision has the potential to redefine 3D SAR imaging technology. The envisaged outcomes include enhanced 3D SAR imaging fidelity, a reduction in reliance on a huge number of cross-track samples, and a profound enhancement in target scene understanding. Given its pioneering nature and the hybridization of different fields, Microwave Vision does not integrate into the existing thematic sessions at IGARSS. But we believe it will receive widespread attention. 

This dedicated session aims to be the epicenter of discussions, debates, and disclosures around 3D SAR imaging with Microwave Vision. It will provide researchers and industry experts an unparalleled platform to present recent findings, exchange groundbreaking ideas, identify burgeoning trends, and network with an international assembly of SAR imaging enthusiasts.

The scope of this session includes but not limited to: 
A. Semantic Electromagnetic Scattering and 3D SAR Information Retrieval 
1. Semantic Scattering Modeling
2. Inverse Scattering and Information Retrieval
3. 3D SAR Information Retrieval

B. Vision Perception in 3D SAR imaging 
1. Visual feature extraction and model interpretation
2. Visual recognition, detection, and segmentation
3. 3D vision techniques in microwave imaging 
4. Computer vision applications in microwave imaging 

C. 3D/4D SAR imaging technologies based on Microwave Vision
1. 3D/4D SAR imaging meets microwave vision
2. Three-dimensional microwave imaging principle study and system design 
3. Applications of three-dimensional microwave imaging 
4. Fusion of three-dimensional SAR imaging and other sensors and its applications

A major impediment in the use of thermal remote sensing data in ecology and agriculture has been the data limitation of having no fine resolution (< 100m), long temporal repeat (16 days), and no multispectral channels for emissivity correction. The successful launch of ECOSTRESS and installation on the International Space Station (ISS) in July 2018 has provided global multispectral thermal data at 70 m resolution and for a 3-5 day repeat cycle of day-night pairs. Future planned NASA SGB (2027), the Indian-French TRISHNA (end 2024) and ESA LSTM (2 satellites 2028) missions with the harmonization of data sets and orbits will extend and enhance current thermal data availability with 60m resolution, multispectral, and daily day-night pairs.

The main use of thermal data has been estimating agricultural evapotranspiration and water management. Thermal remote sensing can provide environmental measuring tools with capabilities for measuring both managed and natural ecosystem development and integrity. Recent advances in applying principles of nonequilibrium thermodynamics to ecology provide fundamental insights into energy partitioning in ecosystems.  Ecosystems are nonequilibrium systems, open to material and energy flows, which grow and develop structures and processes to increase energy degradation. More developed terrestrial ecosystems will be more effective at dissipating the solar gradient degrading its exergy content. 

Terrestrial ecosystem's surface temperatures have been measured using airborne and satellite sensors for several decades.  Using NASA’s Thermal Infrared Multispectral Scanner (TIMS) Luvall and his coworkers (Luvall and Holbo 1989; Luvall et al 1990; Luvall and Holbo 1991) have documented ecosystem energy budgets for including tropical forests, mid-latitude varied ecosystems, and semiarid ecosystems.  These data show that within a given biome type, and under similar environmental conditions (air temperature, relative humidity, winds, and solar irradiance), the more developed the ecosystem, the cooler it's surface temperature and the more degraded the quality of its reradiated energy. These data suggest that ecosystems develop structure and function that degrades the quality of the incoming energy more effectively, that is they degrade more exergy, which agrees with the predictions of nonequilibrium thermodynamic theory (Schneider and Kay 1994a; Kay and Schneider 1994; Schneider; Sagan 2005 and Hamberg et al. 2020). The ecosystem temperature, Rn/K*, Beta Index, and TRN are excellent candidates for indicators of ecological integrity.

The same thermodynamic approach can be used for determining crop yield and optimum nitrogen fertilizer application. Alzaben (2020), using exergy destruction principle (EDP) tested under greenhouse and field conditions on corn plants at three different scales (i.e., leaf, canopy and over a plot area). Agricultural crops experiencing greater growth and providing greater yield will have lower surface temperature. Two hypotheses are developed as predicted by the EDP. It is hypothesized that agricultural crops experiencing greater growth and providing greater yield will have lower surface temperatures. The second hypothesis is that crops grown under optimum/higher rates of nitrogen will have lower surface temperatures compared to crops grown under nitrogen stress conditions. 

Continuous urbanization in a world of ongoing climate change dramatically transforms human life and creates an important necessity for cities, resilience and sustainability. This involves a deep understanding of socio-economic dynamics as well and an overall need for holistic approaches to provide new insights into the ways we should move towards liveable societies. The realization of the above calls for an implementation frame and the 2030 Agenda for Sustainable Development provides such a global framework for action on sustainable development. For the monitoring of progress towards specific SDGs and associated targets, accurate, robust and timely data from diverse sources are imperative. Although the contribution of many types of data to further sustainable development is widely recognized, great focus is placed on Earth Observation (EO), especially for its potential to complement traditional sources of socio-economic. Few of the questions in place are: how can we improve or deliver new types of environmental information combined with censuses and household surveys? how can remotely mapped land cover over time can be linked to the economic use of the respective land? how do we reveal new insights into climate change associated risks and map vulnerabilities and impacts for different sectors? how can we promote the overall wellbeing of Earth citizen’s as the absolute indicator of our future society’s success?
Human’s wellbeing is linked to several aspects of everyday life in cities, where EO can really support the understanding of the perplexed interactions and interfaces. For example, extreme heat can have adverse effects on human health, particularly among vulnerable population groups, and its effects can be especially detrimental in cities which also have limited green, open spaces, poor ventilation, and various types of surfaces that absorb heat. Air pollutants, for which impacts on health is well established and threshold values are framed, are also monitored though EO and, complemented by sophisticated atmospheric models, can deliver health-related indices to delineate pollution impacts on overall wellbeing. Urbanization and climate change are also critical for their impacts on World Heritage properties, and in the case of urban heritage, there is an additional critical need to integrate different aspects of the sustainable development agenda, including urban resilience and sustainable urbanization, with the protection of heritage values, considering the centrality of cultural heritage’s social, ecological and economic dimensions for sustainable urban development.
The objective of the session is to better understand the spatial and temporal dimensions of various wellbeing aspects as above, and demonstrate through projects and examples the progress achieved during the last years on creating synergetic and multi-disciplinary approaches involving EO in support of the relevant policy frames, including the 2030 Agenda of SDGs.

Polarimetry is going to start a new operational ere with the upcoming polarimetric satellite SAR missions (ALOS4, NISAR, and Tandem-L) equipped with digital antenna beaming. ALOS4 planned for launch in 2023 will permit polarimetric SAR imaging at 3m resolution and 100km swath. This is a significant advance in comparison with  the existing polarimetric satellite SAR missions (RADARSAT-2, ALOS2, and TerraSAR) of limited swath (50km). With the approach of this new ere of operational use of polarimetric SAR in support of key applications,  it is important to reconsider the state of the art in the methodology and tools  currently adopted for polarimetric information extraction. This special session will allow us to learn more about the most advanced tools recently developed for optimum polarimetric information extraction such as target scattering decomposition, speckle filtering, image classification, and polarimetric SAR modeling. The session that will gather edge leading guest scientists will also give the opportunity to  discuss the gaps that would have to be fulfilled to fully exploit the polarimetric information provided by satellite and airborne SAR in support of key applications.

Historically, observations of natural phenomena and physical processes by remote sensing systems were coincidental with the overflight of the instruments available. The global mapping strategy has been excellent for monitoring and unraveling large scale, long duration processes. For example, prevailing winds or even hurricanes have become far better understood through this type of missions. Even geostationary low Earth orbits have provided vast quantities of well registered data, globally.  However, the study of many smaller scale, short duration processes and phenomena are only fueled with coincidental capture during the normal scanning cycle.  Global mapping missions are essential to the long-term monitoring of the state of the Earth. But novel observing strategies (NOS) can now be considered for a variety of purposes.

With the advent of constellations of satellites with both passive and active sensors, low-latency downlinks, and AI algorithms running on edge computing, there is an opportunity to use the output of the sensor to task it and other sensors, remote, airborne or in situ.  Not only does this capability enable more concentrated process studies but also attention to transient and transitional phenomena, such as tornadoes, extreme storms, and biological phenomena that operate at the time scale of the diurnal cycle,  

Novel observing strategies can be placed into service, that were only imagined before. For example, cooperating observing systems, such as TROPICS, can observe phenomena from multiple angles or a string of satellites can observe a short-lived or dynamical phenomenon for much longer periods of time. An array of multiple platforms of identical sensors can work as a phased array, maintaining focus for as long as it is observable by shifting the focal point.. They can also be used to improve signal to noise ratios, etc.

Novel observing strategies can also be considered when planning a new mission driven by the need for a new measurement. They could facilitate the creation of “virtual missions” composed of several existing missions and/or sensors as well as of additional in-situ, airborne or space sensors, from various organizations (government, industry and academia), nationally and internationally. NOS would provide the capability to optimize the use of an existing portfolio and to complement it with other well-chosen sensors, thus reducing risk, cost and time of development of new observations.

The purpose of this session is to share experience and concepts related to the NOS in Earth Observation, although many of the control and monitoring technologies needed for these environments are re-usable in different domains, such as heliophysics and planetary. This is directly related to digital twin technology.

Surface Topography and Vegetation (STV) is a NASA targeted observable to map Earth’s changing surface and overlying vegetation structure. Science and technologies for targeted observables are being matured into an observing system architecture.  STV will acquire high-resolution, global height measurements, including bare surface land topography, ice topography, vegetation structure, and shallow water bathymetry. These measurements serve a broad range of science and applications objectives that span solid earth, cryosphere, biosphere and hydrosphere disciplines.  The overarching questions asks how does Earth’s changing surface structure inform us about climate change, natural hazards, ecosystem habitats, and water availability? A common set of measurements would meet many of the community needs. STV objectives would be best met by new observing strategies that employ flexible multi-source and sensor measurements from a variety of orbital and sub-orbital assets. Science and application objectives would be best met by new, 3-dimensional observations from lidar, radar, and stereoimaging. Simulations, experiments, data analysis and technology development in interferometric SAR, lidar and stereo photogrammetry approaches, platform options and system architectures will all mature STV toward an observing system. This session invites submissions on STV technology maturation activities and related science activities.

Earth Observation (EO) sensors are acquiring Big Data volumes at very high data rates (e.g., the Copernicus missions produce 12 TB of data per day). In particular, next generation SAR systems will offer a quantum leap in performance using large bandwidths and digital beam forming techniques in combination with multiple acquisition channels. These innovative spaceborne radar techniques have been introduced to overcome the limitations imposed by classical SAR imaging for the acquisition of wide swaths and, at the same time, of finer resolutions, and they are currently being widely applied in studies, technology developments and even mission concepts conducted at various space agencies and industries. Such significant developments in terms of system capabilities are clearly associated with the generation of large volumes of data to be gathered in a shorter time interval, which, in turn, implies harder requirements for the onboard memory and downlink capacity of the system. Similar considerations can be drawn with respect to optical sensors, such as multispectral and hyperspectral ones, which provide nowadays large amounts of images at high resolution. Therefore, the proper quantization/compression of the acquired data prior to downlink to the ground is of utmost importance, as it defines, on the one hand, the amount of onboard data and, on the other hand, it directly affects the quality of the generated EO products.

EO data show unique features posing important challenges and potentials, such as learning the data models for optimal compression to preserve data quality and to avoid artefacts hindering further analysis. For instance, based on the peculiarities of the imaged scene (e.g., in radar imaging these are characterized by the reflectivity, polarization, incidence angle, but also by the specific system architecture, which may offer opportunities for efficient data quantization; differently, multispectral data are characterized by the land cover or the presence of clouds), a more efficient data representation can be achieved by searching for the best quantizer and the ad-hoc tuning of the inner quantization parameters. Additionally, onboard preprocessing of the acquired data to a sparse domain (e.g., range compression in the case of SAR data) can also lead to a more compact data representation.

Artificial Intelligence (AI) represents one of the most promising approaches in the remote sensing community, enabling scalable exploration of big data and bringing new insights on information retrieval solutions. In the past three decades the EO data compression field progressed slowly, but the recent advances in AI are now opening the perspective of a change of paradigm in data compression. AI algorithms and onboard processing could be exploited to generate/discover novel and more compact data representations. 
This session would like to bring to the field new methodologies for both loss-less and lossy compression of remote sensing data. Several data compression topics are welcomed to the session, which include (but are not limited to): data-driven and model-based compression methods, Kolmogorov complexity-based algorithms, source coding with side information, neural data compression, compression of correlated sources, integrated classification and compression, semantic coding, big data compression and application-oriented compression.

Recent advances in sensor and aircraft technologies allow us to acquire huge amounts of remote sensing data. Diverse information on Earth's surface can be derived from these multi-resolution and multimodal data, providing a much more comprehensive interpretation for Earth observation, e.g., spectral information from multi- and hyperspectral images can help to reveal the material composition, elevation information from LiDAR data helps to estimate the height of the observed objects, synthetic aperture radar (SAR) data can measure dielectric properties and the surface roughness, panchromatic data are instead focused on spatial features of the acquired landscape, and so forth.
 
State-of-art works have proven that the fusion of these multi-resolution and multimodal images provided better performance than those only using a single image source. However, challenges remain when applying these data for some applications (classification, target detection, geological mapping, etc.). For example, classical issues could be related to the misalignment of multimodal images, the presence of clouds or shadows (in particular, when optical data are involved), and spectral/spatial differences hampering the post-fusion of these data.
 
This invited session will focus on multi-resolution and multimodal image processing and interpretation, such as multimodal image alignment, restoration, sharpening of multi-spectral and hyperspectral images (e.g., pansharpening, hyperspectral pansharpening, and hypersharpening), use of machine learning approaches devoted to several tasks (e.g., feature extraction and classification) exploiting the multimodality of the data, and so forth. We will discuss the latest methods/techniques for multi-resolution and multimodal image processing, as well as how this can benefit our interpretation.

Polarimetric GNSS-R (Global Navigation Satellite System-Reflectometry) represents the evolution of GNSS-R technology, poised to enhance land and cryosphere assessments significantly. The integration of polarimetry into forward scattering measurements plays a pivotal role in disentangling critical factors like vegetation, soil moisture, roughness, sea ice characteristics, and freeze/thaw state investigations. For instance, a long-standing objective in GNSS-R has been the retrieval of soil moisture in a single pass, without heavy reliance on ancillary data. Accomplishing this objective would empower small satellites equipped with GNSS-R payloads to conduct autonomous land monitoring, negating the need for additional dynamic measurements. However, prior research has highlighted the complexity and low accuracy associated with single-pass soil moisture retrieval in the absence of in-situ moisture or ancillary data. An avenue to surmount this challenge is to enhance existing GNSS-R instruments with polarimetric capabilities, enabling more versatile Earth surface analysis, particularly in polarimetrically significant regions like icy surfaces, bare soil, or vegetated areas.

Present-day trends in Polarimetric GNSS-R revolve around the utilization of either two circular polarization antennas (RHCP/LHCP) or two linearly polarized antennas (H/V). Collaborative discussions among experts in the field are essential to propel progress and furnish improved guidelines for determining when one polarization scheme should be preferred over the other. Such dialogues are expected to foster fruitful exchanges among peers hailing from diverse teams and backgrounds. Topics under scrutiny include the impact of polarimetric GNSS-R, ranging from modeling and data simulations for future missions, drawing inspiration from existing non-polarimetric missions, to the analysis of actual polarimetric data.

This session holds significant relevance for upcoming polarimetric GNSS-R missions, such as ESA's HydroGNSS, as well as for future missions that may arise, requiring polarimetric capabilities to yield higher-quality GNSS-R products, such as soil moisture measurements or cryosphere characterization, and even novel products like vegetation opacity. Furthermore, the adoption of polarimetric GNSS-R retrievals could facilitate the independent retrieval of critical geophysical parameters like soil moisture, obviating the need for ancillary data. Thus, these retrievals would provide complementary datasets to those currently available from ongoing missions, serving as valuable training and validation resources for future algorithm development. Combining models with data from existing GNSS-R missions (e.g., CYGNSS, BuFeng-1, FY-3E, Spire, SMAP reflectometry) will enable a deeper understanding of the potential outcomes of a polarimetric GNSS-R mission. The session will encompass presentations from international teams engaged in polarimetric GNSS-R, spanning efforts in model development, existing spaceborne measurements, and the anticipated launch of polarimetric GNSS-R missions.

In a rapidly changing world, understanding and mitigating the impacts of environmental changes on our planet has become an imperative. Earth System Digital Twins (ESDTs) have emerged as a revolutionary approach, seamlessly integrating Earth sciences, AI technologies, and real-time data to simulate, monitor, and predict Earth's complex systems. This technical session explores the intersection of Earth Action applications, what-if decision making, and the pivotal role of AI-driven software technologies in advancing ESDTs.

Earth Action Application:
The Earth Action application component of ESDTs emphasizes the real-world relevance of these digital twins. Through the incorporation of multidisciplinary data sources, such as geospatial, atmospheric, oceanographic, and ecological data, ESDTs enable comprehensive modeling of Earth's dynamic systems. This session will feature papers on emerging applications and prototypes that demonstrate how ESDTs can revolutionize our capacity to assess and respond to environmental challenges, from tracking wildfire propagation to assessing urban resilience against climate-induced hazards.

What-If Decision Making:
One of the most compelling aspects of ESDTs is their capacity to support what-if decision making. This session will explore how ESDTs empower stakeholders with the ability to simulate various scenarios and assess the consequences of different policy choices. In doing so, ESDTs provide invaluable insights for informed decision making, offering tools to anticipate, prepare for, and mitigate the impacts of environmental changes.

AI-Driven Software Technologies:
Central to the success of ESDTs are the sophisticated AI-driven software technologies that underpin their development and operation. This session delves into the latest advancements in machine learning, deep learning, and data assimilation techniques, which enable ESDTs to process vast and heterogeneous datasets in real-time. Moreover, we explore how these AI technologies enhance the predictive capabilities of ESDTs, improving their accuracy and responsiveness. Topics covered will include data integration and fusion, model validation and calibration, scalable computing infrastructure, and user-friendly interfaces and visualizations for decision-makers.

By attending this technical session, participants will gain a deep understanding of how ESDTs can transform the way we interact with and manage our planet's complex systems. They will also explore the critical role of AI-driven software technologies in creating actionable insights for addressing global environmental challenges.

The Sendai Framework for Disaster Risk Reduction was adopted at the Third UN World Conference on Disaster Risk Reduction in Sendai, Japan, on March 18, 2015. 
The goals outlined in this framework have encouraged the development of risk reduction strategies by a wide array of sectors, including anticipatory action for humanitarian aid. As such, stakeholders of the humanitarian aid domain define a set of actions taken to prevent or mitigate potential disaster impacts before a shock or before acute impacts are felt. Anticipatory humanitarian action, is reshaping the humanitarian system and is increasingly recognized as a key solution to reducing the impacts of climate change and extreme weather events to local communities. A critical challenge for the application of anticipatory action is to maximize the window of opportunity between the moment of prediction and the arrival of a forecasted shock to trigger interventions that prevent or mitigate imminent humanitarian impacts. 

In order to be properly applied, anticipatory action requires a variety of data, to feed forecast models, quantify impact to population and assets, and eventually inform decisions through agreed early-action protocols. The role of Earth Observation (EO) becomes increasingly important for improving the aforementioned predictions related to impact of various hazards and provides an independent, continuous and synoptic view of the communities-regions-countries to be impacted. 

The session reflects on inputs from the humanitarian community for reducing entry barriers to EO, develop simple solutions for non-expert users and eventually advance and mainstream the use of EO for anticipatory action. The session will focus on the use of EO and other collateral data for geospatial applications in anticipatory humanitarian action, including a wide field of relevant themes:
-	Identification of capability gaps in EO-based systems
-	New methods and approaches towards anticipating hazards for humanitarian aid applications (e.g. application of Artificial Intelligence for anticipatory action)
-	Methodologies to validate forecasts Validation methods
-	Evaluating the impact of EO-based anticipatory action on the ground
-	Standards towards a harmonized, repeatable EO-driven monitoring, evaluation, accountability and learning (MEAL)
-	Space-based services beyond EO: GNSS and SatCom for anticipatory action.

The session 'Advancing Technologies for Wildfire Risk Management in the Context of the 2030 Green Deal' promises to be a crucial and forward-looking discussion at the intersection of environmental protection and cutting-edge technology. As we embark on the journey to achieve the goals outlined in the 2030 Green Deal, addressing the escalating threat of wildfires is of paramount importance. This session will provide a comprehensive exploration of innovative solutions (e.g., multimodal data fusion, applications of AI for wildfire science problems, sensor networks) and strategies to mitigate wildfire risks in an environmentally responsible manner.

Wildfires are increasing in intensity and frequency, exacerbated by climate change and land use patterns. In response to this pressing issue, the session will bring together experts from various fields, including environmental science, technology, policy and firefighting, to examine how emerging technologies can be used to improve wildfire prevention, detection and response.

Participants can expect to gain insights into cutting-edge tools such as satellite imagery, drones, AI-driven modelling and sensor networks that are transforming our ability to monitor and manage wildfires. The discussion will also explore the ethical and environmental implications of using advanced technologies to manage wildfires, ensuring that solutions are consistent with the principles of sustainability and environmental protection.

The 2030 Green Deal places a strong emphasis on promoting a harmonious coexistence between humans and nature. This session will explore how technology can help achieve this balance, not only by reducing the destruction caused by wildfires, but also by facilitating ecosystem restoration and recovery after fires.

Ultimately, "Advancing Technologies for Wildfire Risk Management in the Context of the 2030 Green Deal" is an opportunity for policymakers, scientists, technologists, and environmental advocates to come together, exchange ideas, and forge a path forward to protect our planet from the growing threat of wildfire.

“They just work” is a common argument for the use of artificial intelligence and machine learning (AI/ML) systems for inference. However, it is not sufficient for applications where an AI system is asked to detect rare or important events that are associated with high-consequence decision making, which is often the case in hyperspectral image analysis. Remote sensing end users, i.e., humans who have to decide what to do with what their algorithms tell them, have been rightfully reluctant to adopt the “black box” class of machine learning algorithms – uninterpretable algorithms that have otherwise been shown to be effective in fields outside of remote sensing. This reluctance to “black box” methods is because model explainability (XAI) and interpretability are critically important for an end user that must act, with confidence, on an AI system’s predictions. 
 
Nevertheless, AI/ML techniques are becoming increasingly more ubiquitous in hyperspectral remote sensing analysis, particularly with the ever-growing volume of hyperspectral remote sensing data in both public and commercial sectors. And because many of the research results are promising, an increased emphasis on explainability is all the more urgent. AI systems in our community need to not only be predictable, but they also need to be transparent in their reasoning, and they need to be interpretable.  
 
In our Community Contributed Session, we will emphasize techniques for end-to-end, traceable explainability – starting with the model training inputs, through the system architecture, and to the outputs, while considering sensor design and domain information throughout. In doing so, we will open the “black box” that typically obfuscates insights into AI/ML models in hyperspectral target detection. Because AI/ML explainability methods can apply to different domains within remote sensing, we hope that this session will demonstrate transferable techniques as well as enable cross-pollination of new ideas. 

By 2050, around 70% of the world's population will live in cities. Around 90% of this growth is expected to happen in Low-and-Middle-Iincome Countries (LMICs), often in areas that are deprived in terms of housing conditions, services, infrastructure etc. SDG 11 but also several related SDGs (e.g., SDGs 1, 6 and 7) aim at sustainable cities and communities that are well-serviced. Several recent high-level political events (e.g., the 2023 SDG Summit) stressed that the progress of SDGs is lagging behind. The UN Secretary-General stressed the need for a Rescue Plan for the SDGs. Beyond the slow progress, high uncertainty exists in measuring the progress across many SDGs (e.g., SDGs 11 indicators have been declared as Tier 1 without a scalable and spatial approach). Earth Observation (EO) combined with Geospatial Data have great potential to fill reporting gaps and quantify uncertainties. However, EO data are often not used to their full potential for SDG monitoring, even though many initiatives have opened up EO data and methods to experts on SDG reporting (e.g., the Earth Observations Toolkit for Sustainable Cities and Human Settlements). Within this session, we will reflect on innovations in developing global, scalable and transferable methods to reduce monitoring uncertainties, focusing on LMICs and urban poverty, deprivation and service gaps. Session contributions will present methods that focus on scalability, low cost of data, transferability and the documentation of uncertainties. We will also look into new EO data sources (e.g., SDGSAT-1), multi-source data integration (e.g., citizen science data), and communication of spatially explicit uncertainty measurements. This session will bring experts on different urban poverty-related SDG goals and targets together to allow exchange and discussion about technical solutions and how to increase the impact of EO and GEO-spatial methods. Our session topic is timely and links to the 2025 comprehensive review of the indicator framework. Timely, trustworthy, and open data are essential for global monitoring of the 2030 agenda to support stakeholders involved in the local and national reviews of SDGs and increase access to data for the ongoing development of reporting platforms.

This session welcomes contributions that delve into the practical and theoretical aspects of leveraging causality and/or machine learning techniques, all within the context of the critical role played by Remote Sensing and Earth Observation data. By emphasizing the significance of these technologies, we aim to pave the way for a more sustainable future in agriculture and food security. Specifically, the methodological direction of the session is two-fold.

To drive sustainability, we need to continuously monitor agricultural activity at different scales and answer causal questions for decision making. The ability to properly harness the wealth of information provided by Remote Sensing and Earth Observation is critical. The creation of predictive models that remain consistent and reliable across diverse agricultural landscapes is crucial. Machine learning building on causal principles can lead to the development of this necessary type of geolocation-invariant models. Moreover, Remote Sensing and Earth Observation data provide the foundation material for answering causal questions (i.e. causal discovery in complex environments, causal effect estimation,), which are essential for evidence-based policymaking. This data-rich environment enables us to develop proactive strategies for sustainable agriculture and to establish transparent, accountable agricultural systems.

Towards secure food production, several applications of machine learning in agriculture aims to augment conventional farming practices through automation and the integration of contemporary technologies, thereby mitigating risks, fostering sustainability, and enhancing predictability, ultimately striving to bolster agricultural productivity. Some notable applications of AI within Agriculture 5.0 include monitoring agricultural crop vegetation status and health, automated crop identification, early-stage disease detection, automatic determination of site-specific crop requirements in terms of water and nutrients, formulation of farming strategies pertaining to chemical and mechanical treatment control, and the utilization of AI-based intelligent decision support systems for yield and price estimation. Additionally, the future integration of agri-robots for sowing and harvesting stands as a promising prospect.

