Large-scale machine learning models for atmospheric and Earth system dynamics, also known as foundation models, are currently being developed. Examples include Aurora, ORBIT, the WeatherGenerator, and the developments as part of the SwissAI initiative. When compared to machine learning weather forecasting models, foundation models present a unique set of challenges and opportunities. For instance, when training a model on numerous datasets, questions arise regarding the selection of these datasets, the way they should be integrated during training, and the assessment of training efficacy. Additionally, large, pre-trained machine learning models require adaptation to specific applications through techniques such as fine-tuning and distillation, which aims to streamline the model's parameters for optimal performance. In the field of weather and climate science, the potential of post-pre-training methods has yet to be fully explored. To ensure the dissemination of knowledge and the exchange of insights within the community, it's essential to share and discuss the lessons learned during pre-training at scale. The current session collects contributions on the development of large-scale machine learning models and their application to specific problems. The session encourages submissions that address methodological questions related to the development or evaluation of large-scale models (e.g., conservation of physics), as well as studies on the technical aspects (e.g., training on hybrid HPC systems) or that focus on specific applications.

Large language models (LLMs) and agentic workflows are rapidly transforming scientific research by enabling new capabilities in literature and data discovery, analysis, coding and insight generation. At the same time, their deployment requires rigorous attention to safety, reliability and trustworthiness in scientific contexts.

This session will highlight both the transformative applications and the critical challenges of using LLMs in science. Key topics include developing specialized guardrails against hallucination and bias; creating robust evaluation frameworks, including uncertainty quantification; ensuring scientific integrity, data governance and reproducibility; and addressing unique scientific risks.

We invite submissions on novel scientific applications of LLMs and agentic workflows, methods that ensure integrity and reproducibility, safety mechanisms (e.g., guardrails, risk mitigation, alignment), responsible AI frameworks (including human-in-the-loop design, fairness, and ethics) and lessons learned from real-world deployments. Our goal is to foster discussion on pathways toward safe, effective and trustworthy use of LLMs for advancing science.

The emergence of generative artificial intelligence (AI) tools such as OpenAI, Google DeepMind and Meta, has opened new frontiers in geoscience research, education and communication. These tools offer a range of capabilities, including code generation, data interpretation, report drafting, and knowledge summarization. They provide new opportunities to accelerate workflows, enhance accessibility, and support interdisciplinary collaboration.
This session welcomes contributions that explore the application of generative AI tools across geoscientific disciplines. Submitted contributions should be related and not limited to the following topics:
- AI-driven approaches in geosciences
- The use of LLMs for scientific writing and literature review automation
- GenAi for geoscience education, training or public outreach
- Natural language processing in geospatial data management
- Critical assessments of LLM accuracy, bias and ethical considerations
-Integration of generative AI in geoscientific data acquisition, processing and interpretation
The goal of this session is to bring together geoscientists, data scientists, educators, and technologists to discuss the potential and limitations of generative AI in the field of geoscience.
Real-world applications, case studies, tool demonstrations and conceptual frameworks are all welcome. The session format will support oral, poster.

Deep learning is revolutionizing geosciences by enabling advanced pattern recognition and predictive modeling across complex datasets. This session welcomes contributions on applications of deep learning in the full spectrum of earth sciences, submitted abstracts are related but not limited to: -Reservoir characterization, -Remote sensing, -Mineral exploration, -Natural hazard forecasting, -Hydrology, and climate modeling. Emphasis is placed on architectures, data strategies, explainability, and integration with domain knowledge. Oral and Poster presentations are welcome.

Machine Learning (ML) is increasingly integrated into weather and climate science workflows, from emulating complex dynamical systems to enhancing predictive capabilities and uncertainty quantification. However, the opaque nature of many ML models poses challenges for scientific credibility, operational deployment, and stakeholder trust. Explainable AI (XAI) offers a suite of methodologies to interrogate, interpret, and validate ML models, enabling more transparent and accountable use of data-driven approaches in Earth system science.