In the rapidly evolving intersection of Artificial Intelligence (AI) and Earth Observation (EO), the session titled “AI-DataEng-EO: AI-powered Data Engineering and Reusability for Earth Observation Applications” will focus on the pivotal role of AI in reshaping EO data engineering and promoting data reusability. This session focuses on the application of AI methods, such as representation learning and knowledge modelling and representation, to transform, explain, fuse or otherwise prepare large and complex EO datasets for (re)use in downstream applications. In addition, it will welcome contributions on AI-powered semantic data annotation and metadata enrichment, due to their significance in improving data discoverability, understandability, and reusability, fostering a culture of informed and sustainable data-driven decisions in geoscience and remote sensing. More specifically, a non-exhaustive list of topics relevant to this session is the following: 
1. Data Preprocessing and Enhancement: AI-driven techniques for preprocessing and enhancing Earth Observation data, including noise reduction, feature extraction, and data augmentation.
2. Data Fusion and Integration: Address the challenges and solutions related to integrating data from multiple sources, including satellite, aerial, and ground-based sensors, using AI-based fusion techniques.
3. Time-Series Analysis: AI models and approaches for analysing time-series data from Earth Observation sources.
4. Data Reusability and Open Data Initiatives: AI for complementing best practices for making Earth Observation data more accessible, reusable, and interoperable.
5. Semantic Data Annotation: AI-driven semantic annotation, metadata enrichment and knowledge extraction to improve Earth Observation data discovery and understanding.
6. Data Quality Assessment: AI-driven data quality assessment, anomaly detection, and error correction in Earth Observation datasets.
7. AI-Enhanced Data Products: AI-powered data products and services that leverage Earth Observation data for various sectors.
8. AI for Data Search and Retrieval: Discuss AI algorithms and technologies that enhance the search and retrieval of relevant Earth Observation data from large archives.
9. Data Privacy and Ethics: Ethical and privacy considerations when applying AI to generate Earth Observation data derivatives, including issues related to personal privacy, consent, and data security.

A series of Advanced Land Observing Satellite (ALOS) by the Japan Aerospace Exploration Agency (JAXA) has been continuously operated since 2006 and is currently observed by ALOS-2 for precise observations. ALOS series consists of missions by the high-resolution optical and L-band Synthetic Aperture Radar (SAR) named the Phased Array type L-band SAR (PALSAR). An L-band SAR mission is taken over by ALOS-2 and will be followed by ALOS-4 which is planned to be launched soon. The optical mission was followed by ALOS-3, however the launch failed due to H-3 rocket Test Flight 1 malfunction. As a result, the study of the next-generation high-resolution optical mission has been accelerated, intensive studies are underway within JAXA, and the project is expected to be launched in the near future. The ALOS-4 follow-on mission is also being considered within JAXA, and continuous L-band SAR observations with no gaps in time are expected. The primary mission objectives of the ALOS series are to contribute the disaster monitoring and prevention, national land and infrastructure information updates, and global forest and environmental monitoring which are major research and application themes in geoscience and remote sensing fields. 
In this Community Contributed Session, what should be focused on the ALOS series missions, Cal/Val, science, and applications will be discussed. The summaries of achievements by ALOS and ALOS-2 will be introduced and planned to be conducted by ALOS-4. The perspectives of the future ALOS series missions of both optical and L-band SAR will be discussed based on these results, which may cover the importance of mission continuity, international collaborations, advantages, and disadvantages that should be reflected in future missions.

Many satellite data users lack the expertise, infrastructure, and internet bandwidth to efficiently and effectively access, pre-process, and utilize the growing volume of space-based data for local, regional, and national decision-making. Even sophisticated users of Earth Observation (EO) data typically invest a large proportion of their effort into data preparation. This is a major barrier to the successful utilisation of space-based EO data. This barrier presents a major obstacle to mainstreaming the use of EO data to realise the full value of EO data and is a threat to the success of major global and regional initiatives supported by the Committee on Earth Observation Satellites (CEOS). As data volumes grow, this barrier is becoming more significant for the majority of users. Countries and international organizations have expressed a desire for support from CEOS to facilitate access to and processing of satellite data into “Analysis Ready Data”. Systematic and regular provision of CEOS-ARD has the potential to reduce the burden on global satellite data users and, as a direct consequence, boost data use and it is the first step towards interoperability. In 2016, the CEOS created a definition for CEOS-ARD and subsequently developed a Framework and Product Family Specifications. This session is being organised by CEOS Land Surface Imaging Virtual Constellation (LSI-VC) in collaboration with Geoscience Australia, the United States Geological Survey (USGS), and the European Commission (EC). It aims to share with the international community the latest developments on CEOS-ARD initiative as well as to continue the dialogue with the private sector with the objective of exploring new opportunities and understanding challenges when considering user needs, discovery, and access to CEOS-ARD compliant datasets.

The session will focus on work done by researchers that have used Capella Space Synthetic Aperture Radar (SAR) data. Here is a brief description of the proposed session.

Capella Space provided datasets to a number of researchers for variety of scientific studies. Last year we organized organized a community contributed session to show how very high-resolution SAR imagery positively contributes to study oceanography, geology, disaster management in case of flooding event, sea ice glaciology and amplitude change detection using signal processing and machine learning techniques. 

In 2024, we would like to cover additional studies to show the value that commercial very high-resolution SAR data brings to the Earth Observation remote sensing community. In particular, we aim to present more research works leveraging interferometric compatible images from New Space systems, such as Capella, and to foster discussion about how commercial small SAR satellites can augment other SAR systems, such as TerraSARX, NISAR, Sentinel-1 and RADARSAT-2 / RCM. In this context, we aim to discuss the advantages of having SAR systems launched in mid-latitude inclined orbits or using small satellite systems in bistatic or multi-static configuration.

This session addresses many of the IGARSS 2024 themes such as S/M.1: Spaceborne SAR Missions and S/M.7: New Space Missions, and earth science focused areas such as D/S.5: Risk and Disaster Management, C.3: Sea Ice, as well as methodological areas such as  SAR T/D.14: Change Detection and Temporal Analysis, T/S.2: Differential SAR Interferometry T/S.5: Bistatic SAR.

Atmospheric active remote sensing from space is growing at an exponential rate. Current and upcoming complex aerosol and cloud profiler missions (e.g. CALIPSO-NASA, Aeolus-ESA, EarthCARE-ESA/JAXA, AOS-NASA,  ACLD-CNSA, Aeolus2-EUMETSAT/ESA, INCUS-NASA, Earth-Explorer candidate mission Wivern-ESA) and upcoming constellations of CubeSats and micro-satellites (e.g. Tomorrow IO), will enhance EO-based research to advance our understanding of the role that cloud and aerosol play in the Earth’s radiation budget, while enabling the  optimization of Earth System Models through data assimilation. 
Prior to the exploitation of the new datasets, validation activities are critical to ensure the quality, credibility, and integrity of the Earth observation data. The upcoming missions are foreseen to have several validation challenges, due to the multi-sensor complexity/diversity and the innovation of their standalone and synergistic products. Hence, a clear need arises for establishing best practices in the field of cloud, precipitation, and aerosol profile validation. 
The aim of the session is to promote discussions between scientists towards defining best practices for space-borne aerosol, cloud and precipitation profile products. Additionally, new retrievals and scientific findings  from space-borne profiles are invited. This session is welcoming contributions on all relevant aspects, such as:

Lessons learned from past/recent campaigns/studies
Lidar/Radar Fiducial Reference Measurements 
Cal/Val protocols
Upcoming campaigns and new measurement strategies
Cal/Val needs for current/upcoming Lidar/Radar satellite missions
new profiling retrievals
science applications/findings

The management of increasingly scarce natural resources and the growing severity and frequency of natural disasters constitutes one of the most demanding challenges societies are facing in current times. Exploiting insights from the vast amount of Earth Observation (EO) and Geoscience data through large-scale analytics promises to be one of the key tools to address and resolve this challenge. However, the sheer volume of data required for Earth observational purposes often exceeds the capabilities of existing cloud data centers that usually process much smaller machine-learning benchmark datasets for experimental purposes. We invite the global EO analytics community to collaborate in discussing, conceptualizing, and implementing open-science, open-source distributed computing and distributed machine learning approaches to effectively tackle this challenge. Connecting distributed infrastructures through federation-algorithms will play a crucial role in developing scalable machine learning models to address mentioned and other global challenges.

Geospatial observations aggregate terabytes of data daily. Managing is costly and complex, as it typically spread across different locations and organizations. However, existing deep insights algorithms that provide scientific and business value, require all the data to be co-located in one place, presenting a unique challenge also known as "data gravity". Physically relocating data to a single High-Performance Computing center for integration is extremely costly, time consuming and highly undesired.

There are two distinct alternatives to overcome this large geospatial data challenge. The first is to represent and manage distributed data in a unified way, through data federation. This way not all the data, needs to be transferred, but only the fraction that is needed by locally running models. This approach solves a part of the problem only. The second approach involves training novel distributed algorithms on distributed data "at the edge", i.e. where the data is. Only small amounts of highly compressed data (meta data) needs to be exchanged between locations. This is known as model federation. Notably, the latter approach avoids the expensive and time-consuming process of transferring raw data from one location to another. This method holds the potential to deliver time-sensitive insights efficiently, even within a potentially heterogeneous network of resource-constrained nodes, such as e.g. a network of orbiting satellites.

For this session we welcome submissions concerned with schemes and technologies that facilitate unified views of data and models at the user interface, while underneath, federation and distributed technologies are at work. They may span across, but are not limited to the following areas:

•Space-based data centers,
•Federated learning in Space,
•Distributed Artificial Intelligence in Space,
•Smart compression of satellite data in Space,
•Hyper-parameter optimization of AI algorithms for EO,
•Temporal analysis of EO data in Space,
•Anomaly detection in large-scale EO data,
•Methods and tools for handling large-scale EO data,
•Hardware solutions for in-orbit data centers,
•Hardware acceleration of AI in Space,
•Data storage and transport, 
•Data-access schemes, 
•Privacy and authentication, 
•Model training and execution (inference),
•Model distribution and unification,
•Big data in Space,
•New trends and open questions in big data systems in Space.

In an era characterized by the complex and evolving Health challenges posed by climate change, the intersection of Earth Observation (EO) technologies and Artificial Intelligence (AI) is providing us with capabilities that can lead to new tools to combat and control them. This Session embarks on a comprehensive exploration of the application of AI-enhanced EO technologies that contribute to climate-change-induced diseases, including vector-borne diseases, water-borne diseases, air pollution-related, and heat wave-induced health threats. In this Session we are interested (but not limited) in: 

Development and deployment of early warning systems, aiming to empower communities and health organizations with timely information to mitigate disease outbreaks and prepare for climatic shifts. Furthermore, there is high interest in state-of-the-art explainability techniques, enabling stakeholders to interpret AI-driven insights and decision-making processes and key factors identification.

Additionally, the establishment of reliable and trustworthy AI algorithms is a critical part of the health applications, seeking to enhance the robustness and effectiveness of our health resilience strategies. We are interested in quantifying and measuring the confidence of the AI algorithms and the area of applicability of the AI models.

In the context of climate change, a key component is to understand the evolving dynamics of diseases, their relationship to climatic conditions, and the subsequent implications for public health. Additionally, the Session aims on the exploration of mitigation actions designed to reduce the impact of climate change on disease prevalence and health outcomes.

Both traditional statistical learning and deep learning approaches that relaying on EO data and can provide information useful for health relible applications are welcome on this Session

Cryosphere components such as snow cover, glaciers and permafrost are very sensitive to temperature increase and related atmospheric changes. Remote sensing data offer essential tools to monitor these changes, particularly in large and inaccessible regions such as mountain areas. 
In the last decades retrieval of physical snow parameters and assimilating of EO products into models were advanced and help to get a better knowledge on the status of seasonal snowpack and understanding of the cryosphere. But there are still challenges and gaps to be solved such as the snow in forests and shaded regions, and discrimination between cloud and snow. Moreover, some key snow parameters of large interest such as snow water equivalent, snow depth and quantitative information on snow wetness are still in an early development phase or missing. Accurate and reliable products with attached uncertainty information in this direction will also be useful in model assimilation approaches thus consequently improving model predictions (Zheng et al. 2023).
In this view, the exploitation of the recently launched or upcoming satellite missions based on L-band SAR such as NISAR, SAOCOM and the upcoming Copernicus ROSE-L and the image spectroscopy provided by hyperspectral sensors such as PRISMA and EnMAP and the upcoming CHIME are of utmost important to provide more accurate information on the cryosphere processes.
This session will highlight the main current challenges in the cryosphere monitoring and how these can be addressed with current and next generation of satellites and where gaps remain to be filled with future satellite missions as well as with improvement more accurate and reliable algorithms, including the combination of different sensors.

High spectral resolution lidar (HSRL) is a significant lidar technique for atmospheric and oceanic measurements. Using various optical filters (e.g., Fabry–Pérot interferometer, atomic/molecular absorption filter), it is capable of distinguishing the particle/aerosol scattering spectra and the molecule scattering spectra, which are mixed up in the backscattering lights from the atmosphere or water. Utilizing this principle, the optical properties (extinction coefficient, backscatter coefficient, lidar ratio, etc.) of the objective particles (aerosol and cloud in the atmosphere, phytoplankton in the ocean) could be detected accurately, and then the concentration, the particle type/species could be derived. Moreover, the HSRL can also be deployed as wind detection instrument as it has the capability to detect the Doppler shift in the atmosphere backscattering light. Spaceborne HSRLs provide globally high temporal-spatial resolution aerosol/cloud/wind/phytoplankton observation profiles. This session will focus on the ongoing Chinese HSRL satellite DQ-1 (Daqi-1) to discuss its lidar techniques and applications.
The Chinese atmospheric environment monitoring satellite DQ-1 has been successfully launched on 16 April 2022. As an integrated detection scientific research satellite, it will serve as an important part of Chinese atmospheric environment monitoring system. The DQ-1 is operated in a sun-synchronous orbit at the altitude of 705 km and provides global comprehensive monitoring of atmospheric particles, carbon dioxide (CO2), aerosols and clouds. The DQ-1 equips five sensors including an Aerosol and Carbon Detection Lidar (ACDL), a Particulate Observing Scanning Polarimeter (POSP), a Directional Polarization Camera (DPC), an Environmental trace gas Monitoring Instrument (EMI) and a Wide Swath Imaging system (WSI). As the primary payload among them, ACDL consist of two different modules. One is the aerosol-measurement module which provides aerosols and clouds profile measurements with high accuracy globally, and another is the CO2-measurement module for atmospheric column CO2 observations. The aerosol-measurement module of ACDL is an HSRL with two-wavelength polarization detection, that can be utilized to derive the aerosol optical properties. The aerosol and cloud optical properties products of ACDL include total depolarization ratio, backscatter coefficient, extinction coefficient, lidar ratio and color ratio.

Over the past decade, near-surface geophysics and close-range remote sensing have emerged as pivotal tools in the realms of environmental and urban monitoring. Researchers have dedicated substantial efforts to digitally reconstructing built structures and forestry elements, encompassing buildings, infrastructure, and trees. The resultant information models, including Geographic Information Systems (GIS), Building Information Modeling (BIM), or Computer-Aided Design (CAD), have gained increasing significance in applications such as urban planning, disaster management, sustainability assessment, and forest monitoring.With the fast development of machine learning and deep learning, the current analytical toolkits, spanning from spatial to intelligent analysis, offer potential for profound multi-data integration, enhancing outcomes and engendering more efficient techniques in the domain of land cover and land use detection. However, with regard to near-surface geophysics and close-range remote sensing, this integration remains this integration still remains at a basic level, involving just pixel-by-pixel composition or basic analysis.
Typically, close-range sensing technologies like laser scanning and photogrammetry are harnessed for digitizing manmade objects. This necessitates the unsupervised interpretation of complex scenes and the automated extraction of parameters from a diverse array of domain-specific objects, such as heritage sites, structures, and individual trees. In the last few years, there has been intense research activity towards the automation of this process. However, there is still important work to be carried out involving (i) the collection and processing of close-range sensing data (ii) scene interpretation including semantic segmentation and object detection, and (iii) parameter extraction for the final information models.
This workshop will present new technologies and methodologies that target the above objectives. We welcome submissions that cover but are not limited to the following:
Close-range sensing systems;
Geometric evaluation of mapping systems;
Close-range sensing data structures and models;
Scene interpretation, including semantic segmentation, classification, and object detection;
multi-sensor data fusion.

Coastal interfaces are the nexus of lateral flow and exchange of water, carbon, and sediment between land and sea. They are highly dynamic and complex systems that provide a wide range of ecosystem services, including regulating and maintaining coastal water quality, providing habitat for biodiversity, protecting coastal communities from storms and flooding, and supporting coastal economies through tourism and fisheries.

Earth observation (EO) and geosciences play a vital role in understanding and managing coastal interfaces. EO provides data on a wide range of coastal processes, such as sea surface temperature, chlorophyll concentration, suspended sediment concentration, wave height, and tide height. This data can be used to monitor changes in the coastal environment, identify emerging threats, and develop adaptation strategies.

Geosciences provide a fundamental understanding of the physical, chemical, and biological processes that shape the coastal interface. This knowledge is essential for developing effective management strategies.

EO and geosciences can be used to support the achievement of several Sustainable Development Goals (SDGs), including:
•	SDG 6: EO data can be used to monitor water quality in coastal areas, identify pollution sources, and track the spread of harmful algal blooms. This information can be used to develop strategies to protect human health and coastal ecosystems.
•	SDG 11: EO data can be used to assess the vulnerability of coastal communities to sea level rise and coastal erosion. This information can be used to develop adaptation strategies, such as building seawalls or relocating communities to higher ground.
•	SDG 13: EO data can be used to monitor changes in the coastal environment, such as sea level rise, sea surface temperature, and ice cover. This information can be used to understand the impacts of climate change on the coastal zone and to develop adaptation strategies.
•	SDG 14: EO data can be used to monitor the distribution and abundance of marine life, as well as the health of marine ecosystems. This information can be used to develop sustainable fishing practices and to conserve marine biodiversity.
•	SDG 15: EO data can be used to monitor coastal ecosystems, such as mangroves and coral reefs. This information can be used to develop strategies to protect and conserve these ecosystems.

EO and geosciences play a vital role in understanding and managing coastal interfaces. They can also be used to support the achievement of several SDGs, including those related to clean water and sanitation, sustainable cities and communities, climate action, life below water, and life on land.  

This session is open to papers from a wide range of papers spanning over use of EO data for applications in hydrology, coastal oceanography, biogeochemistry, ecology, and geomorphology. We encourage researchers to submit papers that present new and innovative ideas for addressing the grand challenge of coastal interfaces using EO and geoscience.

The proposed session aims to bring together remote sensing experts, environmentalists, and policymakers to explore the burgeoning domain of predictive modelling under the umbrella of the OneHealth initiative. In particular, the Horizon Europe projectOneAquaHealth is committed to bolstering the sustainability and integrity of urban freshwater ecosystems, elucidating the intricate nexus between ecosystem health and human well-being. The overarching goal is to empower decision-makers with timely and adequate data, facilitating efficacious measures to return the health of aquatic ecosystems and promote the ethos of OneHealth. By harnessing the potential of Artificial Intelligence (AI)-assisted tools, OneAquaHealth seeks to evolve environmental monitoring paradigms, thereby enabling the early identification of warning indicators pertinent to ecosystem health. This session envisages fostering a rich dialogue on how Earth Observation (EO) and Remote Sensing (RS) technologies can be ingeniously leveraged to buttress the objectives of the OneAquaHealth project and the OneHealth initiative. 

Topics for Attendance:
1. Advancements in Predictive Modeling: Delve into the recent advancements in predictive modelling techniques and their application in monitoring of biodiversity, ecological quality, environmental health and restoration of rivers and other aquatic ecosystems. 
  
2. AI-Assisted Environmental Monitoring: Explore the role of AI and machine learning in enhancing environmental monitoring, identifying early warning indicators, and aiding in decision-making processes.
  
3. Earth Observation and Remote Sensing Technologies: Discuss the significance and the innovative applications of EO and RS technologies in understanding and monitoring ecosystem health, specially then urban freshwater ecosystems.
  
4. Interdisciplinary Approaches to Ecosystem Health: Engage in discussions on the interdisciplinary approaches embodying geoscience, remote sensing, and public health domains, fostering a holistic understanding and management of ecosystem health.
  
5. Policy Implications and Decision Support: Examine how predictive modelling and enhanced environmental monitoring can inform policy, support decision-makers, and promote practical measures to restore and sustain ecosystem health.
  
6. Case Studies on OneHealth Initiative: Share and learn from case studies where the OneHealth initiative has been instrumental in restoring aquatic ecosystems and promoting human well-being.

The Copernicus Data Space Ecosystem and DestinE Core Platform, conceived and operated on behalf of the European Commission by the European Space Agency, provide synergetic access to a wealth of vital information on the state of our planet.  
 
Copernicus is the most ambitious Earth observation programme to date. It provides accurate, timely and easily accessible information to improve the management of the environment, understand and mitigate the effects of climate change and ensure civil security. The Copernicus Space Component provides essential data from Space allowing the continuous monitoring of our environment for the benefit of all European Citizens and makes it available via the Copernicus Data Space Ecosystem.   

Copernicus Data Space Ecosystem is the new exploration element of the Copernicus Programme. The Data Space represents a paradigm shift from data distribution via downloads towards in-code API access, allowing processing, filtering, spectral index and zonal statistics calculation, limiting downloads to the resulting information. Therefore, the speed of creating insight is substantially improved and the data volumes to move are drastically reduced. Access is provided through the Copernicus Browser for user-friendly, open and intuitive online viewing, sharing and downloading of the data. In addition, the Data Space provides online coding tools and code libraries with direct access to the data, and in a commercial option, virtual machine processing capacity is made available with Sentinel imagery already on board. The Ecosystem is an open invitation to third parties to create their own complementary value-add services with the available tools and data. It provides a stable, lasting platform for building large-scale operational services, commercializing Earth Observation solutions and educating newcomers to remote sensing.
 
Destination Earth unlocks the potential of digital modelling of the Earth system at a level that represents a real breakthrough in terms of accuracy, local detail, access-to-information speed and interactivity. The DestinE Core Platform will be accessible to a full range of stakeholders from experts, scientists and policymakers to individuals, and will employ novel digital technologies, such as cloud-based supercomputing and artificial intelligence for providing extreme-scale data analytics, Earth-system monitoring, simulation and prediction capabilities. At the same time, it will allow users to customise the platform, integrate their own data and develop their own applications.  
 
This session aims to highlight efforts and opportunities within the Copernicus Data Space and DestinE Core Platform to contribute to a rich ecosystem of advanced applications and services, providing an overview of how they work together and for some of the possibilities for onboarding and federation and empowering users to access and provide actionable information to measure and act to improve sustainability and resilience to the benefit of our planet.  

This is a working session for advancing the IEEE GRSS EO data service.

GRSS is developing the next-generation EO infrastructure for the archival, curation, and sharing of open data and computational resources - for the membership, by the membership. This task responds to the growing need for infrastructure support within the GRSS community, including TCs, Chapters, Global Activities, Industry. Further, it is a response to GRSS strategic direction SD1 EO Data and Compute Resources for Technical Development. Stakeholders of this infrastructure activity include GRSS (to address SD1, increase membership, contribute to outreach); TCs (common platform to leverage); GRSS members (centralized resources - links to publications, data, platform, code); general public (incentive to join, centralized repo and platform), Chapters (platform for sharing/using datasets and training). To start with, as agreed in the December 2021 
AdCom, in 2022 existing cloud platforms and services should be explored and studied, among others.   

This infrastructure is being established utilizing NASA Visualization, Exploration, and Data Analysis (VEDA) tool together with the rasdaman (raster data manager) engine which offers analysis-ready datacube analytics and AI through user-centric APIs. Additionally, via rasdaman the worldwide largest datacube federation, EarthServer, with its 160+ PB of Earth data is integrated.

EO-Cube is a Strategic Initiative of IEEE GRSS implemented by the Earth Science Informatics (ESI) Technical Committee, supported by IEEE GRSS Strategic Initiative funds which is gratefully acknowledged.

Agenda:
- NASA VEDA:  Visualization, Exploration, and Data Analysis (Manil Maskey)
- EO-Cube: The IEEE GRSS Datacube Service (Peter Baumann)
- Moderated Discussion: Co-Designing the IEEE GRSS EO Service (Manil Maskey & Peter Baumann)

It is evident that data has played an important role in driving the advancement of artificial intelligence (AI). While historical attention has primarily focused on the progress of AI models, there is now a growing momentum within the AI community to establish a dedicated platform for discussing the significance of data. This momentum has resulted in data-centric AI concept that addresses the need to systematically manage data throughout the AI lifecycle which includes a spectrum of approaches aimed at the creation, iteration, evaluation, and maintenance of data within AI systems. 

This momentum is equally significant for the Geospatial AI community, which leverages AI to address various geoscience questions, uncover Earth science events, enrich our understanding of physical processes, and drive scientific discoveries.  Additionally, the data-centric AI approach is particularly important in geoscience due to increasing dependency on data-driven methodologies. Given the scale of large Earth science missions and high-resolution numerical model simulations, a data-centric AI framework is crucial for enhancing the returns on these expensive missions and projects. 

While a growing body of literature on data-centric AI exists, the momentum for its adoption within the geoscience community appears relatively slow. To address this, this session will delve into critical aspects of data-centric AI and foster a collaborative environment that gathers a diverse group of geoscience researchers, practitioners, domain experts, data and platform providers, and data/AI engineers. Moreover, this session also seeks to gauge the interest in creating a dedicated venue for the Geospatial AI community to publish their work on data-centric AI. 
 
The discussion topics will encompass, but not be limited to:
-Methods of Earth science data collection, aggregation, and benchmarking
-Frameworks for data governance in the context of geospatial AI
-Implications of data bias, variance, and drift in geoscience AI applications
-Role of data in geospatial foundation models: pre-training, prompting, fine-tuning
-Optimal data strategies for standard evaluation framework amidst evolving model landscapes
-Data-centric explainable AI within geoscience
-Studies pertaining to active learning, data cleaning, and data acquisition for AI in geoscience applications
-Specialized tools and infrastructure designed to support the implementation of data-centric AI approaches in geoscience

Artificial intelligence technologies for Earth observation have been dramatically improved in the last dozen years, during which a set of state-of-the-art methods involving Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Transformers, and the latest fundamental models have been widely studied and exploited for the popular tasks such as object detection, object tracking, semantic segmentation, change detection, super-resolution, and by covering various sectors such as land cover and land use analysis, urban management, security, disaster resilience. Along with the diverse and highly accurate algorithms, datasets and benchmarks are the indispensable ingredients for training deep networks, monitoring the learning process, and evaluating performance. Although numerous datasets have been proposed in recent years, we still urgently need more large-scale datasets for different tasks in different domains, especially at a time when fundamental models are popular. This session will continue last year's focus on datasets and benchmarks, with a preference for those that are large-scale, multimodal, and aligned with sustainable development goals. Firstly, larger datasets provide more comprehensive and reliable insights, leading to more accurate and effective machine learning models. This is because larger datasets allow for more diverse training examples, better coverage of the problem space, and less chance of overfitting (i.e., the model performs well on the training data but poorly on new, unseen data). Secondly, multi-modal data integration can provide richer and more comprehensive information about the Earth's surface and atmosphere by fusing data from multiple sensors, frequencies, and temporal resolutions. Thirdly, we insist that all the efforts in technology and datasets should serve for humans involving improving quality of life, boosting economic development, protecting the environment, and reducing poverty.