This session invites contributions that advance the use of XAI to improve trust, interpretability, and robustness in ML applications across weather and climate domains — not only to validate and constrain models, but also to enable scientific discovery and insight. We welcome submissions that address:

• Development and application of XAI techniques for interpreting ML-based forecasts, reanalyses, and climate projections
• Integration of physical constraints and domain knowledge into interpretable ML frameworks
• Use of XAI to diagnose model biases, failure modes, and uncertainty propagation
• Explainability-driven approaches to support causal inference, feature attribution, process understanding, and knowledge discovery, including the identification of emergent patterns or physical insights from ML models
• Human-in-the-loop and stakeholder-informed validation of ML models in climate and weather services
• Tooling challenges in applying XAI to high-dimensional, regression-based climate and weather problems where current methods are often limited in scalability, generality, and interpretive power
• Operational and policy-relevant applications of XAI in climate adaptation, mitigation, and risk assessment

We encourage interdisciplinary submissions that bridge ML, weather and climate science, software engineering, and human-computer interaction, and that demonstrate real-world impact or translational potential.

Hybrid intelligence refers to integrated systems of human and machine intelligence, combining the adaptive, contextual, and ethical reasoning of humans (individually and collectively) with the computational power and scalability of AI. This session will explore practical applications of hybrid intelligence in geosciences – covering areas such as knowledge curation, decision support, data analytics, science communication, and actionable science. We will also address the ethical and societal dimensions of human‐centred AI, ensuring that scientists remain at the core of innovation. For geoscientists, hybrid intelligence means fusing deep Earth science expertise with AI-driven insights to tackle complex environmental and societal challenges. The emphasis is on AI, including generative AI, as a tool to empower and extend human insight in geoscience workflows, not to supplant it. We welcome contributions that advance the discussion on harnessing AI responsibly for the benefit of both humanity and the progress of geosciences.

Contributions may address, but are not limited to, the following topics:
-AI tools for geoscientific analysis and outreach
-AI-enhanced decision support systems
-Leveraging knowledge graphs
-Generative AI and Deep Learning in geosciences
-Geoscience-specific AI agents
-Ethical considerations of applying AI in geosciences

Modern challenges in climate risk management, disaster response, public health, resource management, and logistics demand robust spatiotemporal analysis of increasingly complex geospatial datasets. Recent studies, however, highlight significant challenges when applying ML and AI to spatial and spatio-temporal data along the entire modelling pipeline, including reliable accuracy assessment, model interpretation, transferability, and uncertainty assessment. This gap has been recognised and led to the development of new spatiotemporally aware strategies and methods in response to the promise of improving spatio-temporal predictions, the treatment of the cascade of uncertainties, decision making and facilitating communication.

This session focuses on the strategic integration and application of artificial intelligence (AI) and machine learning (ML) to address these challenges. We welcome contributions that explore novel methods, software tools, and infrastructures designed to improve spatiotemporal predictions, manage cascading uncertainties, and support decision-making. Emphasis will be placed on interpretability, transferability, and reliability across the modelling pipeline, as well as on the communication of results to diverse stakeholders. Case studies, theoretical advances, and cross-disciplinary approaches are encouraged.

Europe has embarked on an ambitious journey to build the next generation of digital replicas of our planet. The European Commission’s Destination Earth (DestinE) initiative is at the heart of this effort: a multi-year programme, implemented by ECMWF, ESA and EUMETSAT, that is developing high-precision digital twins of the Earth system to model, monitor and simulate natural phenomena, hazards and the related human activities. DestinE combines cutting-edge Earth observations, advanced Earth system modelling, Artificial Intelligence (AI), and Europe’s most powerful supercomputers to deliver actionable insights on climate adaptation, disaster risk reduction, and sustainable development. Complementing this effort, ESA’s Digital Twin Earth programme, together with EU Horizon Europe projects and national initiatives, are advancing the scientific foundations and Earth observation components that underpin these digital twins.

This session invites contributions that explore the applications of Earth system digital twins, co-designed with stakeholders, ranging from extreme event prediction to long-term climate adaptation, from urban liveability to marine and hydrological systems. Building on the successful Digital Twin sessions at EGU in recent years, this session offers a forum for sharing user perspectives that will help shape Europe’s digital twin ecosystem and its global relevance.

The development of digital twins for Earth systems, such as Destination Earth, is revolutionizing our approach to understanding and managing risks associated with climate change and natural hazards. These advanced simulations enable us to integrate diverse datasets, providing a comprehensive view of climate dynamics and human-environment interactions. By combining predictive models with real-time observations, digital twins offer unprecedented opportunities to make predictive Earth observation, explore "what if" scenarios, simulate hazard cascades, and test various adaptation strategies.
This session is dedicated to exploring the role of digital twins in enhancing our capacity for hazard prediction, risk assessment, and anticipatory mitigation action. We seek contributions that demonstrate how digital twins can be used to generate synthetic data, refine predictive models, and provide actionable insights for disaster risk management. We are particularly interested in studies that highlight the synergies between digital twin technology and other AI-driven tools, such as predictive analytics and machine learning, in improving operational outcomes. By focusing on the intersection of digital twins and predictive modeling, this session aims to foster cross-disciplinary dialogue on how these converging technologies can accelerate resilience to climate-related risks and natural hazards, including in a variety of impact sectors (energy, food, etc…). We invite researchers and practitioners to share their insights and developments in this rapidly evolving field, paving the way for more robust and effective preparedness and disaster response strategies.

Digital Twins (DTs) are dynamic virtual representations of physical processes, already applied in engineering and industry. Their main strength lies in the continuous assimilation and visualisation of large, spatially distributed datasets, integrating different sources and types of data with numerical simulation models. This enables replication of system behaviour, provides an up-to-date status of ongoing physical processes, and supports informed decision-making. DTs represent powerful frameworks that bridge physics-based models, observational data, and AI to improve our understanding, forecasting and management of the subsurface. While a digital twin is often designed to address a specific question or topic, there is still no standardised workflow or consensus on the methodology to be used. Given the growing number of emerging projects, the complexity of workflows, and the wide range of disciplines involved, this remains an important topic for discussion.

This session invites contributions on methodologies, (semi)automated workflows, and applications of digital twins for the subsurface, with a special focus on uncertainty quantification, data assimilation, multi-source data streams, automated data cleaning, and decision support. We particularly welcome studies addressing subsurface workflows from multi-type data to decision-making, including advanced optimisation methods, Bayesian approaches, machine learning, hybrid modeling, as well as economic, social components and policy considerations. Case studies from groundwater, geothermal energy, energy storage, hydrogen, carbon storage, geomodelling, natural risks and other subsurface-related systems are also encouraged. The session aims to foster dialogue on methods across disciplines and highlight both challenges and opportunities in building reliable subsurface digital twins.

Foundation Models (FMs) are set to revolutionize domains like Earth Observation (EO) and Earth Sciences. Trained on vast unlabeled datasets via self-supervised learning, they can uncover complex patterns and latent information. Once pre-trained, Geospatial FMs can be adapted to diverse tasks with minimal fine-tuning or additional data. As a result, this paradigm shift is set to reshape the entire information value chain, with far-reaching implications for industry, research and development, and the broader scientific community.

This session aims to share the latest research and technological advances and discuss practical solutions for effectively integrating FMs into the Earth Observation and Earth Sciences ecosystems. We encourage interdisciplinary collaboration, and submissions from AI researchers, EO and Earth data scientists and industry experts, as well as from stakeholders from High-Performance Computing (HPC), Big Data, and EO application communities.

The main topics for the session are:
● Latest Advances in AI Foundation Models: FMs can process data from various sensors, including multi- or hyper-spectral, SAR, LiDAR, and more, enabling comprehensive analysis of the Earth's dynamics holistically. Recent progress marks a shift from sensor-specific models toward sensor-aware or sensor-agnostic architectures.
● Benchmarking and Evaluating Foundation Models: Establishing standardised fair evaluation metrics and benchmarks to assess the performance and capabilities of FMs, ensuring reliability and efficiency, moving beyond simplistic or canonical use cases.
● Embedding and Geospatial Semantic Data Mining: FMs enable advanced geospatial semantic mining by leveraging latent space embeddings to uncover meaningful patterns and relationships. This enhances interpretation while reducing the need for large volumes of raw data across time and space.
● Implications of Foundation Models for the Community: Understanding the potential societal, environmental, and economic impacts of FMs, fostering informed decision-making and resource management. Seamless integration with downstream systems such as digital twins, public dashboards, and early warning platforms, including deployment at the edge (e.g. onboard satellites) is essential. Emerging roles of Agentic AI, in synergy with Large Language Models (LLMs) open new pathways for autonomous, context-aware EO applications.

Machine learning is reshaping the modelling of many physical processes in Earth system models, offering new routes for parameterisation, emulation, and hybrid modelling. This session focuses on the use of machine learning to emulate computationally expensive and unresolved processes, accelerate physical models, simulate across weather and climate, and improve representation across domains such as convection, turbulence, radiation, hydrology, sea ice, and other components of the Earth system.