Topics include but are not limited to
- Large-scale remote sensing datasets and benchmarks;
- Earth observation datasets and benchmarks with multimodal data;
- datasets, benchmarks, and events relevant to sustainability (climate change, natural hazards, urban sprawl, carbon emissions, poverty, etc.) based on remote sensing data.

In the last forty years plenty of algorithms and solution have been defined for fully exploiting the potential of SAR images and extracting information by SAR data. Therefore, SAR processing has been assessed as one of the main important tools for the Earth Observation. Thanks to their coherent nature and to the ability of working in any meteorological conditions, SAR data are being intensively used for many different applications such as 3D reconstruction, feature extraction, land cover, target recognition, scatterer detection, data fusion and many others, within different domains (urban, natural, marine, etc…). 
In the last years, the SAR processing domain is observing a shift from traditional model-based solution to the deep learning (DL) based one. Indeed, the need of a fast and precise processing of the great amount of data new advanced sensors provide with short revisiting time matches with the versatility, efficiency, and wide applicability of DL methods. The ability of automatically extracting features from the data allow to achieve State-of-Art performance in many fields such as denoising, super-resolution and so on, perfectly fit with the need of a fast and precise processing of SAR images for a continuous Earth Observation.
The actual obtained results are impressive, but many issues are still open for many applications.
The main issue shared by all the DL based method for SAR image processing is the lack of real ground truth to be used as reference for the training. As matter of fact, the lack of ground truth has made many strategies to arise leveraging on synthetic data, processing of temporal series of real data or unsupervised training. This session addresses the issue of the lack of a real ground truth for DL based method within the SAR image processing framework. In particular, it focuses on the actual state-of-art solutions and on new perspective that are arising in all the possible are of SAR image processing: SAR, InSAR, PolSAR and TomoSAR. The aim is to stimulate an open discussion on the presented results and on what is worth to investigate in the near future.

Digital twins are at the frontier of science when we discuss about studying and understanding complex systems and phenomena in our environment. They allow us to experiment in a well-defined environment with our current understanding of various processes and enable us to learn more about how those systems would react to changing conditions. The scientific progress plays an important role here and provides a starting point of a much longer value chain. Many different initiatives at national and international level are currently supporting the development of both necessary technologies for interoperability and exchange of data as well as the setup of digital twins in various domains for starting the modelling process. In Europe alone we have initiatives like Destination Earth, The Digital Twin of the Ocean and the Digital Twins of Environment, all contributing to the scientific progress in this domain. Additionally, many countries are launching their own targeted programs in parallel. This gives great opportunity to progress in this field but is also generating a certain risk for entropy and doubling of efforts. It is hence paramount to enable a dialog between all involved parties and exchange on as many levels as possible, from the design of the underlying software architecture and infrastructures to host those software stacks over the combination of various types of physical based and data-driven models. Questions of data quality and studies of the reliability of results in such complex systems can’t be neglected as well and ask for automated solutions, as well as making sure that the results are distributed following open science principles and the concept of FAIR data.
This session aims at providing an overview of ongoing development and implementations of digital twins in the European research community. It covers both infrastructure and architectural design questions as well as examples of a successful implementation of digital twins in context of Earth Observation and related disciplines.

Exchange on current developments
Harmonization on the architectural design
Discuss interoperability between different implementations
Discuss best practices for implementation and operation of digital twins

The frequency of natural hazards associated with the land, hydrosphere, cryosphere, and atmosphere is increasing.  Such an increase is evident in the mountainous region (like the Himalayas) due to climate change. The glacial lakes in the higher mountainous regions are very sensitive to climate change, the increasing temperature triggers the lake bursts that breach the dams causing floods affecting people living in the foothills and surrounding areas. All kinds of natural hazards occurring in mountainous and coastal areas that are associated with extreme events (precipitation, cloud bursts)  are sensitive to climate change.  The small satellites, and drone sensors together with the ground data are being used to analyze data with the AI/ML for providing early warning, mapping, and recovery plans prior to and after the natural hazards to help the community living in the vulnerable and affected areas. The space agencies are planning for new missions to help the community with the natural hazards. The session invites papers  dealing with the satellite, drone, and airborne data and modeling to provide an early warning, recovery plans, and damage assessment for the benefit of the community in the affected areas.

Recent advancements in the fields of remote sensing, artificial intelligence (AI) and edge computing present intriguing opportunities across various domains of science and industry that stand to directly benefit from in-orbit data processing capabilities. Such real-life applications include, but are not limited to environmental monitoring, precision agriculture, object detection and tracking, detection of natural disasters, extraction of soil properties, and many more. The integration of AI into space-based systems holds the potential to expedite responses to diverse events, primarily due to the rapid transformation of exceptionally voluminous raw data, such as multispectral or hyperspectral images, as well as the Synthetic Aperture Radar data into actionable insights directly within satellite platforms. Consequently, the transmission of such data to ground stations is significantly accelerated and cheaper, thereby offering a substantial scope for scalability in the application of AI solutions on a global scale. Nevertheless, formidable challenges persist, spanning hardware limitations, energy constraints, the utilization of limited computational resources, the scarcity of ground truth data, and the establishment of “trust” in AI-driven solutions. Additionally, (deep) machine learning models deployed on board satellites need to be robust against varying-quality data of potentially changing distribution, and are commonly trained from very limited and not necessarily spatially representative training sets, as real-world ground-truth data do not exist before the satellite is in orbit. Therefore, there have been a plethora approaches utilizing a variety of transfer learning, few-/zero-shot learning, semi-supervised learning algorithms, as well as various data augmentation algorithms to deal with this issue. Overall, to effectively deploy (deep) machine learning algorithms on board satellites, the community still needs to address important challenges related to, among others, the ground-truth data availability, efficient training and deployment of AI models, compressing the models to fit the target hardware which is both computationally- and memory-constrained. 

This session undertakes the above-mentioned challenges of deploying AI on board satellites (and other edge devices), and will welcome submissions spanning across, but not limited to, the following topics:
-	On-board deep learning for Earth observation applications,
-	On-board satellite data compression,
-	On-board band selection and feature extraction,
-	On-board continual learning techniques and tools,
-	On-board algorithm configuration and hyperparameter tuning,
-	Compression of deep learning models for edge devices,
-	Deep learning architecture design approaches for on-board processing,
-	On-board training and fine-tuning of machine learning models,
-	Robustifying on-board AI against low-quality and/or noisy data,
-	Few- and zero-shot learning for on-board AI,
-	On-board image quality enhancement,
-	Multi-modal on-board data analysis,
-	Distributed computing and distributed machine learning in Space,
-	Hardware approaches for accelerating on-board processing,
-	Data-level digital twins for synthesizing training data,
-	Explainable AI for on-board processing,
-	Validation and benchmarking of AI for on-board processing,
-	Examples of industrial, scientific and societal real-world impact of on-board AI.

“The Sustainable Development Goals (SDG) are a universal call to action to end poverty, protect the planet and improve the lives and prospects of everyone, everywhere”. 

The definition of the SDG and the associated Global Indicator Framework represent a data-driven framework helping countries in evidence-based decision-making and in development policies in different domains, being the security and safety of human beings and societies at the heart of the agenda.

In parallel, Earth Observation (EO) is one of the data sources to build-on to address many of these indicators. EO, together with advanced technologies for data processing, such as data fusion or artificial intelligence, enable tools that offer decision-makers enhanced capacity to monitoring, assess and act, incorporating visualization ability which is key to understand a large number of scenarios.

Relevant organizations around the Globe are working in policy and decision-making mechanisms that incorporate information from different data sources, including EO, to face challenges in domains such as food security, water security, energy security or health security, with the final goal of contributing to the achievement of specific SDG indicators. 

However, a big challenge is encountered when some indicators in different domains are interconnected, as it is difficult to be aware and access the most recent insights obtained by the different parties involved. 
Thus, it is necessary to invest and put in place measures to get together current state-of-the-art solutions and results in different domains and raise awareness and foster synergies between key actors. 

This session will focus on current EO-based initiatives and results obtained by key actors in the international stage that are supporting the achievement of several SDG indicators in key domains, aiming at analysing the status-quo in each of the domains, while fostering cooperation and exchange of know-how and capacities. 

The Earth is experiencing unprecedented climatic, geomorphologic, environmental, and anthropogenic changes. Facing the population growth effects, global warming and climate change, the Digital Twin Earth (DTE) provides capabilities to visualize, monitor and forecast natural and human activity on the planet, that contributes to sustainable development and environmental improvement. The global Earth Observation (EO) plays an important role to develop DTE. Among EO sensors, the Synthetic Aperture Radar (SAR), due to the observation capability during day and night and independence on atmospheric effects, are the only EO technology to insure global and continuous observations. SAR, unlike optical sensors, transmits pulsed signals and afterwards receives echoes reflected from objects. The 2-dimensional SAR image is then created by focusing using signal processing techniques, exhibiting the scattering behaviors of the observed field's interactions with the electromagnetic wave.

A deluge of SAR sensors has increased the availability of data for diverse SAR applications. The allure of data-driven learning originates from its ability to automatically extract abstract features from massive data volumes; hence, a considerable number of deep learning researches for SAR applications have been conducted during the past few years. Current popular AI methods predominantly follows the data-driven paradigm, where a large number of SAR data is all you need to drive an intelligent network. This would address the issue of insufficient data, physical inconsistency of the prediction, and lack of interpretability. To this end, it is crucial to develop explainable and trustworthy AI technologies for various SAR applications in the future.

The inherent knowledge and physics of SAR domain contribute to improving the explainability and trustworthiness of AI models. Aiming at various SAR applications, such as SAR/PolSAR/InSAR/TomoSAR..., target detection/recognition/tracking, image classification and segmentation, data generation, 3D reconstruction, etc., we encourage researchers to study and develop explainable, physics-aware, and trustworthy learning methods including but not limit to: physics-aware hybrid model, interpretable deep neural networks, post-hoc explanation algorithms, robust and trustworthy results, uncertainty quantification and explanations, physics-aware generative models, causal inference, etc. These technologies are intended for the next generation of the DTE system.

The Community Contributed Session, “Exploration and Exploitation of New Earth-Observing Satellite Applications for Weather and Climate Science”, will focus on innovative ways to utilize Earth-Observing data from new and existing satellite instruments. Already there is a plethora of Earth-Observing sensors in Geostationary (GEO) and Low Earth (LEO) orbit, managed by a multitude of international organizations that provide extensive datasets of Earth's climate and weather dynamics on both regional and global scales. 
However, such wealth of information is still ripe for additional exploitation, and this session aims to explore novel approaches, concepts and techniques to improve current capabilities and create new applications. Such potentials may include providing high-resolution and short-term forecasting, extreme weather prediction and monitoring, new ways to provide imaging and sounding solutions from existing sensors, and new environmental, hydrological and ecological data products and applications. This may require improved integration of sensors across the electromagnetic spectrum, implementation of more frequent or higher resolution data collection and transmission, and improvements in radiometric and spectral ground and on-orbit references. Other potential ways to achieve this include novel machine learning (ML) and deep learning algorithms for improved environmental classification and prediction applications, improvements in atmospheric composition analysis, and better integration with ground-based systems, including Earth System Digital Twins and data assimilation based on ML. 
In addition, technologies such as Hyper-resolution Imaging, Lidar Systems, Radio Occultation, or emerging technologies like Hyperspectral Sounding, Quantum Sensors, and SmallSats & Constellations will be needed to explore new applications in support of reducing data gaps and have a more comprehensive information of the state of the Earth.
These advancements, in addition to new innovations in how the earth and atmosphere is measured and characterized, can reshape and advance our understanding and current capabilities for weather and climate science goals. It can also provide benefits in terms of more accurate predictions and earlier warnings for localized and extreme weather events, enhancements in data quality, and additional insights into the global environment.

In the Global South, the urban poor living in deprived urban areas, including ‘slums’, are more vulnerable than other urban dwellers to climate-related hazards that can negatively affect their health and wellbeing. This heightened vulnerability stems from various factors, including environmental and morphological conditions at the area level (such as building density and lack of green spaces) and household-level characteristics (such as the type of building materials used and overcrowding). Climate change exacerbates this inequality, particularly with the rise in extreme weather events like heat waves.
In this session, innovative Earth Observation methods and advancements for modelling, mapping, and quantifying the urban population exposed and susceptible to extreme heat hazards will be presented, with a focus on deprived areas. AI models utilising Earth Observation, open geospatial data and Citizen Science data for fine-grained mapping of urban air temperature, population distribution and deprivation will be showcased. The contribution of local communities to the process and their active participation will be emphasised. Additionally, specific challenges faced in this field of research will be discussed, such as limited data availability, limited access to the field, and the necessity for cost-effective and scalable methods.
Urban thermal inequality in the Global South must be put on the map and quantified to support advocacy efforts, facilitate dialogues between communities and local governments, and develop practical adaptation measures. This research aligns with Sustainable Development Goals (SDGs) 1 (no poverty), 3 (good health and wellbeing), 11 (sustainable cities and communities) and 13 (climate action). Its outcome has the potential to favour community-based initiatives involving simple, local, low-cost solutions, including those rooted in nature-based approaches.

The EY Open Science Data Challenge is in an annual competition for students and early career professionals interested in AI solutions to address global sustainability issues. Participants are provided with satellite data and are asked to build machine learning models focused on one of the United Nations Sustainable Development Goals (SDG). Since 2021, EY has focused the challenge topics (e.g., fire detection, biodiversity species distribution, rice crop yield forecasting) on geoscience issues and Earth remote sensing datasets. 

For 2024, the challenge is focused on coastal resilience. Some of the most vulnerable areas to climate change are low-lying coastal zones in developing countries and small island states. Coastal zones are characterized by narrow stretches of land that host critical ecosystems, infrastructure, and economic assets, often with conflicting interests and uses. Characterizing the environmental and socioeconomic exposure at local scales, and changes over time, is becoming increasingly critical for the sustainable management of coastlines, planning adaptation to the impacts of climate change, and the management of other climate risks. 

The primary goal of the challenge will be to develop baseline data products for coastal resilience in data-poor environments (e.g., Caribbean, Pacific Islands) through classification models that identify coastal infrastructure and ecosystems at local scales using satellite data and machine learning algorithms. A secondary goal of the challenge is to develop a practical disaster response plan that uses these models and uses generative AI to build a sample climate risk plan that considers other potential datasets (e.g., topography, population, socioeconomic) to address future coastal vulnerability to tropical storms. 

This session will present a summary of the EY Open Science Data Challenge and papers from the three international finalists.

In an era where space exploration and applications are transitioning from government-led endeavors to multi-stakeholder ventures, optimizing funding is paramount. Input will be sought from various stakeholders of the Space Domain, such as Space Agencies, leading firms in the field and research institutes that will attempt to illuminate the intricate web of financing mechanisms available – from national funds and venture capital (VCs) to European Space Agency (ESA) contributions.  

This session delves into the diverse funding mechanisms fueling groundbreaking research and operational infrastructures. By examining the intersection of national and international cooperation programs, this session unveils the transformative potential of collaborative efforts towards Space innovation and excellence.  

Key areas of discussion include the strategic exploitation of flagship programs, enabling a seamless fusion of technology, research, and investment. The session highlights how these programs serve as catalysts, propelling innovation, and scientific inquiry forward. Moreover, it addresses the critical engagement of users, sectors, and decision-makers, emphasizing the importance of inclusive collaboration. From public-private partnerships to innovative funding models, the session sheds light on creative financing approaches that empower the space industry to flourish. 

Participants can expect in-depth analyses of success stories, challenges faced, and lessons learned, providing invaluable insights for future endeavors. By showcasing exemplary models of collaboration and funding, this session inspires stakeholders to invest in cutting-edge technologies, shaping the future landscape of space exploration and services. 

Agriculture is directly affected by the ever-increasing frequency of weather extremes. In a changing climate, heavy precipitation events, droughts, flash-floods, prolonged periods of temperature extremes (heatwaves / frosts) that are occurring more often and are more intense, can destroy a year’s yield on a broad spectrum of crop types. The repetitiveness of damages from weather perils in many cases is threatening to the economic viability of the farmer.
In many of those instances, however, consequences can be mitigated or even reduced to a minimum if early warning systems are available and information is timely and effectively communicated to the farmers. For that to happen, distilled information from every available source needs to emerge through novel and easy to understand tools that denote both the current state in detail as well as provide a trustworthy reachout for the near future. Services that consult on the optimal seeding time, raise alerts along the cropping season for perils that can be counterbalanced so as to avoid excessive damage (e.g. adjustments in irrigation, optimal use of pesticides, etc) and even consult of the associated risk as the harvest approaches, that can protect the effort of a whole cropping season.
In recent years, a number of such services have been utilising the best of what numerical models, earth observational datasets and in-situ instruments have to offer, while in some cases hybrid approaches blend two or more of these worlds together. This session aims to showcase such exemplary attempts that help to pave a safe path towards a more sustainable agriculture in a changing climate and reduce the impact to food chain and food security.

Planetary geology studies and the understanding of outer space exotic worlds is largely based on analyses of various remote sensing data acquired by space missions. Space borne remote sensing is fundamental in understanding the formation and evolution of planetary surfaces and of their shallow subsurfaces. The surfaces of the terrestrial planets and their satellites have been largely shaped through volcanic and tectonic processes. Extreme conditions on outer solar system bodies, such as the Jovian, Saturnian, and ice giant satellites, result in different types of volcanism and tectonism. Fracturing and faulting processes mainly affect minor bodies such as asteroids and small moons, where volcanism and tectonism have not played an important role. We invite contributions that cover a wide range of topics including geomorphology and composition of volcanic deposits, edifices, and plumes, volcano-induced deformation and edifice growth and collapse to tectonic structures, faulting and fracturing processes, crustal stress and strain analysis, cryovolcanism, and any study related to planetary endogenic processes. Furthermore, studies that relay interactions between planetary interiors, surfaces, and atmospheres are welcome. Comparative studies of volcanic or tectonic systems on Earth with a strong remote sensing component are encouraged, as well as studies on terrestrial analogues that help understanding the working mechanisms of outer space bodies and vice versa. 

Climate change, through consequences such as global warming, rising sea levels, extended dry seasons or floods, acid rain, heavy storms, is threatening our cultural heritage and affecting our cultural landscapes. Safeguarding and protecting cultural heritage from the effects of climate change and natural hazards is urgent.  There is a pressing need to explore and test innovative ways to monitor and protect monuments, historical buildings and sites from climatic risks and natural hazards. Today, Earth Observation data has the potential to provide enhanced monitoring of heritage sites over time leveraging on several technologies and techniques: ground penetrating radars (GPR), global navigation satellite systems (GNSS), LIDAR, Sonar, unmanned aerial vehicles (UAV), Autonomous Underwater Vehicles (AUV), Multispectral, Hyperspectral, SAR and 3D Remote Sensing techniques, artificial intelligence, machine learning and deep learning. A multi-source integration of space-based data and in situ observations is essential in this regard to obtain high level products and provide advanced information about ongoing risks at underwater, coastal, urban heritage sites but also cultural landscapes.
This session focuses on recent advances that contribute to the protection of heritage exposed to climatic, natural, and anthropogenic hazards. Contributions may include the development of remote sensing methods and techniques, models (including 3D models), laboratory tests and field applications to enhance the ability of heritage and connected communities to withstand and adapt to the era of extreme events. Potential contributions include, but are not limited, to the following:
•	Innovative prototypes, models and algorithms that advance monitoring and contribute to fundamental understanding of the effects of climate-change and natural hazards on cultural heritage 
•	Machine learning and artificial intelligence methods to identify, quantify and mitigate risks derived from natural, climatic, anthropogenic and biological hazards, including both single- and multi-hazard scenarios, at various types of heritage.
•	Aerial, ground, underwater, as well as integrated sensing solutions for monitoring heritage risks.
•	Advanced methods, including differential interferometry and time series processing, for monitoring ecosystems to assess risk for expected and unexpected events and assess their impact at heritage.
•	Early warning and decision support systems powered by remote sensing data to optimize heritage management.

•	Material characterization and advanced prediction capabilities for heritage deterioration.
•	Data fusion methods that enhance the development of high-performance earth observation “data cubes'' for a given cultural heritage location or epoch

Artificial Intelligence (AI) applied to remotely-sensed data, particularly satellite images (like hyperspectral and multispectral images, HSI and MSI), plays a crucial role in environmental monitoring. It enables timely actions to mitigate gas emissions, identify unexpected emitters (e.g., methane sources), monitor inland water quality, extract soil parameters, and estimate pollutant data for large areas. These applications extend to scenarios requiring rapid responses and present unique challenges. Detecting and assessing floods is complex due to the environmental effects of water in affected regions. On the other hand, wildfires are natural threats that devastate ecosystems and have far-reaching socio-economic consequences. Fire behavior depends on factors such as fuel type, flammability, quantity, climate change, topography, and wind conditions. Traditionally, fire area estimation relied on field methods using GPS data, but this approach could only determine the perimeter of the hazardous area. It also faced challenges due to inaccessibility and changing fire dynamics over time. Remote sensing technology, particularly MSI/HSI, provides a more comprehensive solution. It may be exploited to extrat changes over time, enabling the identification of active fires, burned areas (also with decreased chlorophyll content), and potential fire resurgence (partial fuel burnout). This method offers advantages over traditional techniques that only consider the perimeter. Additionally, it allows for continuous monitoring of fire evolution and early detection. Volcanic ash, a consequence of eruptions, poses various threats, including air and water pollution, climate impact, and aviation safety risks. Monitoring and forecasting volcanic ash clouds are of paramount importance, as dust from volcanic eruptions can lead to respiratory diseases and water contamination. Satellite remote sensing surpasses ground-based methods as it eliminates the need for installing instruments in remote and hazardous areas. These examples illustrate the societal benefits of effectively leveraging AI for analyzing satellite data. Whether onboard satellites or on the ground, AI accelerates data analysis and facilitates the extraction of actionable insights from raw satellite data. There are, however, several important challenges directly concerned with the characteristics of the data and – among others –  ground-truth data availability, representativeness and generalizability for specific environmental applications. This session addresses the challenges in deploying AI for environmental monitoring and designing data-driven algorithms in this context, welcoming submissions on a range of related topics.

-	Classic and AI algorithms for environmental applications,
-	Data-level digital twins for synthesizing training data for environmental purposes,
-	Few- and zero-shot learning for training AI algorithms,
-	Leveraging Big Data and unlabeled data for environmental monitoring,
-	Training AI algorithms from weakly-labeled remotely-sensed datasets,
-	Greenhouse gas detection and monitoring from satellite images,
-	Methane plum detection and segmentation,
-	Monitoring floods and wildfires from satellite data,
-	Bare soil detection and soil analysis from satellite data,
-	Air quality analysis and monitoring from satellite data,
-	Detecting and tracking industrially-induced pollution from satellite data,
-	Multi-modal satellite data analysis for environmental applications,
-	Validation of AI algorithms for environmental applications,
-	Examples of industrial, scientific and societal real-world impact of AI for environmental monitoring.

Climate variability and ballooning populations are putting unprecedented pressure on agricultural croplands and their water use, which are vital for ensuring global food and water security in the twenty-first century. In addition, the COVID-19 pandemic, military conflicts, and changing diets have added to looming global food insecurity. Therefore, there is a critical need to produce consistent and accurate global cropland products at fine spatial resolution (e.g., farm-scale, 30m or better), which are generated consistently, accurately, and routinely (e.g., every year). 

This community contributed session (CCS) will bring together scientists involved in global agricultural cropland mapping at highest known resolution (30m or better) using Earth Observation (EO) data in support of world’s food and water security analysis. The session will focus on paradigm-shift in producing myriad global cropland products involving multiple satellite sensor derived petabyte-scale big-data analytics of the Planet, artificial intelligence (AI), machine learning/deep learning (ML/DL), and cloud computing on platforms such as the Google Earth Engine or Amazon Web Services (AWS). The session will present and discuss various global cropland products such as cropland extent, watering method (irrigated or rainfed), cropping intensities, crop types, and crop water productivity produced using EO data at highest known resolution.

GPM is an international collaboration between NASA, JAXA and other international agencies. The GPM mission represents significant advancements in engineering for the satellite’s active radar and passive radiometer instruments. Global precipitation observations at fine temporal and spatial scales provided by GPM lead to scientific advancements and societal benefits. This session will provide details of GPM engineering, and instruments, (first half session) and science and retrieval algorithms (second half session) with emphasis on  extreme events and applications. The GPM mission has touched a large community of scientists, engineers and users and this special session will represent a broad sample  from this group.

We propose a 2-part session focused on recent advances made for modeling GNSS reflectometry, considering land, ocean, and physically informed retrieval, in the frame of the activities of the GNSS-R Modeling Subgroup of the Modeling In Remote Sensing (MIRS) technical committee of the GRS society. 
Part 1 is focused on land and ocean applications and it aims at giving a picture about the state of the art of research and their impact on data processing and understanding. Part 2 aims at investigating connections among modeling aspects and applications, with a focus on physics-informed machine-learning retrieval. 

The potential of GNSS reflectometry has attracted increasing research interest in the last two decades, which stimulated technological demonstrations and  new space missions. As a matter of fact, the use of signals GNSS reflected by land has attracted scientific and industrial interest. The possibility of characterizing wind fields over the ocean, soil moisture, vegetation biomass, the freeze/thaw state of the soil at higher latitudes, is now consolidated. Many research groups are currently involved in studies based on the exploitation of data produced by the NASA CyGNSS mission, whilst the preparation of the HydroGNSS mission is getting closer to the launch, scheduled in late 2024. 
Significant progress has been made in understanding the physics describing the interaction between navigation signals and bio-geophysical parameters, but improving accuracy and sensitivity of the signals scattered around the specular direction demands further efforts.

Established approaches for retrieving critical geophysical and biophysical parameters from remote sensing observations exploit our understanding of physical processes through appropriate mathematical electromagnetic modeling like radiative transfer models. These models are fundamental in interpreting the interactions between electromagnetic energy and atmospheric/geological components and lay the groundwork for accurate parameter retrieval. While such methods can achieve impressive performance in numerous tasks, from soil moisture estimation to surface temperature retrieval, they rely heavily on specific assumptions and an appropriate selection of parameters. At the same time, data-driven approaches based on machine learning (ML) have demonstrated exceptional performance in numerous remote sensing retrieval tasks, leveraging the available data that can be employed for training such models. Yet, the data-hungry nature of ML models poses a significant hurdle, especially in scenarios where obtaining copious amounts of high-quality real-world observations is impractical or impossible, which is typically the case in remote sensing-based retrieval.
This session focuses on ML methods of retrieval that combine physical models and data-driven ML approaches. Examples of such synergies include but are not limited to the following topics:
·       Integration of physical constraints into ML-based retrieval;
·       Training of ML architectures using simulations from physical models;
·       Physics-constraints time-series analysis, including forecasting;
·       Fusion of physical and ML models for geophysical parameter retrieval and analysis;
·       Data-driven parameter selection for physical models;
·       Training of ML methods using in-situ observations and data assimilation estimates;
·       Development of Analysis Ready Datasets for ML model optimization.

The expectation is that the integration of physical models and ML models will significantly enhance the quality of geophysical parameter retrieval by reducing the impact of training data availability for ML-based methods and enhancing the quality of derived products in terms of retrieval accuracy as well as spatial and temporal resolution. The proposed CCS is aligned with the concerted efforts of the Modeling in Remote Sensing Technical Committee (MIRS TC) of the IEEE Geoscience and Remote Sensing Society (GRSS).

Hyperspectral data is entering into a new era of more available data than ever before. But without proper calibration and validation of these data, they can't be compared to other sensors, spectral libraries, used to make precise measurements, and ready to use for citizen science. While there are more sensors only so many can cover enough of the earth's surface for users who need high temporal coverage.  Another goal of this session is to address users working with multiple hyperspectral sensors and how to ensure best comparison between sensors. This session will provide a forum for commercial and government organization to show their cal/val process, innovative new techniques for cal/val, cross calibration of sensor constellations, and cross calibration of sensors outside of their constellation. The discussion section will focus on how to improve collaboration with different sensors and team and encourage engagement in the forming GSIS calibration, validation working group.

Currently there are more hyperspectral sensors on orbit than ever before. There are new launches planned for 2024 and there are improvements planned planned calibration/Validation for in existing sensors.  This session endeavors to provides the hyperspectral community a latest update on the state of commercial and government hyperspectral systems, collective efforts between different systems as well as government and commercial collaboration. Future systems to be launched in the next 2-3 years will also be considered so as to inform the community of what is coming. Small Satellites / and multiple satellite constellations present new and unique challenges, how are these challenges being addressed and how will multi hyperspectral satellites interact with single mission sensors?  Lastly the discussion section will focus on how best to work together, get data to users and how the community will need to evolve with the presence of new sensors.

Modern High Performance Computing (HPC) architectures and parallel programming models have been influenced by the rapid advancement of Artificial Intelligence (AI) and hardware accelerators, such as GPUs and FPGAs. Classical workloads on HPC systems, like numerical methods based on physical laws, are increasingly becoming heterogeneous. This trend is further amplified by the swift development of novel quantum technologies, algorithms, and applications.
Quantum Computing (QC) introduces an innovative approach to computing, drawing on the principles of quantum mechanics. From an HPC standpoint, QC demands integration on multiple fronts. At the system level, quantum computing technologies must be incorporated into HPC clusters. At the programming level, the revolutionary ways of programming these devices necessitate a comprehensive hardware-software stack. And at the application level, QC is poised to cause major shifts in the complexity of certain applications, potentially making previously compute-intensive or intractable problems in the HPC realm solvable in the future.
The European High Performance Computing Joint Undertaking (EuroHPC JU) has selected six sites in the European Union (EU) to host quantum computers, utilizing various technologies and architectures. This initiative necessitates the fusion of new scalable software engineering techniques with "classical" HPC at both hardware and software tiers. Quantum programming languages are designed to control specialized physical devices, making coding and code verification an emerging discipline closely tied to the nature of data and applications. The creation of quantum circuits is facilitated by "classical" programming, simulators, or Python. Outcomes are derived either from simulators operating on the user's device or through quantum software development kits.
These tools require modifications to cater to the needs of the Geoscience and Remote Sensing Society (GRSS) domains, as well as specific quantum complexity classes. This session invites discussions on specialized topics that intersect HPC and QC, particularly those that influence applications in the GRSS domain. Applications in GRSS confront the challenges posed by big data originating from Earth observation, geological surveys, environmental data, and other similar heterogeneous datasets. Currently, cutting-edge methods are being executed in Data Centers dedicated to remote sensing, climate monitoring, and oceanic observations.

The last few years have seen many advances in quantum resources that can be applied to Earth Observation, especially in quantum communications and quantum sensing. Although the development of quantum computing systems has been slower and is not as mature, quantum computing holds big promises for advancing artificial intelligence, especially Machine Learning. These advances will be essential for speeding up the processing, analysis and ingestion of data into science and human models as well as for running surrogate models that will be the core of what-if investigations in future Digital Twin systems, and therefore will support Sustainable Development Goals such as "Climate Action". This session will explore the development of novel Quantum Machine Learning frameworks and algorithms for processing and analyzing Earth observing data. This includes quantum-assisted and quantum-inspired algorithms as well as theoretical analyses, simulations and preliminary results obtained on actual quantum computing systems. The papers may address the main topics of quantum algorithms design: classical data embedding into quantum states, quantum state transformations, quantum circuits design, quantum state measurement, quantum machine learning or neural networks, as for instance. If not theoretical, the methods are expected to be implemented on actual quantum computers such as the DWave quantum annealer or IBM and results should be benchmarked vs. the “classical” counterparts. Applications dedicated to the special interest indicated for IGARSS 2024, “Acting for Sustainability and Resilience” are very much welcome.

Recent advances in remote sensors, offering higher spectral, spatial, and temporal resolutions, have led to significantly larger data volumes. This poses challenges in processing and analyzing the massive data promptly to support practical applications. Concurrently, the development of computationally demanding algorithms and methods, such as Machine Learning (ML) and Deep Learning (DL) techniques, necessitates parallel implementations with high scalability performance. As a result, parallel and scalable computing architectures and algorithms have become essential tools for addressing challenges in geoscience and remote sensing applications. In recent years, both high-performance and distributed computing have seen rapid advancements in hardware architectures and software. For instance, the popular graphics processing unit (GPU) has evolved into a highly parallel many-core processor, boasting immense computing power and high memory bandwidth. Furthermore, the evolution of High-Performance Computing (HPC) architectures and parallel programming has been shaped by the swift progress of DL and hardware accelerators, like modern GPUs. This community session on scalable parallel computing for remote sensing aims to gather papers on cutting-edge and trending areas, focusing on leveraging the newest high-performance and distributed computing technologies and algorithms to expedite the processing and analysis of vast remote sensing data.

The Image Analysis and Data Fusion Technical Committee (IADF TC) yearly organizes the IEEE GRSS Data Fusion Contest, an open competition based on freely provided multi-source data and aiming at stimulating the development of novel and effective fusion and analysis methodologies for information extraction from remote sensing imagery. Similar to the last few years, the 2024 edition of the contest is planned to include a competition based on the performance of developed approaches on the data released. The developed algorithms will be ranked based on their performance accuracy, and the winners will be awarded during IGARSS 2024, Athens, Greece.


Following the same approach as in the 2016-2023 editions of the DFC and IGARSS, the IADF TC is proposing the present CCS that is aimed at timely presenting the most effective and novel contributions resulting from the competition. A session is proposed, in which the best-ranking submitted papers will be presented, and two slots will be used by the contest organizers to summarize the outcome of the competition. According to the schedule of the contest, the session is currently proposed without explicitly mentioning speakers and tentative titles but will be filled in after the competition is completed. It is worth noting that the corresponding papers would not go through the submissions of regular papers but would be reviewed directly, in full paper format, by the Award Committee of the Contest. This process will ensure both thorough quality control and consistency with both the timeline of the contest and the final paper submission deadline to IGARSS 2024.

The Image Analysis and Data Fusion Technical Committee (IADF TC) yearly organizes the IEEE GRSS Data Fusion Contest, an open competition based on freely provided multi-source data and aiming at stimulating the development of novel and effective fusion and analysis methodologies for information extraction from remote sensing imagery. Similar to the last few years, the 2024 edition of the contest is planned to include a competition based on the performance of developed approaches on the data released. The developed algorithms will be ranked based on their performance accuracy, and the winners will be awarded during IGARSS 2024, Athens, Greece.


Following the same approach as in the 2016-2023 editions of the DFC and IGARSS, the IADF TC is proposing the present CCS that is aimed at timely presenting the most effective and novel contributions resulting from the competition. A session is proposed, in which the best-ranking submitted papers will be presented, and two slots will be used by
the contest organizers to summarize the outcome of the competition. According to the schedule of the contest, the session is currently proposed without explicitly mentioning speakers and tentative titles but will be filled in after the competition is completed. It is worth noting that the corresponding papers would not go through the submissions of regular papers but would be reviewed directly, in full paper format, by the Award Committee of the Contest. This process will ensure both thorough quality control and consistency with both the timeline of the contest and the final paper submission deadline to IGARSS 2024.

The continued success of remote sensing across various applications, from semantic map production to environmental and anthropic area monitoring, hazard management, and more, has driven the development and deployment of state-of-the-art sensors capable of providing diverse insights into the Earth's condition. These sensors offer data in various modalities, spanning different types of imagery such as optical, hyperspectral, and synthetic aperture radar, as well as other data formats like Lidar point clouds and precise positioning information via GNSS. While early remote sensing efforts and research predominantly focused on individual sensors, contemporary approaches, notably those rooted in machine learning, seek to integrate data from multiple sources as they often offer complementary insights. Today, an even broader array of data sources is available, including crowd-sourced photographs, oblique images, and data from social networks, opening up novel avenues for tackling the most complex challenges in Earth monitoring and comprehension.

Despite the abundant availability and advantages of multimodal data, which encompasses multi-sensor, multi-frequency, and multi-temporal data, the analysis and fusion of information from these sources remain a complex and continuously evolving research frontier. Modern AI strategies founded on deep learning are at the forefront of enabling effective image analysis and multi-sensor data fusion. As a result, image analysis and data fusion have emerged as vibrant and dynamic research domains, characterized by a substantial demand for knowledge exchange, discussion of ongoing challenges, introduction of new datasets, and the proposal of innovative solutions.

The Image Analysis and Data Fusion Technical Committee (IADF-TC) of the Geoscience and Remote Sensing Society is dedicated to addressing these challenges. Its mission is to facilitate connections among experts, provide educational resources for students and professionals, and promote best practices in the realm of image analysis and data fusion applications. Among its various activities, the IADF-TC organizes an annual community-contributed session held during IGARSS, where it assembles the latest and most cutting-edge contributions in research areas such as machine learning, decision fusion, multi-modal data fusion, pan-sharpening, data assimilation, and multi-temporal data analysis.

This proposed session boasts a long and successful history within IGARSS, consistently held for over a decade. As a well-established session, it garners the full attention of both senior researchers and young scientists. Furthermore, it addresses topics of increasing significance in remote sensing and geoscience, appealing to an interdisciplinary audience with interests spanning methodology and application domains.

The exponential increase in earth observation data demands systems that are not only scalable and efficient but also compliant with FAIR (Findable, Accessible, Interoperable, and Reusable) principles and Open Science Initiatives from government agencies. Addressing these challenges require a multi-pronged approach that includes (but not limited to):

Enhancing remote sensing data search and discovery through semantics, ontologies, knowledge graphs, and language models.
 Advancing cloud-optimized data systems and data products.
Developing innovative data storage and access frameworks tailored for both general geospatial analysis and machine learning applications.
 Building innovative dashboards that leverage next-gen data systems to increase engagement and data value.

These advancements serve to increase visibility, streamline data access, searchability, and manage the accelerated volume and velocity increase of remote sensing data. Consequently, they encourage broader data utilization and re-utilization, benefiting not only the remote sensing community but also citizen scientists and machine learning researchers. This session welcomes presentations that illuminate how these or related technologies contribute to building more robust and accessible remote sensing data systems.

High-resolution thermal Earth Observation (EO) images play a key role in contributing to the development of innovative approaches and methodologies useful for both the scientific and user communities across a broad field of applications. Over the next few years further substantial progress and development are expected in high resolution thermal Earth Observation (EO), considering the planned new space thermal missions, such as NASA-ASI SBG-TIR, ESA-EC LSTM, CNES-ISRO TRISHNA missions and other missions that include thermal infrared sensors. The ECOSTRESS mission (NASA) is providing excellent precursor data for these upcoming missions. The high spatial, spectral and temporal resolution of thermal data allows for the retrieval of a valuable source of information about geophysical parameters fundamental in the monitoring of natural and anthropogenic changes to the ecosystems. Land surface temperature is a key variable needed for understanding and adapting to climate variability, managing water resources sustainably for agricultural production (e.g. irrigation), mitigating health stress during heatwaves (together with evapotranspiration), predicting droughts, monitoring coastal and inland waters and addressing natural hazards such as fires and volcanoes, etc.
In this sense, the present session aims to let the scientific community to present their innovative applications in the different domains mentioned above in order to strengthen the international cooperation, coordination and synergies of research and among the upcoming high-resolution thermal missions.
To this purpose, as a Community Contributed Session, the session will couple solicited talks with open-call contributions submitted by scientists of the whole Geoscience and Remote Sensing community working with EO developing thermal missions.

Earth Observation (EO) applications for emergency management and security are key to institutional users for assessing risks, responding effectively to events and delivering wide situational awareness. 
As the number of actors in the satellite imagery market is increasing and the opportunities for image collection are proliferated, various technical challenges emerge (e.g. data fusion, trustable automated image analysis, etc). 
Taking into account the aforementioned motivations, and building in the outcomes of previous IGARSS editions, the session aims to bring together applied scientists as well as actors in industry and national or European institutions which develop, deliver and/or exploit image analysis-based geospatial services in operational domains. The session will focus on the use of EO and other collateral data for geospatial applications in emergency and security operations, including a wide field of relevant themes:
-	Operational automatic detection and extraction of various features, including road network, buildings, vessels, vehicles, etc.
-	Post-disaster and/or post-conflict impact assessments, e.g. detection of damaged buildings
-	AI-assisted end-to-end UAV operations
-	Human-in-the-loop algorithms for imagery intelligence
-	Cascading-risk impact on emergency and security scenarios, e.g. impact of floods in traffic of hazardous goods  
-	Conflict/emergency risk indicators and maps

Finally, we also welcome papers addressing meta-analyses of the impact and uptake of these technologies in operations, as well as lessons learnt from deploying these technologies in operational environments. 

This session expands on the latest results from cross-disciplinary observations from space and ground measurements associated with major geohazards: earthquakes, volcanoes, and space weather. It advances the existing interdisciplinary studies of the Earth's EM environment associated with lithosphere-atmosphere-ionosphere coupling (LAIC) and other processes. It was recognized that satellite technologies provide new opportunities never achieved before to study the geospheres coupling associated with geohazards from space. Results from the latest satellite missions Swarm (ESA, 2013), CSES1 (China/Italy, 2018), and FORMOSAT-7/COSMIC-2 (Taiwan/USA, 2019), which were explicitly designed to investigate ionospheric anomalies related to geohazards and space weather will be presented. The presentations will feature a multi-instrumental approach to global EM observations. Data from LEO satellites can provide a global view of near-Earth space variability and complement ground-based observations that are limited in global coverage. Using ground-based observations and LEO satellites, we consider a wide range of observable Earth EM environment activities. Such activities as - thunderstorms, lightning, TLE, geomagnetism, and space weather can help clarify the missing scientific knowledge about earthquake processes and significant volcanic eruptions. The session talks will include but are not limited to the latest major geohazard events, such as the 2023 Earthquake in Morocco; modeling and analyses; geochemical, electromagnetic, and thermodynamic processes; and case histories relating to stress changes in the lithosphere, geohazards, and space weather. 

Main topic: Land cover and environmental monitoring of the Earth's surface based on satellite and aerial data.
-	applications on regional, national and global scales;
-	demonstration of new LC classification techniques;
-	classification of optical and SAR data, 
-	processing of time series, change detection;
-	aggregation of satellite and aerial data.

Land cover is the basic and main important information collected by remote sensing techniques. Almost all topics related to environmental monitoring use land cover information derived from optical and SAR images collected from satellite and aerial levels. 

Since forest structure is of great value to terrestrial ecology, habitat biodiversity, and global carbon storage assessments, it is desired to monitor and quantify the state of, and change in aboveground biomass and forest height (that well correlates with biomass) along with other forest biophysical characteristics. It is important to generate large-scale (e.g., state,  continental, and global) moderate-resolution (e.g., few hectares down to sub-hectare) products of forest aboveground biomass and forest height. Forest height is not only a carbon storage metric that well correlates with biomass but also a critical variable identified by international forest monitoring efforts such as Global Observation for Forest Cover and Land Dynamics (GOFC-GOLD), Global Forest Observations Initiative (GFOI), and programs such as the United Nations’ Reducing Emissions from Deforestation and Forest Degradation (REDD+) programme. This information can also support efforts aimed at quantifying biodiversity, particularly given the rapid declines and losses of many plant and animal species world-wide.

To address this scientific goal, the remote sensing community has been working towards combining multi-sensor measurements, such as Synthetic Aperture Radar (SAR) and lidar. For example, these include JAXA's ALOS/ALOS-2/ALOS-4 (single L-band SAR) and MOLI (lidar) missions, NASA'S NISAR (single L-band SAR) and GEDI (lidar), DLR's TanDEM-X (twin X-band SAR), ESA's BIOMASS (single P-band SAR) as well as China's LT-1 (twin L-band SAR) and TECIS (lidar). Other spaceborne passive optical sensors including NASA’s Landsat and ESA’s Sentinel-2 have also been successfully combined with lidar missions for large-scale forest height mapping.

SAR has the capability of all weather and day/night observation. In the fusion observing scenario, the high spatial and temporal resolution of radar would be combined with the high confidence of vertical structure, yet more sparse coverage, measured by lidar and/or passive optical sensor. It is obvious that radar (and passive optical) missions have complete spatial coverage with good spatial resolution; however, the interpretation of the radar data is more difficult leading to a moderate accuracy in measuring the vertical structure. In contrast, the lidar mission has a sparse spatial coverage with small footprint size while the lidar data interpretation is much easier than radar resulting in a much better vertical confidence. Therefore, this proposal will demonstrate a few novel ways to combine the complete spatial coverage of radar and precise vertical measurements of lidar so that large-scale (potentially global-scale) forest height/biomass maps can be generated. In particular, it is desired to develop novel scientific algorithms for determining the vegetation vertical structure and forest aboveground biomass/height through the fusion of multiple spaceborne SAR, including Interferometric SAR (InSAR), Polarimetric InSAR (PolInSAR) and Tomographic SAR (TomoSAR) data, as well as lidar and/or optical data.

The large-scale forest height mosaic product can be used to create aboveground biomass maps, which will account for the terrestrial carbon storage and model the dynamics of carbon cycle. This piece of information is useful not only for addressing the climate change related scientific issues, but also for answering the question about the missing sink of terrestrial carbon storage. This information will help developing countries to better understand and quantify the carbon emission as well as their decision making regarding the United Nations’ REDD+ programme.

NOAA’ Joint Polar Satellite System with its fleet of three satellites in orbit provide resilient and reliable Earth observations for operational meteorology and other mission critical applications. Two more satellites in the series are under development and the constellation is expected to provide backbone observations that support both short- and long-term weather forecast models well into the next decade. In collaboration with partner agencies such as NASA, ESA, EUMETSAT and JAXA, NOAA provides its stakeholders a large set of global observations in Low Earth Orbit (LEO). The synergy between NOAA and its partner missions offers significant benefits to users such as improved global refresh of observations and complementarity of measurements in multiple regions of the electromagnetic spectrum to enable detailed monitoring of the Earth. Building upon the success of the JPSS program, NOAA is evolving its LEO portfolio to not only continue its current suite of observations but also to improve then in future to support evolving user needs. In addition to providing timely and critical observations for extreme weather and disasters, the long historic data record from LEO satellites is also critical for climate monitoring. This session invites presentations from LEO missions that make routine observations to monitor the Earth and its environment for applications that support decision makers. Subjects covered in this session will include applications and accomplishments from current operational missions as well as plans for new missions from space agencies. Presentations that demonstrate the societal and economic value of LEO observations to applications that are integral to decision making are also of high interest to this session.

Every year, millions of people worldwide are impacted by natural and man-made disasters. Floods, heat waves, droughts, wildfires, tropical cyclones and tornadoes cause increasingly severe damages. Civil wars and regional conflicts in various parts of the world, moreover, lead to an growing number of refugees and large changes in population dynamics. Rescue forces and aid organizations depend on up-to-date, area-wide and accurate information about hazard extent, exposed assets and damages in order to respond fast and effectively. To this regard, emergency mapping has been using remote sensing data since decades to support rescue operations with the required situational awareness. Providing this information in a rapid, scalable and reliable way, however, remains a major challenge for the remote sensing community.
Commonly used emergency mapping protocols involve a large degree of manual assessment by interpreters, who visually compare remote sensing images of a disaster situation. Therefore, obtaining an area-wide mapping is time-consuming and requires a large number of experienced interpreters. Nowadays, the amount of remote sensing data and related suitable sensors is steadily increasing, making it impossible in practice to assess all available data visually. Therefore, an increase of automation for impact assessment methods using multi-modal data opens up new possibilities for an effective and fast response workflow.
In this session, we want to provide a platform for research groups to present their latest research activities aimed at addressing the problem of automatic, rapid, large-scale, and accurate information retrieval from remotely sensed data to support disaster response. More specifically, the focus lies on machine learning-based approaches for the extraction of relevant information about hazard extent (e.g., flood mapping), exposed assets (e.g., road condition assessment) and impacts (e.g. building damage assessment), acquired from satellite, aerial or drone platforms. The choice of training data for these tasks is restricted to a limited number of open datasets, which have a major impact on the methods’ performance: in this session we encourage the presentation of new public benchmark datasets and aim at increasing awareness on existing ones.

Climate change is one of the most pressing challenges facing humanity today, with far-reaching implications for ecosystems, economies, and societies worldwide. Remote sensing and geospatial data play a pivotal role in monitoring and understanding climate change. Machine learning, with its ability
to process vast amounts of data and extract meaningful insights, has emerged as a powerful tool in this endeavor. This proposal seeks to organize a special session at IGARSS (International Geoscience and Remote Sensing Symposium)
to explore the applications of machine learning in climate change research.

Session Objectives:
--To showcase recent advancements in machine learning techniques applied to climate change research.
--To foster collaboration between remote sensing experts and machine learning practitioners.
--To discuss challenges, opportunities, and ethical considerations in using machine learning for climate change mitigation and adaptation.

Session Topics:
1. Machine Learning for Climate Data Analysis:
-- Climate model evaluation and improvement.
-- Data-driven climate trend analysis.
-- Extreme weather event prediction and attribution.
2. Remote Sensing Data Fusion:
-- Integration of satellite, aerial, and ground-based data.
-- Multisensor data fusion for climate monitoring.
-- Uncertainty quantification in fused data.
3. Climate Change in Agricultural Analysis:
-- Adapting Agriculture to a Changing Climate
-- Crop Diversification and Climate Change Mitigation
-- Digital Agriculture Solutions for Climate Resilience
-- Precision Agriculture in the Face of Climate Change
4. Climate Resilience and Adaptation:
-- Machine learning-based decision support systems.
-- Early warning systems for climate-related disasters.
-- Optimizing climate adaptation strategies.
-- Climate-Smart Agriculture: Resilience and Sustainability
5. Ethical Considerations and Bias Mitigation:
-- Fairness and bias in climate models and predictions.
-- Ethical considerations in data collection and sharing.
--Addressing environmental justice concerns.
and many more related topics.

Session Format:
The special session will consist of presentations by leading experts in the field, followed by interactive Q&A sessions. We will encourage interdisciplinary discussions and collaborations among researchers, practitioners, policymakers, and industry representatives.

Benefits to IGARSS Participants:
1. Exposure to cutting-edge research and practical applications at the intersection of machine learning and climate change.
2. Opportunities to network with experts and potential collaborators from diverse backgrounds.
3. Insights into addressing real-world challenges in climate change mitigation and adaptation.

Conclusion:
This Community Contributed Special Session on Machine Learning for Modelling and Monitoring Climate Change at IGARSS will provide a platform for researchers and practitioners to share their knowledge, exchange ideas, and explore innovative solutions for addressing the complex challenges posed by climate change. We believe that this session will contribute significantly to the ongoing efforts to understand, mitigate, and adapt to climate change using machine learning and remote sensing technologies.

Climate change research requires the ability to discern the most influential features and oscillations driving environmental shifts. This session focuses on the power of machine learning in geophysical parameter estimation and feature importance analysis to unravel the complexities of climate change both spatially and temporally. An objective of this session is to showcase how various machine learning techniques can extract crucial information from remotely sensed datasets, providing accurate estimates of key geophysical parameters. Examples of complex dynamic systems where these techniques show great promise include air sea interactions, atmospheric wave dynamics, machine learning based forecasting, and many others. By bringing together experts in the field, a guided dialogue can be fostered on innovative research that demonstrates how various machine learning techniques can enhance our comprehension of climate processes and, in turn, inform more effective climate change mitigation strategies. These techniques include supervised and unsupervised neural networks, time series forecasting and regression algorithms that work towards a better understanding of climate change through parameter estimation and feature importance using satellite data. Additionally, this session will explore how to optimize machine learning algorithms for physics-based systems (i.e. climate change). A better understanding of how we can use machine learning in the analysis of data pertinent to understanding feedback loops relevant to our changing climate would enable the development of more robust algorithms for the analysis of spatial and temporal data from remote sensing instruments. Attendees will gain valuable insights into how geophysical parameter estimation and feature importance analysis are contributing to a sustainable future in the face of climate change challenges.

The mining industry is a cornerstone of economic and industrial development as it plays a pivotal role in meeting the world's essential raw materials resource demands for sectors including renewable energy technologies to electronics and beyond. However, the industry faces an imperative to operate in an environmentally sustainable and socially responsible manner. Earth Observation (EO) data, powered by state-of-the-art machine learning and deep learning methods, offers a unique opportunity to address this challenge, offering solutions across all phases of the mining life cycle.

Thus, this Community-Contributed Session seeks to explore innovative solutions for sustainable and efficient mining practices through the integration of machine learning algorithms and EO data supporting systematic mineral exploration, continuous monitoring of mining operations, and the critical phases of closure and post-closure. We will shed light on the latest EO technologies, data analysis, and predictive modelling, emphasizing early warning systems to mitigate environmental risks, optimize resource extraction, and secure critical raw materials availability. The integration of multi-sensor data, multi-scale analysis, and multi-temporal insights will enhance decision-making across the mining life cycle. 
This double session includes presentations dealing with  Exploration and Mineral Mapping Applications, focusing on advanced machine learning techniques to enhance the accuracy and efficiency of exploration and mapping, Environment and Mine Site Monitoring Applications, concentrating on real-time monitoring and safety protocols, promoting sustainability and responsible resource extraction. We prioritize studies combining a wide range of EO data sources, including Copernicus data, European space-based missions (e.g., COSMO-Skymed, EnMAP, PRISMA, TerraSAR-X), commercial satellites, airborne platforms, drones, and in-situ techniques for calibration, validation, and enhanced insights at various spatial and spectral resolutions.

This session is directed to experts from the fields of EO, geospatial science, machine learning, and mining who can present their innovative work in subjects including but not limited to: i) real-time EO monitoring solutions and early warning systems to ensure safety, environmental compliance, and optimal resource extraction; ii) predictive models that use EO data to anticipate environmental changes, hazards, or potential issues related with mining activities; iii) advanced machine learning techniques for EO data analysis, pattern recognition, and decision support; iv) novel machine learning solutions to decrease the need for traditional in-situ data collection methods v) deep learning algorithms for image processing and feature extraction from multi-sensor EO data; vi) analyzes of EO data over time to detect temporal changes and trends; vii) integration of data from various sensors to collect timely and comprehensive information about mining sites; viii) integration of data from different scales to provide a holistic view of mining processes.

Overall, this double session aims to promote sustainable and efficient mining practices while also advancing societal acceptance and resource autonomy, through innovative solutions based on EO data and machine learning algorithms to drive the mining industry towards a greener and more sustainable future.

Hyperspectral imaging spectroscopy data is acquired from a suite of new generation satellite sensors that include: 1. German Deutsches Zentrum fur Luftund Raumfahrt (DLR’s) Earth Sensing Imaging Spectrometer (DESIS) sensor onboard the International Space Station (ISS), 2. Italian Space Agency (ASI) PRISMA (Hyperspectral Precursor of the Application Mission), and 3. German DLR’s The Environmental Mapping and Analysis Program (EnMAP). Further, Planet Labs PBC recently announced the launch of two hyperspectral sensors called Tanager in 2024. The NASA is planning hyperspectral sensor Surface Biology and Geology (SBG) mission. Further, we already have over 83,000 hyperspectral images of the Planet acquired from NASA’s Earth Observing-1 (EO-1) Hyperion that are freely available to anyone from U. S. Geological Survey’s data archives. These suites of sensors acquire data in 200 plus hyperspectral narrowbands (HNBs) in 2.55 to 12 nm bandwidth, either in 400-1000 or 400-2500 nm spectral range with SBG also acquiring data in thermal range. HNBs provide data as “spectral signatures” in stark contrast to “a few data points along the spectrum” provided by multispectral broadbands (MBBs) such as the Landsat satellite series. 
The above series of satellites provides an exciting new era of hyperspectral sensors that are expected to help us advance satellite sensor-based science of the Planet Earth. Nevertheless, they also bring many challenges such as data volume, data redundancy, expertise needed to analyze these sophisticated data, and requirements in advancing methods, techniques, and approaches. Our overarching goal in this community contributed session (CCS) is to study world’s leading agricultural crops using hyperspectral narrowband (HNB) data and compare with multispectral broadband data (MBB) data and see where and how we can make advances in crop type classification, crop health and stress studies, and in quantifying crop biophysical and biochemical parameters. The session will present and discuss spectral libraries of agricultural crops to help train, test, and validate artificial intelligence (AI) and machine learning (ML) algorithms. The session will address five major philosophies of hyperspectral data analysis pertaining to agriculture, water, and food security and highlight their strengths and limitations. These 5 philosophies are: 
1.	Full or whole spectral analysis (FSA’s) where entire HNB data are used.
2.	Optimal hyperspectral narrowband data (OHNBs) where the best narrow bands are used, and the redundant bands sieved.
3.	Hyperspectral vegetation indices (HVIs) that best characterize crop quantities.
4.	Classification methods and approaches including artificial intelligence\deep learning, machine learning, and cloud computing.
5.	Modeling crop biophysical, biochemical, plant health, and plant structural quantities based on physical-based and empirically based methods.

Multiple microwave remote sensing techniques have been demonstrated to have the potential for quantitative global monitoring of snow properties, such as SWE, albedo, snow wetness etc.   The techniques include passive radiometry, SAR volume scattering,  Reflectometry, signals of opportunities, Interferomeric SAR, etc. 

The present-day spaceborne sensors encompass a variety of active and passive systems. Active sensors like Radarsat-2, Sentinel-1, TerraSAR-X, COSMO-SkyMed, and passive sensors such as GMI, SSM/IS, AMSR-2, and FY-3 are currently available. Additionaly, there are planned and potential satellite missions including L Band InSAR, P-band signals of opportunities (SNOOPI), TSMM radar scattering at dual Ku bands, volume scattering approach at the X band and Ku band, and passive radiometry at X and Ka band, etc.   The planned and proposed missions will further enhance microwave remote sensing applications in snow properties monitoring. This session seeks new scientific results that can contribute to 1) improve our understanding in modeling microwave signals, 2) analyze the response of satellite, airborne, and ground-based field measurements to snow properties; 3) develop algorithms for  the inversion of snow properties and 4) conduct  field and airborne experiments to validate microwave models and inversion algorithms. 

Modeling the signal collected by a remote sensor, considering the characteristics of the acquisition system (sensor, platform) and the electromagnetic interaction with the target and propagation through the atmosphere, is a key topic in remote sensing. It provides answers to direct (forward) problems, thus enabling the solutions of inverse (retrieval) problems. This shall be done in the whole range of the electromagnetic spectrum used to sense the environment.
The session is intended to address the technical space between basic electromagnetic theory, data collected by remote sensing instruments, and analyses/retrieval products. It focuses on models and techniques used to take geometric, volumetric, and material composition descriptions of a scene along with their electromagnetic (e.g., scattering, absorption, emission, optical bidirectional reflectance distribution function, dielectric properties, etc.) attributes and then predict for a given remote sensing instrument the resulting observation. 
This session seeks papers that can contribute to 1) improving our understanding in modeling microwave and optical signals and their responses to earth surface and atmospheric components; 2) describing advances in data analyses and field experiments for validation of models and inversion algorithms; 3) highlight the sensitivity of the measurements by active and passive sensors to relevant bio-geophysical parameters and identify new observational opportunities and applications. It will provide a forum for researchers to share their findings in single-scattering, multiple scattering (radiative transfer) and downstream applications. Both modelling in the microwave and the optical spectrum are encouraged to be presented, to foster a fertilization of ideas and explore synergies between the two communities. 
The session is being organised by the GRSS MIRS TC and is intended to provide a forum where the modelling community can exchange experience, methods and possibly software tools, thus enabling and facilitating model comparison and validation works, especially by young scientists.  

Crop production has historically depended heavily on tillage. Intensive tillage may cause soil, water, and air quality to decline. For this reason, tillage has been a popular topic of discussion for environmental policies and programs, such as environmental indicators for agriculture. Conservation tillage, which leaves crop residue on the soil to give nutrients and lessen water runoff and erosion, has been promoted and developed in many nations as one of the top technologies for sustainable agricultural development. Despite this significance, there is currently a lack of efficient and extensive field or regional-level monitoring of tillage trends. Determining the extent to which no- (or minimum-) tillage practices are used requires a significant investment of time and money when using conventional resources, such as field surveys. On the other hand, it is possible to successfully monitor tillage activities by using data from earth observation. Due to their capacity to penetrate cloud cover, high spatial resolution and sensitivity to surface roughness, SAR observations are particularly useful for mapping and monitoring tillage operations across the globe. Coherent and incoherent change detection techniques using SAR data have proven very effective in detecting surface roughness changes at field to regional scales. Nevertheless, to augment SAR observations and close the gap to operational services, the synergy of multi- and/or hyperspectral optical data is required.
The objective of the proposed session is to provide an overview of the most promising high-resolution methods and related performance currently under investigation and to present new ideas and new research directions in this field. 

Monitoring land cover in agricultural systems involves the detection of photosynthetic and non-photosynthetic vegetation protecting the soil. Maintenance of crop residues and other non-photosynthetic vegetation on the soil surface maintain a protective mulch that can provide important benefits to the environmental performance of cropping systems by helping to enhance carbon sequestration and to reduce erosion, evaporation, and nutrient loss. Remote sensing allows monitoring the use of cover crops and the management of crop residues, crucial variables for determining the exposure of the bare soil. Similarly, remote sensing of green and non-photosynthetic vegetation provides valuable information for understanding vegetation dynamics in grasslands. Nevertheless, scientific challenges like the interaction with water or the decomposition of the crop residues remain relevant and need to be solved for operational use.  
Nitrogen (N) and water are the main limiting factors in agriculture and, therefore, they are frequently applied for optimizing crop production or quality. As a consequence, overfertilization is a common practice and only about half of the N fertilizer applied is assimilated by the crops, being the other half loss to the environment and causing serious problems for water and air quality. Spectral remote sensors have proven to be a reliable tool for estimating crop N status and crop parameters that determine production, therefore, they can contribute to optimize N fertilization. However, the interaction between N and water status may produce confounding effects in the acquired spectral reflectance, making it difficult to separate crop deficiencies. Other sensors, like thermal or radar can contribute to offer useful information related to crop parameters. In addition, recent techniques such as artificial intelligence, are able to enhance remote sensing accuracy.
This session seeks for state-of-the-art communications related to application of sensors, digitalization, and artificial intelligence to monitoring land cover and optimizing resources efficiency in agriculture.

The investigation of terrestrial hydrological cycle is crucial in view of climate change mitigation, water resource and waste monitoring. In particular, frequent monitoring of soil, snow cover, and vegetation conditions is important for meteorological and climatological forecast as well as for agriculture management.  
The role of soil moisture and vegetation in the climate system has been studied by the climate research community, showing an enhanced understanding after the addition of remotely sensed products. The essential role of soil moisture (SM) and Above-ground biomass (AGB) in the climate system motivated the Global Climate Observing System (GCOS) and ESA to endorse SM and AGB as Essential Climate Variables (ECV) and introduce them to their Climate Change Initiative programme. 
Microwave sensors can give an impressive contribution to these tasks due to the high sensitivity to water content and provide interesting information on soil and vegetation. The exploitation of multifrequency and multi-polarization satellite datasets is important for extracting various parameters of soil and vegetation. The lower frequencies (P, L) being the best for estimating soil moisture at a reasonable depth, whereas the higher (C, X) are more indicated for estimating vegetation water conditions and biomass and snow parameters.
Microwave observations from space-borne sensors are therefore ideal for soil moisture retrieval and vegetation observations, both in term of biomass and water status. A variety of microwave satellite from active and passive sensors has been observing the Earth’s surface since the late 1970s with the aim of monitoring soil and vegetation systems and estimating their main parameters. The use of adequate electromagnetic modelling will ensure correct simulations of both backscattering and microwave emission and grant the necessary datasets for the application of inversion algorithms based on machine learning approaches. 
Microwave observations can be used as inputs in models based on machine learning approaches for the retrieval of land surface parameters such as vegetation water content, soil moisture, surface roughness, and land surface temperature, and may ultimately be integrated into existing (long-term) data products.
In this session some approaches based on multi-frequency microwave observations for estimating soil and vegetation parameters will be described. Both active and passive sensors will be used together with newly implemented algorithms and models.

The ever-expanding volume of satellite data has brought a significant change in the field of geoscience and remote sensing, notably impacting agriculture and a diverse range of stakeholders. This influence extends to Agriculture Insurance firms, Agricultural Consultants, Water Management Authorities, Sustainability Consultants, the Agri-Food industry, Financial Institutions, and Government agencies.  

Additionally, the evident consequences of climate change underscore the need for more systematic and timely inspection of the condition of agricultural fields and the farming practices employed. In response, the updated Common Agricultural Policy (CAP 2023-207) has introduced the concept of exhaustive monitoring, departing from the traditional sample-based operational model, and aims to optimize its Integrated Administration and Control System (IACS) as a key tool in reaching its ambitions of the Farm to Fork and regional-based biodiversity strategies. 

The synergistic utilization of optical and Synthetic Aperture Radar (SAR) imagery emerges an exceptional opportunity for continuous, real-time detection of agricultural practices at the level of fields. The successful integration of complementary data sources of Copernicus Sentinel-1 and Sentinel-2, as well as other satellite missions (e.g., Landsat, MODIS, PlanetScope etc.) constitutes a unique research topic in order to ensure continuous satellite image time series (SITS) for the more accurate detection of agricultural events. This integration overcomes challenges often posed by extended cloud coverage, and is vital for precision agriculture and food security early warning information systems.  

The primary objective of this session is to highlight the pivotal role of synchronous EO-based applications, under the parallel exploitation of cutting-edge technological advancements (i.e., deep learning), in shaping the monitoring of modern and more sustainable agriculture. Finally, this session is dedicated to address challenges through continuous SITS evaluation, which are linked to the on-time detection of a wide spectrum of agricultural activities, such as i) crop yield estimation, ii) monitoring of farming practices and eco-schemes, iii) evaluating carbon sequestration, iv) enhancing grassland management, v) mitigating soil degradation, vi) managing irrigation practices, and vii) assessing the effects of crop diseases and natural disasters. 

Our session focuses on the diverse applications of EO-technologies through practical solutions, harmonized with the latest breakthroughs in artificial intelligence. We explore how these advancements reconfigure sustainable agriculture, guiding effective green deal policy implementation and business strategies. 

Distributed radar systems are opening new paths for imaging internal structures of the Earth, atmosphere, and planetary bodies. Multistatic radar tomography creates 2D, 3D, or 4D images of internal properties by combining the computational imaging techniques common in seismic and medical applications with recent advances in radar signal processing, platforms (e.g., CubeSats, drones, rovers, smartphones,) and networking schemes. Tomographic methods can estimate properties such as temperature, moisture content, and material type inside a volume that is between or below multiple bistatic transmit-receive nodes. These problems are regularly ill-posed due to non-invasive node configurations that do not fully surround a medium, indistinguishability of electrical properties, and ambiguity of conversions between electrical and physical properties. These challenges can be overcome with geophysically informed inversions and priors that limit solutions to those that are physically realizable, which makes this topic highly synergistic between science and engineering disciplines. In many cases, the resulting tomographic radar systems have higher resolution, spatial coverage, and/or accuracy compared with other systems, which opens new possibilities in Earth and Planetary Sciences. For example, scientists and engineers are mapping temperature distributions inside glaciers to improve sea level rise predictions, estimating properties of the ionosphere to advance weather models, evaluating 2D cross sections of forest canopy to quantify biomass and moisture, and investigating internal compositions of asteroids. The development and use of tomographic multistatic radar systems enhance our understanding of the Earth, atmosphere, and celestial bodies.  

Tomographic multistatic radar systems are a synergistic fusion of distributed platforms, computational imaging, novel signal processing techniques, science-informed inversions, and radar technology. Multistatic radar tomography is distinct from TomoSAR in that it leverages scientifically based inversion methods to estimate physical properties rather than creating radargrams and it does not necessitate Doppler processing. Additionally, multistatic radar tomography separates itself from ground-penetrating radar tomography by leveraging high bandwidth radar chirps and either full-wave inversions or pulse compression for improved resolution. The creation of this session is intended to establish a community for this emerging technology and bring together researchers of this topic who have been presenting in disparate sessions. We invite researchers to present results from multistatic tomographic radar systems as well as work on new inversion methods, instruments, or signal processing techniques aimed at enabling or improving multistatic radar tomography. This includes but is not limited to new computational imaging methods, machine learning inversions or pre-processing of tomographic radar data, signal processing approaches that enable tomography, multi-node synchronization schemes, results from deploying a tomographic radar, and other developments of bistatic and multistatic radar systems intended for tomography. Combining knowledge of these topics will help push forward the frontier of multistatic radar tomography.

The National Aeronautics and Space Administration’s (NASA) Soil Moisture Active Passive (SMAP) mission, the first NASA Earth Science Decadal Survey mission, was launched January 31, 2015 to provide high-resolution, frequent-revisit global mapping of soil moisture and freeze/thaw state. The primary science goal of SMAP is to provide new perspectives on how the three fundamental cycles of the Earth system, the water, energy and carbon cycles, are linked together over land. Soil moisture is the key variable that links the three cycles and makes their co-variations synchronous in time. 
SMAP was designed to include L-band radar and radiometer measurements sharing a rotating 6-meter mesh reflector antenna.  The instruments operate onboard the SMAP spacecraft in a 685-km Sun-synchronous near-polar orbit, viewing the surface at a constant 40-degree incidence angle with a 1000-km swath width for a global revisit in 2-3 days.  The radiometer has been operating since April 2015 with no issues. The radar operated from April to July 7, 2015. Since 2017, the European Union’s Copernicus Sentinel-1 Synthetic Aperture Radar data has been used as a replacement for disaggregation of SMAP radiometer data into 3 km spatial resolution. In addition, the SMAP radar receivers have been repurposed to record the reflected signals from Global Navigation Satellite System (GNSS) satellites (SMAP-R). The SMAP mission completed its prime mission operation in June 2018, and has been extended by NASA for operation through 2023. 

In this special session the status of SMAP mission, plan for extension through 2026, highlights of SMAP science results, and new science algorithms will be presented. The SMAP science data product suite of geophysical parameters includes estimates of surface (top 5 cm) and root-zone (down to 1-m depth) soil moisture, net ecosystem exchange (NEE), and classification of the predominant frozen/non-frozen state of the landscape.  The radiometer has advanced capability to detect Radio Frequency Interference (RFI). The radiometer hardware and processing software are also designed to mitigate some RFI contamination. As a result, the land coverage and accuracy of the surface soil moisture retrievals are greatly enhanced. SMAP data products have several key practical applications that affect society through applied science, and key results will be provided. The invited papers will detail global analysis of SMAP radar data and SMAP-reflectometry data, which will be critical to advance the synergistic use of NASA-ISRO Synthetic Aperture Radar and GNSS-R datasets. The algorithm improvements include updated waterbody map, usage of data quality flag, soil moisture and vegetation optical depth for temperate forests and estimation of seasonal free/thaw dynamics.

The ocean covers approximately 71% of the Earth’s surface (90% of the biosphere) and contains 97% of its water. In addition, it holds the keys to and equitable and sustainable planet. The fourth year of implementation of the UN Decade of Ocean Science for Sustainable Development is starting in 2024 and there are still critical issues to be addressed, e.g., climate change, food security, sustainable management of biodiversity, sustainable ocean economy, pollution, and natural hazards. Within this context, availability of measurements  from  space using active and passive remote sensors are of paramount importance to assist policy makers and stakeholders involved in the sustainable exploitation of the ocean environment. 
In the past two decades, several spaceborne microwave active (Synthetic Aperture Radar and scatterometer) and passive (radiometer) sensors, together with optical instruments and opportunity measurements,  have been providing large swath and frequent coverage for ocean monitoring. 
The proposed session will invite presentations that report on the latest developments in cutting-edge research on new methods and techniques to generate added-value products from space-borne measurements in the context of a sustainable exploitation of the ocean resources. Studies related (but not limited) to the following topics will be considered:

1.	estimation of essential physical parameters (e.g., sea state, sea surface height, sea surface temperature and salinity, etc.);
2.	monitoring of hazards (including pollution from oil and plastic, etc.);
3. 	management of marine traffic (including ship/targets observation and classification, etc.).

These key topics are strictly inter-connected and, very often, they call for a synergistic combination of information extracted from measurements collected by complementary remote sensing sensors. Hence, these topic aim at serving as a showcase for a broader community by demonstrating: a) the added-value and the uniqueness of information obtained via remotely sensed measurements for the development of a sustainable ocean environment; b) bridging the gap between operational end-user communities and EO products; c) promoting technological/scientific transfer between research centres and end-user organizations; d) encouraging cooperation among scientists belonging to GRS and Oceanic Engineering (OES) societies.

The Community Contributed Session, “Next Generation of Low-Earth Orbit (LEO) and Geostationary (GEO) Microwave and Infrared Sounders”, would be the fifth in a series of successful IGARSS invited sessions on the topic of next generation sounders, since IGARSS 2020. This newest session aims at discussing the latest progress and exploring new possibilities behind the development of future microwave and infrared sounders onboard LEO and GEO satellites as well as CubeSats. 
The status of new missions, new concepts and system architecture, the progress and challenges of LEO/GEO microwave and infrared sounders as well as strategic international collaborations will be discussed. Such sounders include the Meteosat Third Generation (MTG) Infrared Sounder and EUMETSAT-Second Generation Infrared Atmospheric Sounding Interferometer – New Generation (IASI-NG) and Microwave Sounder (MWS), the NASA TROPICS Mission as well as the planned GEO-XO and LEO SounderSat.
In the past decades, there has been much effort and progress toward advancing microwave and infrared sounders on LEO and GEO satellites. Those instruments have been providing high quality Earth observations. Those observations are pivotal for weather and climate applications and are being assimilated on a daily basis at Numerical Weather Prediction centers all around the world.  Observations from LEO and GEO microwave and infrared sounders have shown their capability to support the generation of accurate global temperature, water vapor profiles, and trace gas column abundances. Infrared sounder observations provide high vertical resolution capabilities, while microwave sounder observations enable all-weather condition capabilities. A key component for further observational improvements is through increased temporal and spatial resolution, which can be realized with a combination of infrared and microwave sounders on LEO and GEO satellites.
Earth observations from LEO and GEO satellites are complementary and are needed to further understand the evolution of environmental processes, leading to more accurate weather forecasts and critical climate products. This session is organized to provide useful information for the planning and decision making of the next generation of environmental observation systems. The next architecture of observing systems is expected to provide continuity, redundancy and enhance critical capabilities needed for weather forecasting and environmental monitoring. At the same time, this session is expected to include presentations that report the geophysical impact of the new generation of LEO/GEO microwave and infrared sounders. This is a critical aspect to understand the expected benefits from the new generation of Earth observation systems.

In recent years, nighttime light (NTL) remote sensing has been popular to monitor human activities, with topics spanning from power outrage due to natural hazards, lockdowns during Covid-19, wars and borders, poverty, urbanization, light pollution and skyglow, and special cultural or social events at night. NTL remote sensing has also been used to study the impacts of human activities at night, including air pollution, urban heat islands, animal behaviors, vegetation cycles, and human health. These topics cover a wide range of the Sustainable Development Goals, including SDG-1 No Poverty, SDG-3 Good Health and Well-Being, SDG-7 Affordable and Clean Energy, SDG-11 Sustainable Cities and Communities, SDG-13 Climate Action, SDG-14 Life Below Water, and SDG-15 Life on Land. 

The NTL related peer-reviewed publications showed a strong knee-in-curve increase especially over the past five years with > 250/year. However, over the years, IGARSS did not have a specific session on NTL remote sensing despite 10-20 papers on this topic annually. These papers were scattered in other sessions that cannot provide a platform to discuss NTL remote sensing in detail. NTL remote sensing is fundamentally different from other types of remote sensing. Unlike daytime remote sensing, whose light source is the Sun, in NTL remote sensing, the dominating illuminance source is mainly the artificial light generated from human activities on the Earth surface at night. This unique nature in light source makes NTL remote sensing fundamentally different and requires specific processing methods. For example, NTL remote sensing is more sensitive to observation angles; time-series analysis is often a must; and the detection/pre-processing of clouds becomes more crucial. 

Recent developments and launches of new satellites and sensors provide a proliferation of NTL-capable sensors and thus NTL products, such as DMSP-OLS, VIIRS-DNB including NASA Black Marble, Landsat-8/9, Luojia-1, Jilin-1, EROS-B, SDGSAT-1, and the International Space Station (ISS). The new products provide either long-term, daily time-series continuity (NASA Black Marble), multispectral capabilities (SDGSAT-1, ISS), or very high spatial resolution of up to 1 meter (Jilin-1). Researchers in the community use these various data products depending on their needs and often communicate with each other. This community contributed session proposal is therefore designed to provide a platform for NTL researchers to communicate nighttime lights, their analysis methods, and their societal applications related to SDGs. 

By gathering NTL researchers within this community contributed session (rather than scattered in other sessions), researchers in the field can engage in in-depth discussion on  sensors calibration, algorithm development, products validation and uncertainties, and applications related to NTL remote sensing – by which the proposed community contributed session will facilitate the usage of nighttime light products and communications in the field, thus advancing geoscience and remote sensing. 

The Earth’s atmospheric planetary boundary layer (PBL) serves as the mediating layer between the troposphere and surface where complex exchange processes are critical to weather, air-quality, and climate systems. Models inaccurately capture these processes across different scales leading to uncertainty in short- and long-term predictions. From space, the PBL remains a challenge to observe due to the long standoff distance and lack of information content from the current program of record.  From suborbital and surface-based platforms, high information content is achieved in the troposphere down through the PBL, but statistical sampling due to lack of spatiotemporal coverage remains a challenge. A such, global, systematic measurements of PBL thermodynamic properties (i.e., profiles of water vapor, temperature, and distributions of PBL heights) remains an unmet challenge formally recognized by the NASA 2017 Decadal Survey. 

Satellite remote sensing of the PBL is an unrealized challenge while innovation is arising in the form of a multi-sensor, multi-mission approach, enabled by emerging technologies and data-science techniques. Potential building blocks include space, suborbital, and ground network to cover the vast spatiotemporal requirements needed to advance PBL science across the many disparate communities. Instrument technologies targeted for increasing information content in the PBL (and troposphere) span lidar, passive infrared (IR) and microwave (MW), radar, and radio occultation. Emerging active-passive retrievals show promise for translating the high accuracy and vertically resolved thermodynamic profiles (and PBLH) from lidar to the swath of IR and MW sounders to increase both vertical resolution and accuracy in the sounder’s retrieval of temperature, water vapor, and PBL-height. The NASA PBL Incubation program is maturing technologies and data fusion techniques to enable observations from different vantage points (space, suborbital) to overcome observational gaps faced by one sensor or observing platform alone.  Here we seek presentations to spark discussion on measurement architectures and the technologies and data fusion techniques that enable those future missions. Thus, this session will envision a future application of IGARSS 2024 Special Scientific Theme SP.5 “Synergetic use of multiple EO missions and sensors.” A mission-of-missions is needed to overcome the hurdles and to realize the benefits of global, systematic PBL measurement. 

Aim: Established approaches for retrieving critical geophysical and biophysical parameters from remote sensing observations exploit our understanding of physical processes through appropriate mathematical electromagnetic modeling like radiative transfer models. These models are fundamental in interpreting the interactions between electromagnetic energy and atmospheric/geological components and lay the groundwork for accurate parameter retrieval. While such methods can achieve impressive performance in numerous tasks, from soil moisture estimation to surface temperature retrieval, they rely heavily on specific assumptions and an appropriate selection of parameters. At the same time, data-driven approaches based on machine learning (ML) have demonstrated exceptional performance in numerous remote sensing retrieval tasks, leveraging the available data that can be employed for training such models. Yet, the data-hungry nature of ML models poses a significant hurdle, especially in scenarios where obtaining copious amounts of high-quality real-world observations is impractical or impossible, which is typically the case in remote sensing-based retrieval. 
This session focuses on ML methods of retrieval that combine physical models and data-driven ML approaches. Examples of such synergies include but are not limited to the following topics:
•	Integration of physical constraints into ML-based retrieval;
•	Training of ML architectures using simulations from physical models;
•	Physics-constraints time-series analysis, including forecasting;
•	Fusion of physical and ML models for geophysical parameter retrieval and analysis;
•	Data-driven parameter selection for physical models;
•	Training of ML methods using in-situ observations and data assimilation estimates;
•	Development of Analysis Ready Datasets for ML model optimization.
The expectation is that the integration of physical models and ML models will significantly enhance the quality of geophysical parameter retrieval by reducing the impact of training data availability for ML-based methods and enhancing the quality of derived products in terms of retrieval accuracy as well as spatial and temporal resolution. The proposed CCS is aligned with the concerted efforts of the Modeling in Remote Sensing Technical Committee (MIRS TC) of the IEEE Geoscience and Remote Sensing Society (GRSS).

The objective of this session is to demonstrate the significant achievements of the PRISMA user communities across various scientific and practical domains, including calibration, validation, and simulation, in the utilization of data acquired by the Italian Hyperspectral mission PRISMA, which was launched in 2019.

In the broader context, one of the primary objectives of the Italian Space Agency (ASI) within the Earth Observation domain is to promote the utilization of Italian space assets, both within the space industry and in non-space environments, by fostering the development of product services and applications that can have a positive impact on the Italian and European institutional, scientific, and commercial sectors. In the context of PRISMA data utilization, ASI's aim is to facilitate the development of new competencies in hyperspectral image processing and, consequently, to encourage the creation of innovative products and services to address conventional market demands.

Within this framework, several initiatives have been undertaken to support the development of algorithms, methods, products, and services based on PRISMA data, ranging from the funding of research and development projects to enabling the commercial utilization of PRISMA data.

The interest in PRISMA data, both within the scientific and commercial communities, is steadily growing, particularly outside of Italy. Subscriptions to PRISMA licenses primarily come from scientists, institutional bodies, and commercial users in over 15 countries worldwide, with the United States, India, and Germany accounting for more than 25% of the total users. The utilization of PRISMA data encompasses a wide range of applications, spanning from precision agriculture to forestry, air quality monitoring, analysis of water ecosystems, hydrocarbon detection, and preservation of cultural heritage.

The expertise gained through these initiatives will not be confined solely to the exclusive use of PRISMA data but will also be extended and leveraged for future hyperspectral missions, such as EnMAP, PRISMA-2, FLEX, SHALOM, and Copernicus/Sentinel hyperspectral missions.

This session is designed, on one hand, to showcase the current state-of-the-art and forthcoming challenges of the PRISMA mission and, on the other hand, to provide the users of PRISMA data with the opportunity to present their proposed solutions and their engagement with the commercial, institutional, and scientific communities while highlighting their achievements.

Ecosystems are composed of a large number of nonlinearly interacting biotic and abiotic components. To properly understand ecosystem functioning and their response to stresses such as climate and land-use change, invasive species, and pollution, a whole-system approach is needed. That is, we must address ecosystem changes by considering the full ensemble of living organisms, the complexity of the trophic web, the properties of the physical, chemical and geological environment and their mutual interactions. Such an endeavour is undoubtedly a “grand challenge” and we are just beginning to unravel these dynamics. Data and models exist at local scale, but to reach the larger spatial scales needed to gain a global vision, we need to blend in situ data with remote sensing observations and provide the necessary information for integrated modelling approaches and digital twin endeavours. All these data-based models should be capable of estimating the ecosystem reaction to different management and restoration action in the various climate and land use change scenarios expected for the near future. In this session, we welcome contributions devoted to quantify ecosystem changes and identify the interplay between ecosystems, biodiversity and geodiversity, blending in situ and remote sensing data. We welcome contributions dealing with new RS product development and validation, methods and results on the comparison and combination of in situ and remote sensing information, and implementation of new models incorporating the knowledge gained from remote sensing observations.

Quantum remote sensing, a field propelled by the fundamental principles of quantum mechanics, has emerged as a revolutionary paradigm, greatly enhancing measurement capabilities across various scientific domains. From fundamental physics to the development of cutting-edge remote sensing technologies, the impact of quantum sensors is profound and ever-expanding. In the vast landscape of quantum technology, a pivotal breakthrough was the ability to cool atoms up to Bose-Einstein Condensate (BEC) using laser and magnetic traps technology. The cold atoms have enabled the utilization of atoms as sensors for a diverse range of parameters, including gravity detection (gravity gradiometers), force measurement (accelerometers), magnetic and electric fields (Rydberg receivers), among others. The recent demonstration carried out by the Cold Atomic Lab (CAL) experiment of being able to create BEC in a microgravity environment on board of the International Space Station (ISS) has opened new avenues for sensor development and exploration, especially in the realm of spaceborne remote sensing. BEC atoms in microgravity are more stable and allow for cooler temperatures and longer interrogation times, allowing experiments and measurements that are not feasible on Earth surface. 

Critical challenges in this domain encompass technology maturation for achieving enhanced sensitivities and the reduction of Size, Weight, and Power consumption (SWaP) of these instruments. These advancements are essential for enabling future spaceborne remote sensing missions, whether they are hosted on the ISS or deployed as free-flying missions. Quantum technologies offer promising solutions, such as leveraging Rydberg atoms for receivers like radiometers, radars, or reflectometers, as well as implementing Quantum Gravity Gradiometers (QGGs) and quantum radars employing entangled photons, among other emerging quantum technologies applied to remote sensing.

This session wants to provide an in-depth exploration of theoretical studies, ongoing research, and practical implementations of quantum remote sensing technologies. It aims to offer a multifaceted perspective, advancing both the theoretical and technological facets of this technique. As researchers delve into the theoretical underpinnings and experiment with practical applications, the potential for revolutionizing remote sensing capabilities becomes increasingly promising, pushing the state of the art forward.

The integration of quantum principles into remote sensing holds vast potential for scientific discovery, and innovative applications. Quantum sensing enables a level of precision and sensitivity that was previously unattainable. This includes improving the measurement of temporal resolution of Earth gravity field for underwater measurement with a precision that current technology such as GRACE, GRACE-FO cannot achieve, and enhancing geophysical remote sensing

Looking forward, the focus of the field will push the boundaries of quantum sensing remote technology to further enhance its capabilities. This includes advancements in miniaturization, power efficiency, and the integration of quantum sensors with data processing algorithms and artificial intelligence. 

This session proposal is from the Chair of the Working Group of Active Optical and Lidar, IEEE-GRSS Technical Committee on Instrumentation and Future Technology (IFT). It is in-line with the GRSS outreach to Space Agencies and Industry and the IGARSS 2024 special theme on “Acting for Sustainability and Resilience”.

It is planned to have a two session (10 papers) on Quantum Technology for Remote Sensing (Part 1 and 2) with emphasize on the invited papers from international space agencies, industry, and academia on enabling technology developments, space missions and observations.

This session focuses on research and developments in an important topic related to Quantum Technology for Remote Sensing, a unique capability to observe a diverse variety of geophysical phenomena from orbit around the Earth and planets has stimulated new areas of remote sensing research that now attracts the attention of scientists and engineers worldwide. 

Quantum Sensing is the most exciting quantum technology, and it has the most potential to change our lives, in terms of societal benefits, in the next decade and beyond. Quantum sensing uses quantum properties to achieve unprecedented measurement sensitivity and performance, including quantum-enhanced methodologies that outperform their classical counterparts. Quantum sensors are highly relevant to overlapping areas such as precision navigation and timing; electromagnetic field sensing; attitude control; communications; and gravimetry.  Typical quantum sensors exploit techniques such as atomic systems, matter waves, quantum entanglement, quantum superposition of states, quantum illumination methods, and manipulation of photons and atoms, in general. Significant gains include technologies important for a range of space-based remote sensing, in situ measurements, metrology, interferometry, quantum communication, ranging, imaging, radar and lidar receivers, and gravity measurements.

This community contributed session will focus on quantum sensing techniques, technologies and geoscience and remote sensing applications related to Earth Science, Astrophysics, and Planetary Science.

Radio Frequency Interference (RFI) is having an increasingly detrimental impact on microwave remote sensing. Interference can corrupt passive and active microwave measurements and reduce the ability to retrieve relevant geophysical measurements globally. In several cases, even a primary spectrum allocation to remote sensing (technically referred to as Earth Exploration Satellite Service or EESS) does not guarantee that the frequency range of interest is free of Radio Frequency Interference since illegal in-band transmissions or out-of-band emissions can still be present. Many innovative technical advances, both in software development and hardware design, have been made by the Earth-observing microwave remote sensing community to improve detection of interference and mitigation of its negative effects. The problem of increasing occurrence of Radio Frequency Interference in microwave remote sensing measurements is closely related to the ever growing spectrum needs of commercial interests, particularly those of the telecommunication industry that  are putting enormous pressure on frequency bands utilized for microwave remote sensing. For this reason, the microwave remote sensing community has also been working closely with spectrum managers to protect the frequency bands of interest for science applications, and it is important to give visibility to this effort at scientific conferences such as IGARSS.

The session will present various interference detection and mitigation techniques developed within the passive and active remote sensing and radio-astronomy communities, report on the status of current and upcoming missions with regards to dealing with Radio Frequency Interference. Current spectrum management issues facing remote-sensing frequencies will also be discussed in this session. 

This session aims to bring together researchers and experts in Geoinformation Technologies and Remote Sensing applied in cultural heritage and archaeological research. Recent technological advancements in both ground-based, aerial and satellite remote sensing sensors providing higher spatial and spectral resolutions have revolutionised current archaeological practises. GIS spatial technologies, Remote Sensing, automatic classification and image processing methods, Big Data analysis and integration, are all aiming towards the advancement of the archaeological record. In addition, increased data visibility through open access policies and cloud storage/cloud processing have impacted traditional approaches. 

The session “Remote Sensing and Geoinformation Technologies in Archaeological Research” invites presentations related to the fields of earth observation using multispectral, hyperspectral and radar sensors, aerial and low-altitude (UAVs) applications and geophysical prospection methods. Papers dealing with the application of advanced image processing (including ML and AI approaches and/or fusion techniques) applied to detect, map, monitor and visualise heritage sites on land and underwater are also welcome.

The session will address best practices and issues in terms of the efficiency of diverse methodologies that can be applied in archaeological contexts existing in different environmental and landscape settings. Emphasis will be provided to the archaeological insights and implications that can result from such technologies.

In particular, we invite researchers to contribute papers on any innovative aspect regarding the increased potential to extract archaeological information from remote sensing and geo-science approaches, providing further insights for the archaeological landscapes and their dynamic interaction with the human agents. 

Papers may address, but are not limited to, the following topics:

•	Synergetic use of multiple EO missions and sensors used in archaeological landscapes.
•	EO and Geo-sciences in support of SDGs in relation to the protection of heritage sites
•	Data Fusion and Data Analysis
•	AI, ML and Big Data
•	Geophysical prospection for mapping and detection
•	GIS spatial analysis and settlement pattern modelling
•	Satellite remote sensing and Geophysical approaches for the reconstruction of ancient landscapes.
•	Underwater prospection
•	Societal Engagement and Impacts

Latin America, a continent of remarkable geographical and ecological diversity, faces a myriad of pressing challenges that require innovative solutions. Latin America's distinctive geological conditions, coupled with its location in tropical regions, present unique challenges that demand tailored solutions. Moreover, the continent grapples with significant economic and social inequalities that require multidisciplinary solutions. The vulnerability of the Amazon rainforest, the alarming loss of glaciers in the Andes, the increasing frequency of floods and landslides due to climate change and the unbalanced conditions for water and food security serve as poignant examples of the region's complex challenges. All of the above, are in line with the different Sustainable Development Goals (SDGs) and can benefit from the use of Remote Sensing to provide a wider view of the problems.
This proposed session aims at providing a platform for research groups to showcase their cutting-edge work in the field of remote sensing and its application to address the critical issues unique to Latin America. The primary focus of this session will be on remote sensing-based approaches that offer a promising avenue to mitigate the multifaceted issues confronting Latin America. Remote sensing technologies, including satellite imagery, airborne sensors, and ground-based sensors, have proven instrumental in monitoring and addressing a wide range of environmental and societal challenges.
The proposed session seeks to foster collaboration among research groups engaged in knowledge generation, enabling them to present their latest findings, methodologies, and innovations, emphasizing connecting local researchers with the broad scientific community. This collaborative environment will facilitate the exchange of ideas and expertise crucial for effectively tackling Latin America's unique challenges.

Human activities and climate change have significantly changed the global environment, ecosystem, economy, and society from various perspectives over the past decades, especially forming a double squeeze and threat on the coastal zone and its sustainable development. According to the United Nations, around 40% of the world’s population lives within 100km of the coast. Coastal sustainability has become a crucial component of global sustainable development. This session topic is highly related to themes in IGARSS, O.4 Coastal Zones, D/S.7 Remote Sensing for Sustainable Development, and several other technical themes with new sensors and methods. However, there is still a lack of such a focus on coastal sustainability with the support of emerging remote sensing technologies. This topic has been successfully organized with two sessions (9 accepted oral presentations) in IGARSS2023 in Pasadena, USA. There were over 20 participants attending the sessions with fruitful discussions.

Recent decades have witnessed coastal reclamation and exploitation, coastal ecosystem and environmental evolution, urban population surge, and urban infrastructure expansion, which brings along different social and environmental impacts, i.e., biodiversity loss, ecosystem fragmentation, and climate change-induced vulnerability for human beings. Sustainable coastal development addresses the significance of timely and efficient monitoring of the urban, ecological, and environmental processes together with their related issues in coastal regions, including urban sprawl, transportation systems, green space and wetland, biodiversity and blue carbon, water pollution and algae bloom, reclamation and aquaculture, natural disasters, etc. The advanced multisource remote sensing techniques, including airborne and spaceborne optical, SAR, and LiDAR at different resolutions together with in-situ data, can provide fine to coarse multi-angle, multi-scale, and multi-frequency observations for coastal monitoring, supporting their resilience and sustainable development. This session invites original research that presents the advances, methodology, and challenges of monitoring different coastal processes and their related issues in coastal regions using multisource remote sensed data. 

The Sustainable Development Goal (SDG) 14, which is all about "Life below water" is sadly the most underfunded of all the SDGs. The World Economic Forum reported that only $10bn overall were invested on SDG14 in the period 2015-2019 which is clearly insufficient if compared with teh yearly investment of $175bn required to achieve SDG 14 by 2030 according to a recent study.
In an effort to accelerate the achievement of SDG14 and its ambitious plans by 2030, new investments have been made and different initiatives, projects and research studies around the world are capturing attention for the potentially disruptive solutions being proposed. Some of them are Earth Observation (EO) solutions that look at the complexity of oceans from different angles, ranging from tracking illegal fishing to monitor water quality and species replenishment, coastal erosion or pollution. 
This session will offer a carousel of some of the best remote sensing solutions for ocean preservation, addressing any of the following aspects: the innovation introduced, the scalability of the solution, the impact generated. We are particularly interested in contributions that, while addressing a clear environmental crisis, can also show the economic and societal benefits they can bring, allowing a blue transformation. We then invite submissions that address one of more of SDG14 targets as:
- prevent/reduce marine pollution
- sustainably manage and protect marine and coastal ecosystems
- minimise and address the impact of ocean acidification
- regulate harvesting and end overfishing, IUU fishing and destructive fishing practices 
- implement science-based management plans to restore fish stocks
-increase the economic benefits to Small Island developing States and least developed countries from the sustainable use of marine resources
-Increase scientific knowledge, develop research capacity and transfer marine technology
-provide access for small-scale artisanal fishers to marine resources and markets
-enhance the conservation and sustainable use of oceans and their resources by implementing international law which provides the legal framework for the conservation and sustainable use of oceans and their resources.

The ever-increasing climate change is a global pressing issue, imposing threats to the environment, impacting also the society and economy that is related to. Remote sensing and geoscience are two important fields used for climate change monitoring and disaster management, employed due to their ability to provide spatiotemporal data for use in applications across several domains, ranging from disaster and crisis management to urban resilience. 
To further strengthen the remote sensing and geoscience knowledge extraction process, Artificial Intelligence (AI) has been incorporated, offering improved data processing, automated feature extraction, real-time monitoring and many others. In cases where data become severely complex, which is the case of satellite images containing many land patterns, AI model face reliability challenges due to their nature of being limited a “black-box” procedure, without further understanding the result of computations. Therefore, establishing techniques to interpret and explain the results of AI models is a well-promising approach to improve the transparency and trustworthiness of AI model outputs, thus strengthening their practicality.
This Community Contributed Session aims in bringing together expertise and in attracting new ideas and solutions in the fields of remote sensing and geosciences, emphasizing on the use of trustworthy AI.

Rationale: The proposed Community Contributed Session aims to showcase that: i) Improving the effectiveness and trustworthy of AI models is important in Remote Sensing and Geoscience data, ii) Combining Machine and Deep Learning technologies in Remote Sensing and Geoscience spans across many scientific fields, all suitable for the IGARSS community and iii) Explainability and interpretability of AI models can be a major step towards evolving standard procedures used for their evaluation, enhancing existing approaches for climate monitoring and disaster assessment.

Uniqueness: The topics highlighted by the proposed Community Contributed Session are not accommodated by any regular session as: i) The technical area of the proposed Community Contributed Session cuts across several remote sensing disciples including satellite imagery, LiDAR, radar sensing, hyperspectral sensing, thermal infrared sensing etc. and geoscience disciples including meteorology, geology etc., all combined with trustworthy AI for climate change monitoring and pre- & post-disaster assessment. and ii) Being such a combination of techniques from different areas, the proposed topic is not accommodated in any regular session. For this reason, it is expected to attract interest from several areas.

The importance of satellite imagery analysis in the context of armed conflict has gained considerable public interest over the past decade. The expansion of remote sensing satellite constellations dedicated to Earth observation has facilitated the continuous monitoring of war zones.
In the aftermath of the recent conflict in Ukraine, remote sensing has received increased attention and recognition for its ability to provide temporal and spatial awareness.
In earlier years, remote sensing was used primarily for reconnaissance and intelligence purposes. However, its role has evolved significantly and today it permeates all aspects of armed conflict, from detailed damage assessment to its critical role in facilitating humanitarian relief efforts.
As we look to the future, we can expect the importance of space-based remote sensing to continue to grow, with even more actors from governments to public institutions to private companies participating in this ecosystem, facilitated by the increasing availability of satellite missions and data, and the growing capabilities of automated image analysis.
With this community contributed session, we aim to provide a unified forum to bring together researchers and engineers interested in using satellite imagery for remote monitoring of armed conflict, and to foster collaboration, knowledge transfer, and interdisciplinary solutions among the international remote sensing community.
Contributions from authors will be considered in, but not limited to, the following topics:

- General remote sensing-based situational awareness
- Fusion of multi-sensor data for improved situational awareness
- Damage mapping
- Remote sensing in support of humanitarian aid

Session Overview

Sustainable agriculture is critical to ensure food security and address the UN’s 2030 SDGs goals. One of the key components in achieving sustainable agriculture is monitoring soil quality, as it directly impacts crop yields, land management, and ecosystem health. This seeks to bring together experts, researchers, and practitioners to explore the innovative applications of Earth Observation (EO) and remote sensing technologies in soil quality assessment.

Session Relevance to IGARSS 2024 Special Interests:
•	EO and Geo-sciences in the Support of SDGs - Agenda 2030: Monitoring soil quality is essential for achieving SDG 2 (Zero Hunger) and SDG 15 (Life on Land), as it directly influences crop productivity and land ecosystem health. Connection to most of the other SDGs may also be made (doi: 10.1016/j.geodrs.2021.e00398).
•	Geosciences and RS for Sector Sustainability: Our session will highlight how RS contributes to the sustainability of the agricultural sector through soil quality assessment.
•	Leveraging the Advancements of Flagship Space Programs: We will showcase how flagship space programs, such as Copernicus, are leveraged for soil quality monitoring.
•	Synergetic Use of Multiple EO Missions and Sensors: Our session will include the combined use of optical (multi- and hyperspectral), radar, LiDAR data from UAVs and satellites to improve the accuracy of soil quality assessments.

Session Topics
Our session will address the following General Topics:
•	SAR Imaging and Processing Techniques: Demonstrating how SAR data can be used to assess soil moisture content and surface roughness, which are indicators of soil quality.
•	Data Analysis: Presenting advanced data analysis techniques and algorithms for extracting soil quality information from remote sensing data.
•	AI and Big Data: Discussing the role of artificial intelligence and big data analytics in enhancing soil quality monitoring accuracy and efficiency.
•	Land Applications: Sharing case studies and practical applications of remote sensing for soil quality assessment in different land use scenarios.

Session Structure
The session will consist of a series of presentations and discussions by experts in the field, covering topics such as:
•	Multi- and Hyperspectral Data from airborne and spaceborne sensors for soil quality monitoring
•	Integration of optical sensors with Radar and LiDAR for Soil Quality Assessment
•	Novel Machine Learning Approaches and processing toolchains (e.g., synthetic bare soil composite generation) for topsoil quality monitoring

Expected Outcomes:
•	The session aims to foster collaboration among researchers, practitioners, and policy-makers to advance the application of remote sensing in soil quality monitoring.
•	Participants will gain insights into the latest developments in remote sensing techniques and their potential to support sustainable agriculture.
•	The session will provide a platform for networking and knowledge exchange, facilitating future research and project collaborations.

Permafrost occurs over approximately 22 % of the Northern Hemisphere land surface, including areas of continuous, sporadic or discontinuous permafrost. In a rapidly changing climate, regions affected by permafrost risk experiencing disruptions in local ecosystems, as well as land deformations and potential increases in greenhouse gas emissions induced by permafrost thaw. Due to scarcity of available observational networks on the ground, considerable efforts have been placed on monitoring permafrost dynamics by mean of Earth observation. However, as it is not currently possible to observe changes in permafrost directly from space, current methodologies rely on monitoring suitable proxies such as land surface temperature, snow cover and land surface subsidence, which can be linked to dynamics in the permafrost active layer. The development of modeling tools to ingest these and future Earth Observations is crucial. International initiatives, such as the ESA CCI+ Permafrost aim to assemble these methodologies to enable a coherent view of tracking hemispheric-scale trends in Permafrost dynamics. Meanwhile, local scale applications relying on e.g. SAR interferometry allow to track events such as landslides related to permafrost thawing.

We invite presentations on novel remote sensing tools and products for monitoring Permafrost regions. Relevant topics include, but are not limited to: land surface temperature products and sensors, detection of seasonal soil freezing, land deformation from InSAR or other methods, mapping of thermokarst formations, and sesonal snow cover dynamics over Permafrost regions. The session is organized on the initiative of the European Horizon-MSCA project “Cloud-based remote sensing data system for promoting research and socioeconomic studies in Arctic environments” (EO-PERSIST, HORIZON-MSCA-2021-SE-01).

Numerous studies on the emerging problems of the last decades have shown that the frequency of environmental disasters and their scale are constantly growing, leading to an increasing risk of great losses to the economy and human lives as well as the collapse of social infrastructure.
This explains why it is important to Geoscience and Remote Sensing to gather the current knowledge and open problems on the monitoring and nowcasting efforts in this field.
The information needed to monitor and nowcasting environmental disasters can be obtained using remote sensing, and in-situ measurements and access to knowledge-based historical data. The topics to be discussed in this session are the following:
• the type of instruments used or planned to be used to perform the ground truth and remote sensing measurements of environmental disasters.
• the cost required to obtain remote sensing and in-situ information on environmental disasters
• the type of mathematical models that can be used to both interpolate and extrapolate temporal and spatial data to increase the reliability of forecasting and nowcasting environmental disasters.

The 17 Sustainable Development Goals (SDGs) posed an urgent call for action of all United Nations Member States in 2015.
Strategies to improve health & education, to reduce inequality, and to foster sustainable economic growth need solutions to limit climate change.

Remote Sensing provide ample tools for monitoring and decision making towards an implementation of the SDGs.
Among others, time series to map land cover and land use track the growth of urban spaces, and allow to document the impact of natural hazards such as floods and wildfires worldwide and the disasters they can cause, offering invaluable insights on a global scale.

Artificial Intelligence (AI), in particular deep learning in computer vision and corresponding foundation models, successfully supports the research and applications in Earth observation (EO). The rapid development of technology, openly available remote sensing data from government agencies such as NASA and ESA, and open-source deep learning tools foster democratization of AI for social good.

However, a series of challenges for AI in EO needs collaboration to tackle:
- What are the limitations of AI techniques in using EO data to contribute to the SDGs?
- Do these limitations suggest urgent remote sensing missions to join forces in?
- Which novel AI methodologies may serve the SDGs best?
- How to engineer data science pipelines with reduced energy consumption in pursuit of sustainability?
- Beyond technological aspects, how do we bake ethics into AI for EO?

In this interdisciplinary session, we invite the community of remote sensing scientists, AI engineers, climate researchers, economists, legal experts, political decision makers, and ethicists to discuss the use of remote sensing for, and to reflect on the status of the UN's SDGs.

Synthetic aperture radar (SAR) provides the unique ability to quantitatively monitor the whole planet with high spatial resolution and precision. It has been widely used in agriculture, forest, soil moisture, ocean pollution monitoring, fire monitoring, flooding and earthquake, et.al. Recently, SAR has entered into a golden age in China. More than 5 national and/or commercial spaceborne SAR sensors are being operated today and more new SAR systems will be launched within the next 5 years. These include the current GF-3, LT-1 and Nvwa constellation missions, et.al. In addition, Chinese SAR imaging capabilities have developed towards high resolution, large swath and more observation dimensions, and the system becomes lighter, smaller and lower cost.

This has created a new class of radar data that has evolved significantly in recent years. In the meantime, hundreds of research articles have been published, exploring algorithms for SAR/PolSAR/InSAR signal processing and demonstrating related applications across many Earth observation fields of interest, from China. It is fair to say that SAR has evolved from its initial development as a new and pioneering radar remote sensing technique into a mature technology in China.

This session will invite contributions on reviewing the current China SAR missions on highlighting the latest trends, introducing the related SAR signal processing techniques and its applications in Earth science, and future advanced sensors. The primary goal of the session is to present current SAR systems, methods, applications and future missions in China. This session will gather contributions of world-renowned authors active in the fields of SAR.

Coastal marine environments, being invaluable ecosystems and host to many species, are under increasing pressure caused by anthropogenic impacts such as, among others, growing economic use, coastline changes and recreational activities. A continuous monitoring of those environments is of key importance for the identification of natural and anthropogenic hazards, for an understanding of oceanic and atmospheric coastal processes, and eventually for a sustainable development and use of those vulnerable areas. Here, Synthetic Aperture Radar (SAR), because of its high spatial resolution, along with its independence of day and nigh,  and its all-weather capabilities, is one sensor of choice.

This Community Contributed  Session (CCS) will focus on the way, in which SAR sensors can be used for the surveillance of changing marine coastal, environments, and how these sensors can detect and quantify processes and phenomena that are of high relevance for the local fauna and flora, for coastal residents and local authorities, and for a better quantification of hazards caused by global change. Examples include:
·	Coastline changes and coastal morphodynamics
·	Coastal run-off and marine pollution
·	Wind fields and storm events
·	Surface waves and currents
·	Illegal, unreported and unregulated fishing
·	Operational use of SAR and other sensors for coastal zone applications

Several internationally well-renowned experts will contribute to this CCS  and will provide a broad overview of SAR applications that are already, or have good potential to be used for the surveillance of changing marine environments worldwide. Although the focus of this CCS is on the application of SAR, the CCS organizers encourage submissions of non-SAR presentations that complement SAR and lead to a more comprehensive solution to address multiple end-user needs for sustainable development of the marine coastal zone. 

After more than two decades of dedicated research and experimentation, Synthetic Aperture Radar Tomography (TomoSAR), an evolution of multi-baseline SAR Interferometry (InSAR), has reached a level of maturity and operational readiness. A significant milestone in TomoSAR's development is height resolution capability, which requires the application of digital signal processing techniques to focus a data-stack containing multiple SAR images of the same area, acquired from various viewing angles.
TomoSAR has been showcased by diverse research teams in various application contexts. Prominent findings involve characterizing interior structures of natural environments like forests and snow, achieved through extensive airborne and ground-based campaigns. Furthermore, the results underscore the exceptional effectiveness of SAR tomography in monitoring deformation and detection of multiple Persistent Scatterers (PS) using satellite-based SAR sensors. Thanks to the availability of multiple SAR satellites, TomoSAR-based time-series deformation monitoring and PS detection has gained widespread popularity, delivering significant results and surpassing the capabilities of conventional InSAR, all owning to TomoSAR's vertical resolution ability.
The future prospects for TomoSAR appear as promising as ever. On one front, there is a focus on developing more sophisticated and high-performance SAR satellites, with several planned spaceborne SAR missions, especially those employing low-frequency sensors such as BIOMASS, NISAAR-ISRO, and Tandem-L. These missions are particularly poised to enhance height resolution capabilities over natural media from space. On the flip side, despite ongoing technological advancements, the tomographic process typically necessitates intricate and essential pre-processing and signal processing operations. It must contend with various challenges that impact the resolution and quality of 3D imaging and scatterer detection. These challenges include the presence of noise, temporal decoherence in stack SAR data, baseline distribution, and other factors that contribute to performance issues in TomoSAR applications. In light of the strong track record of artificial intelligence (AI) and deep learning techniques in various areas of SAR data processing, there have been recent endeavors to define DL-based methods for the TomoSAR domain as well. While the initial results have shown promise in addressing those TomoSAR challenges, several issues with AI in TomoSAR domain remain unresolved, including the absence of a definitive ground truth, the exploration of optimal architectures, and the integration of domain-specific knowledge with DL techniques.
This session, in addition to presenting the current state-of-the-art in space-based tomography, is directed towards the utilization of upcoming spaceborne missions and AI in the TomoSAR domain. The objective is to foster an open discussion about the presented findings to resolve the abovementioned challenges and to identify areas worthy of future investigation, with a particular emphasis on AI and forthcoming missions.

Currently, more than two billion people live in the near-coastal zones at the ocean-land interface with almost a billion more living in adjacent  low-lying coastal areas. These areas and populations are at risk from increasingly severe storms and longer-term sea level rise.  Digital twins, that is, the combination of data, models and AI/ML technologies that simulates Earth system processes and enables short- and long-term forecasts, provide understanding and actionable information to reduce risks to humans, infrastructure and ecosystems. 

The breadth of the topic is immense and covers coastal bathymetry and topography, terrestrial and marine water quality, terrestrial and marine ecosystems, agriculture, infrastructure and socioeconomic factors  There is increasing interest in using new technologies to assess the current state of coastal zones, what can we expect under climate change and how can we mitigate current impact and prepare for future impacts?  This session will bring together scientists that are using satellite and other observations to initialize, update and validate coastal zone process models.  The presentation should be organized around a use case composed of the nature and scope of the problem being addressed, data and models used, results and current or future linkages to digital twins.  Satellite data and models used as digital replicates are especially welcome.  The goals of this session are to provide a view of current work toward CZDT, provide opportunities to grow the coastal zone digital twin community, and foster collaboration.
This session is of importance to Geoscience and Remote Sensing because address key issues in SP 4 Digital Twins with respect to Coastal Zone O4.  The topic is timely and provides an opportunity for researchers working on data and replicate models to share insights and motivate progress on this vital subject.

The research direction of leveraging Artificial Intelligence (AI) for Geosciences and Remote Sensing has opened up exciting avenues and has proven to benefit a wide spectrum of applications. Disaster response and humanitarian applications require rapid analysis of large-scale Earth Observation (EO) data to generate actionable insights.  Given the tremendous volume of EO data coupled with its increasing availability, there is need to develop scalable Geospatial Artificial Intelligence (GeoAI) solutions that specifically cater to the demand of disaster response and humanitarian applications.  Scalability in this context refers to the ability to rapidly process and analyze large-scale EO data through the development of accelerated and optimized GeoAI methodologies in addition to leveraging high performance computing hardware. Although advancements in computing hardware have led to the development of machine learning for high-performance computing, it is not feasible to subscribe to the idea of unlimited storage and compute. Subsequently there is a dire need to develop scalable and accelerated GeoAI workflows for effective resource utilization.

This session seeks to host contributions focusing on novel scalable GeoAI systems targeted for disaster response and humanitarian applications. Topics in large-scale machine learning for high-performance computing methodologies and scalable optimization strategies for aiding humanitarian response efforts, disaster assessment and monitoring applications are invited to contribute this session. Given the deep societal impact of research on scalable GeoAI for disaster response and humanitarian applications, this session would serve as a great platform to bridge the gap between humanitarian practitioners, policymakers and researchers in IEEE GRSS community to discuss and collaborate on the latest research trends in this focus area.

The session titled “Signal and Data Processing in Atmosphere Remote Sensing” serves as a nexus for converging cutting-edge research and modern trends in Earth Atmosphere observation. This session unearths some nuances of capturing, interpreting, and harnessing data from diverse remote sensing instruments, discussing their advanced applications in atmospheric science. The session is composed from five presentations, which comes from different countries: USA, Ukraine, the Netherlands, and Israel. During the session, novel methods in radar technology for atmospheric remote sensing will be discussed based on the USA keynote presentation on emerging methods and means for signal processing in current operational polarimetric weather radars and next-generation phased-array meteorological radars. Participants will uncover and discuss the latest advancements in radar technology, linking these developments with the synergetic use of multiple Earth observation missions and sensors. This integration empowers researchers to obtain a holistic view of atmospheric processes and phenomena.
Diversity in frequency bands, polarimetric applications, different signal processing features, and multi-instrumentality during observation, and novel math models organically complement the noted above geographical diversity of the proposed presentations.
Compact Ka-Band Polarimetric Cloud Radar with a solid-state transmitter and original signal processing algorithms developed in Ukraine will be presented. This presentation underscores the importance of instrument calibration and data quality control, aligning with the crucial research direction of sensors, instruments, and calibration.
The session will discuss new developments extending Doppler radars for motion retrieval of turbulent and convective-scale motions based on some new ideas, came from Israel, about the cloud dynamics and its relation to microphysics. Understanding atmospheric dynamics at various scales has become vital for predicting extreme weather events and climate change impacts, aligning with the broader theme of atmospheric RS applications.
Advancing the discussion, experts from the Netherlands will unveil the potential of ultra-fast-scanning Doppler phased array radar for 3D wind retrieval. This technology bridges the gap between data acquisition and analysis, emphasizing the importance of signal processing and data analysis in modern atmospheric research.
The final presentation prepared in the TU-Delft by joint Ukrainian and Dutch team investigates multi-instrument rain observations, including W-band cloud radar, laser optical disdrometers, microwave radiometers, and weather stations. The fusion of these diverse datasets demonstrates the session's synergy with the overarching trends of data analysis, AI, and Big Data. The intricacies of combining data from various sources to enhance cloud radar calibration and improve the accuracy of atmospheric studies will be discussed.
Thus, this session offers a rather comprehensive consideration of the intricate world of signal and data processing in atmosphere remote sensing. By intertwining modern research directions such as the synergetic use of multiple sensors, data analysis, AI, Big Data, atmosphere applications, and sensors' calibration, participants will leave with a broader understanding of the dynamic and ever-evolving field of atmospheric science. We invite you to exchange ideas, and contribute to the ongoing quest for understanding the secrets of Earth's atmosphere through innovative signal and data processing techniques in remote sensing.

In the era of the space economy, satellite services represent a key element that must be valued and promoted by institutions at a local and global level. Satellites for Earth Observation, Navigation and Telecommunications represent the space sectors with the most significant growth, not only due to the level of maturity, quality and quantity of existing operational infrastructures, but especially for the potential impact of connected applications and services.
They are suitable for ensuring sustainable economic development, promoting significant progress in various sectors and generating benefits for citizens and society. For this reason, they have been recognized as the top strategic priorities of Italian space policies. The Italian Space Agency is the government body responsible for promoting space technology for the development of the country, for this reason has set up a program, called Innovation for Downstream Preparation (I4DP), dedicated to Public Institutions, Commercial Operators and Research Organizations to best meet and satisfy their needs.
The main goal of this initiative is to stimulate the growth of the downstream sector, offering concrete support for the creation of innovative space solutions for the emerging demand and, at the same time, consolidating and enriching the existing national know-how both from a scientific and industrial level.
The implementation of the programme is based on thematic periodic calls for each category of target users, with the main goals to promote the development of applications and value-added services based on EO data and the use of TLC/NAV satellite systems, also combined with each other and / or integrated with non-space data and services, allowing the acceleration of scientific and technological development, through the implementation of demonstrators and pilot projects and preparing a new generation of downstream services to support the governance and monitoring of the territory and its resources.
The first cycle of the I4DP programme, started in 2021, was focused on the following topics: Effects of climate change and extreme events, Sustainable Cities, Management and Monitoring of Infrastructures, also in relation to landscape preservation, and Precision Farming. All these calls were successfully closed in 2022 with the selection of about 20 innovative projects.
This initiative has a positive impact on the Sustainable Development Goals of the UN 2030 Agenda, both directly, as in the case of SDGs 9, 11, 13, 15, and indirectly as in the case of goals 1, 2, 3, 8, 12, in terms of green and sustainable economy, and 16, as increase of the communities participation in decision-making processes at all levels.
The proposed session aims to provide an overview on ongoing ASI’s downstream activities and their future prospects, highlighting the effects in support of entire national communities along the entire value chain of space services and the downstream economic sector, and providing a focus on the selected projects and their contribution in supporting the transition towards a sustainable future.

The Space for Climate Observatory (SCO) stands as a pivotal international initiative uniting stakeholders in the Earth Observation sector (https//www.spaceclimateobservatory.org). Its primary goal is to maximize the utilization of satellite data and digital technologies for decisive climate action. The SCO's mission revolves around coordinating global efforts to foster operational tools for climate monitoring, mitigation, and adaptation, targeting both decision-makers and the general public. To achieve this, the SCO leverages cloud computing infrastructures, satellite data, novel methodologies, and user-centric collaboration to deliver operational tools that empower individuals and policymakers to employ satellite data effectively for community resilience. Importantly, these projects are designed for adaptability to address environmental challenges in various geographic regions.
In line with its global mandate, the SCO also contributes to the United Nations Sustainable Development Goals (SDGs), emphasizing its multifaceted importance.

Our objective with this session is to present practical applications that highlight the role of processing remote sensing and in-situ data in monitoring climate change impacts. Many of these applications have evolved directly from the SCO initiative.

Through live demonstrations and case studies, this session aims to vividly illustrate how the SCO's collaborative efforts have translated into operational solutions. Attendees will gain insight into the transformative potential of the SCO, seeing firsthand how it advances geoscience and remote sensing, ultimately contributing to a more climate-resilient world.

This session proposal is from the Chairs/Co-Chairs of the Working Group of Active Optical and Lidar, IEEE-GRSS Technical Committee on Instrumentation and Future Technology (IFT). It is in-line with the GRSS outreach to Space Agencies and Industry and the IGARSS 2024 special theme on “Acting for Sustainability and Resilience”.

It is planned to have a two session (10 papers) on Space Lidar: Missions, Technologies, and Observations (Part 1 and 2) with emphasize on the invited papers from international space agencies, industry, and academia on enabling technology developments, space missions and observations.

This session focuses on research and developments in an important topic in active optical remote sensing: Space Lidar. Lidar's unique capability to observe a diverse variety of geophysical phenomena from orbit around the Earth and planets has stimulated new areas of remote sensing research that now attracts the attention of scientists and engineers worldwide. With a number of instruments already operational or pending launches within the coming years, many of their original technological issues have been resolved, still the long term reliability of key active components and the survival on harsh space environment requires additional efforts and investments. Some the key topics for this session are:

• Space Agencies (NASA, ESA, JAXA, CNES etc.) on-orbit missions, future missions, technical challenges, observations, and science products
• Continuation of work in the domain of long-lived/ high power UV/visible/infrared lasers and optics, especially contamination and optical damage
• Research to improve the reliability of lasers/diode lasers and high-power optics operated in vacuum 
• Space-qualification of tunable lasers and optics to support trace gas lidars operating in the 1-5 µm region 
• Space-qualification of higher efficiency lasers such fiber lasers and amplifiers. Radiation hardening is an area of particular concern 
• General power scaling of space-qualified lasers with a focus on improved efficiency and thermal tolerances 
• Improved high gain, low dark noise and low NEP space qualified/qualifiable array/detector at all wavelengths, and in particular in IR bandwidth 

This session will focus on science and applications addressed by space-based lidar, as well as on techniques and supporting technology. Our goal is that this session is to provide a stimulating forum where members of the international lidar and related technology communities can present and discuss results, trends, and future directions.

Earth Data, once collected and cleaned, get stored and served for manifold application purposes where they have gained immense societal impact over the years in domains like agriculture and food security, climate change, disaster mitigation, cities and communities sustainability, and further critical societal goals. Recently, technical platforms in support of such goals have started converging under the common concept of Digital Twins and with more and more integration of AI methods for potentially enhanced insight.

A variety of standards exists, issued by different bodies, and they tend to vary significantly with regards to interoperability of implementations, harmonization with related standards, practical usability, availability of compliance test suites, and in the end uptake by implementers, service providers, and users.

Obviously, any decision about what standards to adopt affects architecture, tool selection, and ultimately service quality and the value of insights gained. As such, their wise choice is of critical importance, so their wise choice is of critical importance for government authoBig Data, Datacubes, Standards, OGC, ISO
rities, the  private sector, and even academia.

In this session, key important standard families get presented and inspected critically. Presenters are actively engaged in standardization as editors and co-editors of one or more topical standards addressing Big Data, Digital Twins, Internet of Things, etc. and their interrelation. As such, this session provides a unique opportunity to get informed about the current Big Earth Data standards landscape, to assess relevance and impact of the various standards, and to stay abreast of trends, discussions, and innovations.

Agenda:
1. "Standards for Multi-Dimensional Gridded Geo Data Wrangling: A Status Update", Peter Baumann (confirmed)
2. "ISO TC211 WG6 Geographic Imagery: Purpose, Agenda, Activities", Graham Wilkes (confirmed)
3. "The New ISO/IEC Property Graph Query Language, GQL", Keith Hare (confirmed)
4. "The New OGC/ISO Analysis-Ready Data Specification", Liping Di (tentative)
5. Moderated Discussion with Speakers and Audience

The 17 Sustainable Development Goals (SDGs) represent the global domain targets identified by the United Nations in the "2030 Agenda for Sustainable Development" (2015). These goals, spanning from social and economic themes to land and water environmental topics, aim at fostering global-scale sustainable development  by eradicating poverty, promoting health, improving education levels, protecting the environment, boosting economic growth and achieving social equity and justice. Although policy makers, non-governmental organizations and media have made many relevant achievements in focusing global attention on these common issues, there is still a significant gap between identifying them and solving them in a cost-effective way.

The recent development of Earth Observation technologies and Geo-information methodologies provided new and attractive ways to improve our understanding of natural and human-induced dynamics which are critically changing life on our valuable Earth planet. Hence, they effectively provide key support to achieve SDGs identified in the United Nations’s 2030 Agenda for Sustainable Development.

Within this framework, this session welcomes outstanding original contributions from the scientific and research community on the use of state-of-the-art Earth Observation methods and Geo-information technologies with the aim of demonstrating how they can be used to fulfill specific SDGS related to marine and coastal environments. the agenda 2030 and Sustainable Development for Marine and Coastal Environment will be discussed. The general tasks to be addressed include, but are not limited to, the observation of oil and plastic ocean pollution to target the SDG n. 6 "Clean water and sanitation"; monitoring critical infrastructures related to green energy production sites as offshore wind farms to target the SDG n. 7 "Affordable and clean energy"; the analysis of the climate change impact on met-ocean parameters and marine biodiversity to target the SDG n. 13 "Climate action".

The topics that will be discussed in this session include, but are not limited to, cutting-edge microwave and optical remote sensing techniques and applications, artificial intelligence for remote sensing image processing, improvements of modelling and data fusion strategies, advanced geo-information systems and visual geographic environment applications. This session is supposed to be an ideal exchange platform for scholars with various research backgrounds to communicate their talented ideas in tackling social, economic and environmental issues related to the sustainable development of the oceans and coastal areas.

In the last decades, plenty of solutions have been devised to fully exploit the potential of passive imaging systems for Earth observation. In fact, due to technological, economic, and environmental constraints, the quality of the delivered products is bounded in terms of temporal, spectral and spatial coverage and resolution. Depending on the goals of the mission, these quality limits can be more severe on one dimension rather than another. For example, hyperspectral images are usually provided at a much lower spatial resolution compared to multispectral images. In many cases, think of Sentinel-2, WorldView, and PRISMA, as a tradeoff, the imaging systems provide multiresolution images where the higher spatial resolution is given only for subsets of spectral bands or even just for a single (panchromatic) one.  
 
In this frame, lots of methods have been designed to enrich the remote sensing acquisitions in terms of spatial and/or spectral, and/or temporal resolutions. These include, but are not limited to, the following cases:  
 
- Pansharpening: the fusion of a multi/hyperspectral image with a single higher-resolution panchromatic band, since many sensors provide this kind of multiresolution product. 
- MS-HS fusion: the fusion of a higher-resolution multispectral image with a lower-resolution hyperspectral image. 
- Single image super-resolution (no fusion). 
- Multitemporal super-resolution: a process aimed to reconstruct missing acquisitions due to adverse meteorological conditions or simply increase the temporal sampling of a time series. 
 
After many years of research, where traditional model-based methods have been playing a central role, in the last few years we have observed a paradigm shift from model-based to data-driven approaches, definitely putting the latter at centre stage. Behind this shift is the general expectation that the “knowledge”, or “experience”, hidden in the (big) data could allow to “see” what the models cannot.  
 
In this session we aim to put together contributions on the intimately related topics listed above, welcoming both model-based and deep-learning solutions, to promote a fruitful discussion about where we are on resolution enhancement and what we can expect for the near future. Among the hot questions to be answered we mention a few of particular interest:  
 
- How to face the scarcity of data? 
- To what extent deep learning solutions trained on synthetic data can generalize on real data? 
- Which is the current bottleneck for deep learning methods? Is it the loss, the network architecture, the training modality or the dataset? 
- Which role can play model-based approaches in the deep learning era? 

Remote sensing operations are increasingly comprised of systems of systems—systems operated and managed by multiple independent organizations but working together for mutual benefit—which exhibit competing objectives and constraints, due in part to the many stakeholders involved. The field of systems analysis integrates the development of advanced concepts and architectures with the assessment of benefits and sensitivities of systems using figures of merit to aid decision-making pertaining to complex systems. Systems analysis methods offer traceable, repeatable, and quantitative approaches to understanding and working with such systems. Applying systems-level analyses to remote sensing operations can identify mission architecture designs which perform well across programmatic and scientific factors such as cost, continuity of measurements, schedule, and risk. 
 
Traditionally, research presented at IGARSS focuses on specific technologies and science applications related to remote sensing, with systems analysis research being presented across different sessions with little commonality. This cross-cutting session will serve as a focused venue for researchers to demonstrate systems analysis, decision science, and portfolio analysis methods applied to architectural decisions at the mission- and portfolio-levels, as well as for remote sensing data product use and applications. A focused session dedicated to sharing this research will invite increased collaboration among researchers who work with systems analysis within the field of remote sensing. While the proposed session will best fit under the theme of ‘Mission, Sensors and Calibration’, it will also be integrative across ‘Data Analysis’ and ‘Modeling’ themes as well. Topics presented at this session could include trend analysis, trade space characterization and evaluation to search a large set of architectures for preferred alternatives, capability assessment including mission-level observing system simulation experiments, technology forecasting, value frameworks to quantify stakeholder needs and preference, and risk assessment methods to evaluate new sources of uncertainty from collaborative operations.

TanDEM-X (TerraSAR-X add-on for Digital Elevation Measurement) is a German Satellite mission that is successfully operating now already since 2010 and has opened a new era in spaceborne radar remote sensing. A single-pass SAR-interferometer with adjustable baselines in across- and in along-track directions is formed by adding a second (TDX), almost identical spacecraft to TerraSAR-X (TSX) and flying the two satellites in a closely controlled formation. TDX has SAR system parameters which are fully compatible with TSX, allowing not only independent operation from TSX in a mono-static mode, but also synchronized operation (e.g. in a bi-static mode). With typical across-track baselines of 200-600 m DEMs with a spatial resolution of 12 m and relative vertical accuracy of 2 m has been generated. The Helix concept provides a save solution for the close formation flight by combining a vertical separation of the two satellites over the poles with adjustable horizontal baselines at the ascending/descending node crossings. Form TanDEM-X a global high-resolution digital elevation model with vertical accuracies of 2m and spatial resolution of 12m was derived and is available for science use. 
In this session the status of the mission, the future acquisition plans and the new mission products are presented. In addition, an outlook will be given to the scientist of the way forward with the mission objectives, such that the scientist can prepare for future data acquisition and data requests.

During the last decade, SAR systems technology has reached its maturity as a remote sensing tool for Earth observation, especially when considering orbital platforms. SAR technology has contributed to different societal challenges as climate change, food security or natural and anthropogenic hazards monitoring. Despite orbital systems have and will continues to have a prominent role in the future, terrestrial systems have also demonstrated their usefulness, in particular for local monitoring or for time critical applications, where orbital system present several limitations nowadays, in particular for those applications needing revisit times in the order of minutes, hours or several days. 

Beyond the clear scientific interest of terrestrial systems, ground based radar and SAR systems have also awaken an important interest in private companies due to the appearance of commercial applications specially in the fields of subsidence monitoring, monitoring of vegetation / agricultural crop, change detection etc. These agile radar and SAR platforms require not only new compact SAR system designs, but also high-performance navigation using compact navigation systems and in some cases they are combined with vision systems, as well as adequate SAR imaging algorithms and DInSAR processing chains adapted to particular imaging geometries.

The aim of this section is to present both contributions from research institutions, as well as from private companies to show the current state-of-the-art of the of mapping based on terrestrial radar and SAR systems and applications developed, with a focus on geoscience applications.

A multitude of Earth observation applications require an accurate alignment of remote sensing imagery. These include intra-sensor alignment of different spectral bands, mosaicking of multi-temporal acquisitions, multi-modal registration for data fusion, and 3D reconstruction from multiple views. This session aims to address corresponding challenges and present possible solutions and enable scientific discourse. It is organized by the ISPRS Working Group II/1 on "Image Orientation and Fusion". While the scope of both GRSS and ISPRS shows large mutual overlaps, GRSS is traditionally more concerned with geoscience, Earth observation, and the semantic analysis of remote sensing images, while ISPRS has a strong focus on Photogrammetry - a topic somewhat underrepresented in GRSS. Following the mutual aim of both societies to collaborate and develop closer relationships between participants in the two organisations, this session aims to foster inter-society exchange and discussions. However, submissions are open to everybody with high quality work in the scope of the session. A non exhaustive list of topics of interest includes the following:
- Orientation of classical and unconventional images including but not limited to oblique images, historical images, and thermal infrared images
- Multimodal image matching for alignment, registration and fusion of multi-source imagery, e.g. optical and radar images
- Geometric, algebraic and learning-based approaches to multi-view stereo and structure-from-motion (SfM)
- Modern approaches in intrinsic/extrinsic camera calibration and bundle adjustment (BA), e.g. single-image calibration, online calibration, methods for handling ambiguous and degenerate configurations, large-scale BA, and structureless BA
- Vision-based measurement of dynamic processes, e.g. structural deformations
- Evaluation of performance, reliability, robustness, and generality of methods

The growing global population challenges the sustainability of the global community and the amplified climate change messages, which they have, direct consequences in the fields of water, energy, food security, social standards, economy and much more. In order to support the overarching principle of the UN SDG 2030 vision that “no one should be left behind”, and other global agendas that supports Sustainable Development, reliable, accurate and timely information are required at local, national and regional level, to address climate change related issues across all sectors. Innovation systems approach constructs comprehensive roadmaps to anticipate and improve impacts when climate goals and SDGs are mutually reinforced. 
National committees for sustainable development and governance thrive to be the regional nucleus for maximizing efforts’ integration between the various parties, owed to its societal responsibility towards achieving sustainable development goals (SDGs) at the local, regional and international levels.  In their capacities, their main goal is to support SDGs through active contribution to initiatives leading to scientific solutions, strengthening education and training systems, cooperating in research and practical solutions’ promotion. Therefore, quantifying the progress towards achieving the Sustainable Development Goals (SDGs) requires smart and reliable ways monitoring of the indicators and targets of the 17 SDGs.  Many of these indicators can be effectively and efficiently observed with Remote Sensing Earth Observation (EO) platforms and associated data assimilation systems.  This session will address the synergistic approaches of earth observations (EO) and modelling to showcase EO capacities while utilizing artificial intelligence and big data analysis to the climate studies across the whole world. It will address different areas within the 17 goals that includes but not limited to agriculture/food production, environmental measures and habitats, surface and ground water, renewable energy, sustainable cities, climate, life under water, coastal/marine ecosystems and life on land. This session aims to showcase different applications integrating EO with other information to quantitatively assess the SDG indicators. Such an approach will enable stakeholders and decision makers in their policy level decision making process and to craft a working management strategy. 

Environmental Satellite Systems are a very costly and essential part of the government's earth exploration resources. It is increasingly crucial to quantify the socioeconomic value of the benefits derived from the data from these systems and derived products in order to justify and ensure the procurement of their next generations. In recent years, several important studies have been conducted to enumerate and monetize the socioeconomic benefits of several national or regional environmental satellite systems (e.g., GOES-R, GeoXO, JPSS and Metop) and that such benefits far outweigh the lifecycle costs of those systems.

Furthermore, “satellite data are also supporting society in its efforts to adapt to the impacts of a changing climate. As the frequency and severity of extreme weather events increase, Earth observation missions are helping communities recover from these crises by providing timely information to the insurance industry.”

In this session, environmental economists and representatives from assorted sectors (government, private, academic) will discuss methodologies and findings from analyses that assessed the socioeconomic value of various environmental satellite system’s data and derived products.

The Surface Water and Ocean Topography (SWOT) satellite was launched on December 16, 2022. This innovative altimetry mission is a joint project of the National Aeronautics and Space Administration (NASA) and the French Space Agency “Centre National d’Etudes Spatiales” (CNES), with contributions from the Canadian Space Agency (CSA) and the United Kingdom Space Agency (UKSA).  The primary science payload, a bistatic Ka-band Radar Interferometer (KaRIn), provides almost global measurements of the height of fresh water over land as well as the sea surface over the oceans. These measurements are performed at significantly higher spatial resolutions than any prior altimetry mission, on 50-km swaths extending 10-60 km on both sides of nadir. In addition to ocean products on 250-m and 2-km grids, SWOT provides global snapshots of terrestrial water bodies whose surface area exceeds 250x250 m2 (lakes, reservoirs, wetlands) and whose width exceeds 100 m (rivers), at least twice every 21 days. In doing so, SWOT also enables estimations of river discharge and changes in lake water storage. The targeted water surface elevation accuracy is below 2 cm over ocean and below 10 cm (1-sigma) over continental water bodies after averaging over 1 km2. The first results are beyond expectations and indicate that SWOT is bound to revolutionize oceanography and hydrology. Public release of the data products is scheduled end of 2023.
The session covers the following topics:
- SWOT mission status
- The principal instrument KaRIn and its performances
- Science goals for oceanography and hydrology
- User products and assessed accuracy
- Data distribution
- Calibration and validation 
- Important steps in the processing of SWOT data
- Early results in hydrology (water surface elevation, slope, discharge, storage change...)
- Early results in oceanography including coastal areas (sea surface height, wind speed, wave height, bathymetry...)
- Results on Ka-band near-nadir backscattering (SWOT vs. other measurements and models) 

Enhanced understanding of the water cycle and water management practices are of critical importance for achieving multiple sustainable development goals (SDGs), in particular zero hunger (SDG 2), clean water and sanitation (SDG 6), life below water (SDG 14), and life on land (SDG 15). Remote sensing earth observations (EO) are poised to play a pivotal role in attaining these SDGs by facilitating the science, monitoring, and progress reporting required to meet these goals. 

In the 2017 Decadal Survey, the Surface Biology and Geology (SBG) mission concept was identified as necessary for addressing both scientific and applications across Earth systems. This forthcoming mission will consist of a visible to shortwave infrared (VSWIR) imaging spectrometer and a multispectral thermal infrared (TIR) imager, offering transformative insights into aquatic ecosystems and hydrology, which are essential for meeting SDGs. 

We welcome work that leverages the capabilities of VSWIR and TIR technology to advance the realization of these four key SDGs related to water resources and aquatic applications. Example research topics may include water quality analysis, and habitat protection and restoration, and
drought assessment across cryospheric and agricultural domains. In addition, we invite works centered on practical applications that explore how managers could utilize the combined capabilities of optical and thermal sensing to support aquatic ecosystem management and monitoring. These works should demonstrate the potential of integrating a variety of sensors, including, but not limited to imaging spectrometers (e.g., AVIRIS-NGs, EMIT, DESIS, PRISM), thermal imagers (e.g., ECOSTRESS, Landsat-TIRS), and visible multispectral sensors (e.g., Sentinel-2, Landsat).

Living in the era of massive Geo-Data, foundation models are rising as a way to learn from multi-source types of EO data, vectors, text and hold the promise of solving a wide variety of tasks, from the more traditional image segmentation ones to more exotic ones like conversational remote sensing, storytelling or forecasting climate. 
In this session, we have gathered experts working at the interface between remote sensing, computer vision and natural language processing, to talk about the next generation of AI models, toward foundation models setting up the ... foundation for the remote sensing models of tomorrow.

The synergetic use of Earth Observation (EO) missions, sensors and novel methods provide critical, reliable, and up-to-date information in a continuous manner, required to observe, monitor, and predict environmental factors in relation to land, water, and air, in various spatial and temporal scales, covering a range of multidisciplinary scientific topics. This information plays an important role in the environmental programs in many countries, assessing the current environmental information, and being part of the decision-making process for sustainable development through the involvement of stakeholders. The Eastern Mediterranean, Middle East, and North Africa (EMMENA) region is of great scientific interest, as it is greatly affected by Climate Change, and its aftermaths. The main objective of this Community Contributed Session is to explore the main challenges and the future directions of the synergetic EO-sensor driven approaches with an application area in the EMMENA region. The integration of novel EO, space and ground-based integrated technologies, can contribute to a more sustainable and systematic monitoring of the environment, the timely detection of societal risks/threats and the growth of vital economic sectors. The ultimate goal is to foster the sustainable development in line with the international policy framework (EU Societal Challenges, UN SDGs, Sendai Framework, Paris Agreement) and provide critical information through end user products to policy makers. The ongoing development of big Earth data techniques and the increasing availability of satellite EO data provide opportunities to better monitor the physical, human and built environment. As the EMMENA region is a fairly new segment for EO activities, there are many opportunities to expand in EO research by exploring the importance of synergetic use of EO missions and sensors for a variety of applications. Existing networks and projects in the EMMENA region have already contributed to the exploration of the importance of using EO sensors and methods for the efficient systematic monitoring of the environment. Indeed, EXCELSIOR and Eratosthenes CoE is one existing key player actor in the EMMENA region that has the potential to become a catalyst for facilitating and enabling international cooperation in EMMENA. 
A non-definitive list of possible applications and thematic research areas includes:
•	Droughts and water shortages in the region. 
•	Hazards: Fires, Floods, landslides, Earthquakes
•	Climate Changes and atmosphere (e.g., aerosols, clouds, interactions between atmospheric mechanisms and solar-related applications in a wide range of scales)
•	Agriculture (e.g., Decision-making tools for improving agricultural productivity, optimization of land and water management, exploring the spatiotemporal dynamics of ecohydrological processes, carbon footprint etc)
•	Water resources management and soil 
•	Solar radiation 
•	Urban and built-up areas (e.g., Land use/land cover changes degradation and desertification, population dynamics)
•	Cultural Heritage (e.g., risk assessment to natural and anthropogenic hazards, looting detection, documentation).
•	Marine surveillance applications, i.e., illegal immigration, oil spill detection, marine spatial planning, coastal zone management, sea surface level variations, etc.
•	Machine Learning, Artificial intelligence, and Big Earth Data applications in one of the applications
•	Other remote sensing and/or geoinformatics applications.

SAR systems on UAV and other mobile mapping platforms, such as cars, have increasingly gained attention also within the geoscience community. Small SAR systems deployed on such platforms offer complementary properties with respect to the revisit time, operational flexibility, and observation capabilities as compared to spaceborne and conventional airborne SAR systems. On the other hand, compared to stationary terrestrial radar/SAR systems, the increased synthetic aperture size of UAV/mobile mapping SAR systems allows to obtain a higher spatial cross-range resolution also for quasi-terrestrial observation geometries. 

These complementary properties of UAV/mobile mapping SAR systems open a large field of potential applications, some of which are addressed within the scope of this session including high-resolution DInSAR based measurements of surface displacements, monitoring of vegetation / agricultural crop, change detection.

From a system point of view, these agile SAR platforms require not only new compact SAR system designs, but also compact and innovative high-performance navigation using smaller INS/GNSS systems, in some cases combined with vision systems, as well as adequate SAR imaging algorithms and DInSAR processing chains adapted to the potentially non-linear sensor trajectories and partial aperture synthesis common to UAV/mobile mapping SAR systems and application.

UAV-borne SAR systems allow for experimental formation flying and therefore are an important tool to develop and test bistatic and multistatic SAR mission concepts including synchronization for future spaceborne SAR missions.

This invited session aims at giving an insight into recent state-of-the-art UAV/mobile mapping based SAR systems and applications developed with a focus on geoscience applications. 
After our successful invited/community contributed sessions on this topic during IGARSS 2021/2022 & and IGARSS2023 we would like to keep track of this topic providing insight into the latest technological developments with small SAR systems on UAV/mobile-mapping platforms.

The session typically covers a number of novel systems and UAV/mobile mapping platforms of different size, type (fixed-wing and VTOL UAVs, cars), and a range of applications such as repeat-pass differential SAR interferometry for displacement measurements, change detection, and tomographic configurations. 

We believe that our session topic UAV/mobile mapping based SAR systems and applications is of very high interest for the geoscience and remote sensing community already now and will be even increasing in the future.

Underwater remote sensing also belongs to Geoscience and Remote Sensing. Compared to other technology, sonar systems can provide much higher resolution images in water. Due to the high resolution, the sonar is a well-established remote sensing technique that has proven to be a useful technique for a large number of applications, ranging from underwater archaeology to underwater mapping and reconnaissance in the field of underwater engineering. The navigation, autonomous underwater vehicle (AUV) and electronics have achieved great progress in recent years. Thanks to these developments, the sonar based remote sensing has also been pushed into a new stage. The lightweight and compact sonar can be mounted ever smaller, highly flexible platforms. Besides, current algorithms are computationally more efficient. Furthermore, the sonar images are further improved based on various methods. Last but not at least, sonar technology is much more preferred by underwater engineering-users due to its high resolution.

Space-based surveillance is at the forefront of revolutionizing disaster management and climate monitoring, providing an unprecedented advantage through continuous and wide-scale coverage. In this ever-evolving landscape, satellites equipped with cutting-edge sensors are playing a pivotal role in addressing these global challenges. In the realm of disaster management, satellites offer real-time monitoring capabilities for a diverse range of natural disasters, from hurricanes and wildfires to floods and earthquakes. They not only assess the extent of damage but also predict the paths of these disasters, enabling more efficient emergency response strategies. Furthermore, satellite imagery aids in identifying vulnerable areas, greatly enhancing preparedness and risk mitigation efforts.

Turning to climate monitoring, satellites are indispensable tools for tracking key indicators of climate change. They provide valuable data on temperature fluctuations, sea level rise, glacial melting, and greenhouse gas emissions on a global scale. This comprehensive view of climatic patterns and trends is essential for early detection of environmental shifts, allowing scientists and policymakers to make informed decisions regarding climate mitigation and adaptation strategies. Technological advancements, particularly in sensor technology, have significantly improved data accuracy and accessibility, making satellite data an even more reliable resource. Additionally, international collaborations have expanded satellite networks, fostering a more coordinated and holistic approach to disaster and climate monitoring.

In conclusion, space-based surveillance is an indispensable asset in the fields of disaster management and climate monitoring. Satellites offer unparalleled coverage and data quality, empowering decision-makers with the information needed to safeguard our planet from natural disasters and the far-reaching impacts of climate change.

Maritime sustainability, security, and climate change are pressing global issues that require innovative solutions. Remote sensing, with its capacity to collect and analyze data from Earth's surface and atmosphere, stands as a pivotal instrument in addressing these multifaceted challenges. This conference session delves into the profound significance of remote sensing in the context of maritime affairs, elucidating its vital role in promoting sustainability, fortifying security, and mitigating the adverse impacts of climate change.

In the realm of maritime sustainability, remote sensing offers indispensable capabilities. It aids in monitoring and preserving marine ecosystems, tracking illegal fishing activities, and evaluating the overall health of our oceans. By showcasing the latest technological advancements, this session demonstrates how remote sensing contributes to the conservation of marine biodiversity and facilitates responsible marine resource management. Through remote sensing, we gain valuable insights into the complex dynamics of marine environments, fostering evidence-based policymaking and sustainable practices.

The session also underscores the paramount importance of remote sensing in maritime security. By enabling the surveillance of expansive maritime regions, remote sensing allows for the tracking of vessels, detection of illegal activities like piracy and smuggling, and the safeguarding of vulnerable coastal areas. Real-world applications and case studies will be presented, illustrating how remote sensing technology significantly enhances maritime security efforts. By enhancing situational awareness and response capabilities, remote sensing contributes to the overall stability and safety of maritime operations.

Additionally, climate change poses a dire threat to our oceans and coastlines. Remote sensing plays a pivotal role in monitoring sea-level rise, ocean temperature fluctuations, and the dynamics of polar ice caps. This session will delve into how remote sensing data supports climate research, aids in the development of adaptation strategies, and contributes to the mitigation of climate-related disasters. Through the integration of satellite and airborne remote sensing technologies, attendees will gain insights into monitoring long-term climate trends and assessing the vulnerability of coastal communities.

In conclusion, this conference session offers a comprehensive exploration of the critical role of remote sensing in advancing maritime sustainability, security, and climate change resilience.

 

By 2050, almost 6 billion people could suffer from water scarcity, according to the United Nation (UN), because of unconstrained natural resource consumption, climate crisis and inequitable economic expansion. Irrepressible industrial and agricultural activities, alongside extreme weather events resulting from climate change, pose ever greater threats to water resources. The significance of this water related “crisis” has been addressed in the UN’s 2030 Agenda, with the aim to “ensure availability and sustainable management of water and sanitation for all”, as included in Sustainable Development Goal (SDG) 6. Addressing water security (WS) involves the monitoring of water scarcity; water resources availability; water quality; hydrological processes; flooding and drought; population growth; land cover changes; as well as other attributes relating to ecosystems and human activity and transcends administrative regional and national borders. Acknowledging that WS is a wicked problem, the Water Security and Sustainable Development Hub (https://www.watersecurityhub.org), a £17.8M project established in 2019, has been funded by the UK Research and Innovation (UKRI) via the Global Challenges Research Fund (GCRF) to address global WS related issues in basins from low and middle income countries (LMIC) e.g. Colombia, Ethiopia, India and Malaysia.
Multi-modal and multi-scale Earth Observations (EO) coupled with advanced remote sensing approaches can complement scarce or even non-existent in-situ observations at LMICs, providing consistent time-series of spatio-temporal variations of water resources as a result of the complex challenges posed by evolving climate patterns. The proposed session will present scientific methods to provide temporal characterization of water bodies in Colombia, to model and predict flood susceptibility in Ethiopia, as well as to estimate water storage of inland waterbodies in Ethiopia, to quantify groundwater storage change and land subsidence in India, and to enhance the spatial resolution of precipitation data in Malaysia. In particular, the first study utilises multiple types of EO over the Upper Cauca River Basin in Colombia to monitor and characterize different water bodies over the years and correlate weather variables to climate change effects that turn into extreme increase or decrease of precipitations. The second study aims to predict the short- and medium-term future flood vulnerability of Addis Ababa, the capital of Ethiopia, under different climate change scenarios using a machine learning approach. To generate the prediction, multi-source data representing time-varying and invariant variables is collected and processed from satellites and other EO sources. The third study, exploiting GRACE GLDAS, FLDAS, CHIRPS and GLEAM datasets, estimates the water storage in the Central Rift Valley in Ethiopia. By analysing GRACE gravity anomalies alongside InSAR ground deformation, the fourth study monitors changes of groundwater resources across the megacity of Delhi, India. The fifth study focuses on enhancing the spatial resolution of precipitation data in the climatically variable Johor River Basin, Malaysia, through geographically weighted regression  applied to the IMERG satellite dataset, using also ALOS PALSAR DEM, the Dynamic World Land Cover dataset, Terra-MODIS LST and NDVI remote sensing products. These studies demonstrate state-of-the-art EO approaches; a step-change in monitoring and responding to water security challenges in rapidly urbanising LMIC contexts.

Wildfire science and technology support response activities, and vice versa. The stakeholder communities in fire management, response and suppression have tangible needs for risk assessment, real-time detection and tracking, as well as forecasting tools and technologies throughout the entire fire cycle (pre-fire conditions, active fires, and post-fire impacts). Science and technology provides the innovation and tools to aid this stakeholder community, ideally without standing in the way of active incident response. 
Government agencies, the private sector, and the academic sector can contribute the best available science and technology to help operational agencies overcome current barriers and provide more efficient and effective wildland fire management tools and capabilities. In the active fire community, airborne, ground, and space capabilities in fire science and technology are being codeveloped with partners responsible for wildland fire management, including testing nighttime detection and tracking from uncrewed aircraft. Mediterranean climates and landscapes like Greece, Portugal, Italy, and California, and others, have similar challenges and bear ample opportunities for collaboration. 
This session aims to bring together and showcase some of the key stakeholder perspectives, technologies and science to enable better fire management and response. Response agencies should ultimately be better prepared to manage future wildfires through improved predictive modelling, risk assessments, prescribed burn management and wildfire suppression, early arson detection, as well post-fire mitigation efforts.

This session describes IEEE Standards Association projects that have resulted in published GRSS-sponsored standards, as well as standards development projects that are currently underway or are being considered for the future. Submissions are welcome from all GRSS fields of interest where technology standards could promote innovation.

The sustainable development goals (SDGs) adopted by United Nations member states provide a framework for action on tackling climate change, promoting prosperity, and people's well-being for a better and sustainable future for all. The progress toward attaining SDGs is monitored by analyzing data collected from multiple sources (surveys, government agencies, social media,  etc.).  In addition, the images acquired from sensors onboard Earth Observation (EO) satellites also provide an opportunity to monitor the Earth's ecosystem and built infrastructure. The EO images can provide continuous temporal information over the globe and can cover most remote areas of the world. Besides, satellite images can improve and complement conventional statistical in-situ data collection, as well as provide new types of environmental information. Image analysis and data fusion methods continue to impact the EO applications, such as crop type mapping, mapping slums and urban areas, sustainable forest management, and disaster monitoring and response. These example efforts are well aligned with the SDGs, such as attaining Zero Hunger (SDG 2), Good Health and Well-Being (SDG 3), Sustainable Cities and Communities (SDG 11), Climate Actions (SDG 13), Life on Land (SDG 15), and Secure Property Rights (Multiple SDGs).
This session will focus on the role, opportunity, and challenges of Image analysis and data fusion-based methods applied to EO data by contributing to sustainable development goals.

The 2030 Agenda for Sustainable Development clearly stresses the importance of Geospatial Information and Earth Observations (EO) to monitor progress and achieve the SDG targets. Effective monitoring of the SDG indicators and reporting of the progresses towards the SDG targets require the use of multiple types of data that go well beyond the traditional socio-economic data that countries have been exploiting to assess their development policies. Hence, it is considered of crucial importance to integrate data coming from technologies new to this domain, such as EO, in order to produce high-quality and timely information, with more detail, at higher frequencies, and with the ability to disaggregate development indicators. EO, together with modern data processing and analytics, offer unprecedented opportunities to make a significant change in the capacities of countries to efficiently track all facets of sustainable development.
Amongst all the SDG targets, those related to a sustainable use of natural resources are of particular importance since pressures on our planet’s environment and finite resources are expected to increase further in the future to support continued economic growth or increased food production and consumption patterns. Recent advances in EO research, both on methodological development and technological solutions, offer promising prospects for helping countries set up informed and evidence-based development policies for an optimum management of terrestrial, coastal and marine resources.
The increasing spatial, temporal and spectral resolutions of EO data offer an invaluable opportunity for better informing development policies and quantifying various SDG indicators. However, those EO advances pose several challenges related to the acquisition, processing, integration, analysis and understanding of the data which need to be tackled by the scientific community in order to ensure operational applicability.
This invited session aims at presenting and showcasing the latest advances in EO solutions for achieving the SDG targets, monitoring progress and reporting on the SDG global indicator framework.

Datacubes today are acknowledged as a cornerstone for analysis-ready data and digital twins. Due to their natural, human-centric way of serving data - one spatio-temporal cube per sensor - they enable services which are easier to handle for users and more scalable on server side. Early on, the rasdaman ("raster data manager") Array DBMS has carried over business datacubes into science and technology, in particular: the Earth sciences. Meantime datacubes form an established research field, with many epigons often based on extending python libraries like xarray or using MapReduce-type base systems.

Data providers offering Earth datacubes from the US, Europe, and Asia have joined up to form a federation which is location-transparent to the user: they see a single, large datapool without needing to know where the data sit, including transparent distributed data fusion. Still, the participating data centers retain full autonomy on their own data. Recently, AI support is being added to enable seamless combination of classical analytical processing with Neural Networks based prediction libraries. Recently, the Cube4EnvSec datacube services on environmental monitoring and aviation safety have joined the federation.

EarthServer, which currently already offers 160+ PB (and growing) of Earth data, is free to join for the data providers (their offerings can be free or paid), with an open, transparent, democratic governance based on its Charter currently being established.

In this session, we provide an overview on the platform technology and its capabilities, as well as practical use cases from environmental monitoring, agriculture, and aviation safety. Many of the examples shown can be recapitulated and modified by Internet-connected participants.

Agenda:
- "The EarthServer Datacube Initiative: Introducing Planetary-Scale Location-Transparent Federation", Peter Baumann
- "Using Datacubes to Investigate the Threat of Thunderstorms to Civil Aviation", Colin Price (confirmed)
- "Detecting Medicanes From Climate & Weather Datacubes", Zafer Aslan (confirmed)
- "Formosat and its Use in Taiwanese Datacubes", Chen-Yu Hao (tentative)
- Moderated Discussion , Peter Baumann

Floods, making up a large portion of extreme weather events, are increasing in frequency and magnitude, heightening risks of livelihood and property losses. The emphasis is shifting from flood detection to comprehensive monitoring and validation of complete flood lifecycles—from onset to recession. Satellite imagery provides unmatched perspectives for continuous flood monitoring, analyzing their duration, assessing damages, and observing post-disaster recovery patterns. The current diversity of public and private satellite sensors, each with unique measurements, presents unprecedented opportunities to track and validate floods. Integrating diverse sensor data is pivotal for reliable, nuanced insights. With machine learning and cloud computing, there is an increasing drive to produce near real-time flood lifecycle maps. However, challenges such as the complex task of validating flood maps remain. Multiple independent observations are needed as no single source provides the complete ground truth. The objective is to bridge the gap between our machine learning models-derived flood maps and the on-ground experiences of the affected population.
Most importantly, we need to effectively disseminate our combined knowledge of floods for immediate support to the first responders and for an equitable post-disaster damage assessment. The Remote Sensing Environment, Analysis and Climate Technologies Technical Committee (REACT TC) within the IEEE Geoscience and Remote Sensing Society is a group of scientists and engineers specialized in using state of the art in remote sensing to mitigate the impacts of climate change and help in achieving the United Nations sustainable development goals. This invited session, sponsored by the REACT TC, aims to showcase how various stakeholders in the earth sciences and impact organizations are facilitating sensors, methods, and frameworks to produce knowledge for flood monitoring and validation. We hope to foster collaborations to focus on converting sensor data to drive action.

New strategies and solutions based on high-frequency, high-resolution monitoring and assessment of natural disasters are essential  to preserve the environment and build resilient infrastructures. For instance, a comprehensive assessment of past and current natural disasters (e.g. floods) and their associated damages supports an innovative infrastructure planning that is required to build disaster-resilient communities. 2023 has been another year with numerous devastating water-related disasters hitting many regions across the globe. For example, following storm Daniel that devastated Libya on 10 September 2023, more than 4,000 fatalities have been confirmed and more than 8,000 people are still missing. In this context, advanced remote sensing coupled with numerical prediction modelling appears to be the way forward for: (i) addressing water-related disasters in order to reduce damages and save lives, and (ii) proposing innovative solutions that preserve the environment and support developing resilient infrastructures.

Flood assessment and resilient infrastructure management through remote sensing data are important and challenging research topics. Numerous research groups focus on these topics and applications developed in this area are vast. From 2018 to 2023 we have gathered several scientists from these groups in IGARSS invited sessions to facilitate the exchange of knowledge and experience on the flood mapping topic. Moreover, it allowed to strengthen collaborations between the remote sensing and risk management communities interested in remote sensing flood assessment associated with 3-D (i.e., water depth) and 4-D (i.e., spatial-temporal) models. In addition, the intense discussions between the presenters and a large audience were testimony to the fact that there is a high interest within the flood mapping and risk reduction communities to collaborate on the development of solutions enabling the built up of a more disaster-resilient infrastructure at both local and global levels.

The objective of the 2024 IGARSS session is to introduce related research studies focusing on both remote sensing fundamentals and advanced algorithms based on big data and cloud-computing technologies. Emphasis will be on flood disasters and applications in near-real time monitoring and predictions, as well as long-term risk analyses using advanced satellite Earth Observation (EO) data. EO data coupled with innovative scientific solutions allow to address in a precise manner the level of disaster damages on different land classes including: coastal flood mapping, urban flood-area and damage detection, analysis of weather impacts on agricultural lands, or delineation of reference/historical flood zones. Moreover, for rapid recovery activities and resilient infrastructure investment, flood monitoring using EO data in near real-time is an imperative process in the early stage analysis. Rapid flood detection techniques based on multi-sensor EO imagery are one of the main subjects that will be addressed in the IGARSS 2024 session.

Floods can be very disastrous events, inducing a lot of fatalities as well as damages to properties, infrastructure, and the environment at a global level. Indicatively, in 2022, 176 floods were recorded worldwide, killing 7954 people, affecting 57.1 million people, and resulting to economic losses of 44.9 billion USD, according to the latest available data for 2022, published by the Centre for Research on the Epidemiology of Disasters.
Flood risk assessment and flood monitoring are crucial for efficient disaster management, including the design of civil protection measures in flood-prone areas, and the implementation of studies with proper interventions (both structural and non-structural) towards mitigating flood risk. This is even more crucial in highly dense urban areas, with large population, critical infrastructure and important socioeconomic activities.
This session will present state-of-the-art products and services which are implemented in support of multi-parameter flood risk assessment and management planning at high spatial resolution. These solutions integrate different data sources, including remote sensing, field visits and hydrological and hydraulic simulations, and are characterized by considerable added value, as they support public actors and stakeholders in decision-making and management of floods.
The session will bring together experts and showcase important achievements, including from the EuroGEO Disaster Resilience Action Group, the H2020 e-shape project and the Copernicus EMS. More specifically, presentations will include the flood early warning and near-real-time flood monitoring system “FloodHub” (assimilating flood modelling with the integration of crowdsourced data, in-situ data from hydrometeorological telemetric stations and satellite earth observation data), the real-time flood forecast and early-warning system “SOL”, the flood risk & impact assessment through automatic change detection of Sentinel-1and Sentinel-2 images “FRIEND”, the multi-parameter high-resolution flood risk assessment in the region of Attica (for the needs of the Civil Protection Authority of the Attica Region), as well as the Global Flood Awareness System (GloFAS) operational system of the European Commission’s Copernicus Emergency Management Service (forecasting and monitoring floods across the world).
These innovative works provide support to the decision-making process of the relevant authorities and key stakeholders in the direction of a more effective disaster management towards disaster risk reduction and more resilient communities, especially in the urban areas. This is in line with the requirements for the implementation of the EU Floods Directive 2007/60/EC, the Sendai Framework for Disaster Risk Reduction, the UN SDGs, as well as the GEO’s Societal Benefit Areas.

After six years of successful CubeSat sessions at IGARSS, this year (2024) we plan to organize sessions focusing on progress of CubeSat and smallest missions contribution to future of remote sensing. With the advent of CubeSat and SmallSat deployments by both Government and Commercial entities, there is a need to assess their impact on scientific research. Since 2012 NASA Earth Science Technology Office has been running research program targeted toward technology validation in space, In-Space Validation of Earth Science Technologies (InVEST). This program encourages flying new technologies and new methods on CubeSat platforms. Recently ESA under their new Space through the FutureEO programme selected four CubeSat proposals. This shows an increased interest in CubeSat based missions. Recently we have been able to gather science grade data from some of our CubeSats.
Since we have graduated from amateur experiments of building CubeSats, it is time to look into possible science applications of these platforms. We plan to focus on NASA/InVEST, ESA/Scout and similar programs in other organizations. This will give an opportunity to showcase the latest developments in the remote sensing through smaller platforms. Principal Investigators will be presenting their latest results from their missions. This will give an opportunity for broader community to get a quick overview of the latest technology in Remote Sensing through CubeSats.
This session will be high-level forum bringing together scientists from all over the world involved in the research, design, and development of CubeSat based instruments for Remote Sensing Applications.