Topics include (but are not limited to):

- Subgrid-scale parameterization via machine learning (for example those related to air-sea & land-atmosphere interactions)
- Emulators of physical processes, model components, or whole weather and climate models (including end-to-end learning)
- Hybrid ML-physics modelling frameworks
- Foundation Models
- Reinforcement learning (such as for ensuring physical consistency, stability, optimising model behaviour and improving time-series modelling)
- Physics-informed neural networks, neural operators, and differentiable programming
- Verification of data-driven models (including AI forecasting)
- Physical behaviour, encoding and analysis of AI parametrisations, emulators and whole models (such as through feature-based evaluation/conditional vs unconditional evaluation)
- Calibration and parameter optimization using ML
- Coupling of ML models with physical models
- Cross-domain applications (atmosphere, ocean, cryosphere, land).

This session provides a critical overview of current progress and emerging directions in the application of ML across parametrisations, emulation and hybrid modelling.

Machine learning (ML) is advancing the fields of geotechnics and geosciences by enabling data-driven subsurface characterization, predictive modeling, and real-time decision support.
This session invites contributions on ML applications in geotechnical and geoenvironmental engineering. Topics may include slope stability, tunneling, foundation design, subsurface flow and transport, seismicity, and coupled hydro-mechanical processes. Studies leveraging supervised, unsupervised, and deep learning methods; physics-informed neural networks; and hybrid ML–finite element method frameworks are encouraged.
We also welcome work that integrates ML with monitoring data (e.g., Internet of Things (IoT) sensors, remote sensing), inverse analysis, and the development of digital twins for predictive maintenance, structural health monitoring, and hazard mitigation.
Submissions that demonstrate model interpretability, uncertainty quantification, benchmark comparisons, or hybrid data–model approaches are especially encouraged.

Proper characterization of uncertainty remains a major research and operational challenge in Environmental Sciences and is inherent to many aspects of modelling impacting model structure development; parameter estimation; an adequate representation of the data (inputs data and data used to evaluate the models); initial and boundary conditions; and hypothesis testing. To address this challenge, methods that have proved to be very helpful include a) uncertainty analysis (UA) that seek to identify, quantify and reduce the different sources of uncertainty, as well as propagating them through a system/model, and b) the closely-related methods for sensitivity analysis (SA) that evaluate the role and significance of uncertain factors (in the functioning of systems/models).

This session invites contributions that discuss advances, both in theory and/or application, in methods for SA/UA applicable to all Earth and Environmental Systems Models (EESMs), which embraces all areas of hydrology, such as classical hydrology, subsurface hydrology and soil science.

Topics of interest include (but are not limited to):
1) Novel methods for effective characterization of sensitivity and uncertainty
2) Analyses of over-parameterised models enabled by AI/ML techniques
3) Single- versus multi-criteria SA/UA
4) Novel methods for spatial and temporal evaluation/analysis of models
5) The role of information and error on SA/UA (e.g., input/output data error, model structure error, parametric error, regionalization error in environments with no data etc.)
6) The role of SA in evaluating model consistency and reliability
7) Novel approaches and benchmarking efforts for parameter estimation
8) Improving the computational efficiency of SA/UA (efficient sampling, surrogate modelling, model identification and selection, model diagnostics, parallel computing, model pre-emption, model ensembles, etc.)
9) Methods for detecting and characterizing model inadequacy

Data imperfection is a persistent and multi-faceted challenge in hydrology and more broadly in geosciences. Researchers and practitioners regularly work with datasets that are incomplete, imprecise, erroneous, heterogeneous, or redundant—whether originating from in-situ measurements, remote sensing, modelling outputs, or participatory sources.
While traditional statistical methods have long been used to address these limitations, the growing complexity and diversity of hydrological and environmental data have created new demands—and opportunities—for innovation. Advances in artificial intelligence, data fusion, knowledge representation, and reasoning under uncertainty now allow for more robust integration and interpretation of heterogeneous information.
This session aims to gather contributions that explore how we can move from imperfect, fragmented data toward coherent and actionable hydrological and environmental knowledge. We welcome abstracts on:

• Applications and case studies in hydrology or other domains, addressing missing data imputation, model inversion, uncertainty propagation, or multi-source integration—using time series, spatial data, imagery, videos, etc. The case studies may focus on hydrological and natural hazards (floods, droughts, earthquakes, landslides, marine submersion, etc..) or resources management (water supply, treatment, etc…)
• Methodological developments in data fusion, completion, uncertainty quantification, and AI-based knowledge extraction from heterogeneous data.
• Cross-disciplinary approaches that connect geosciences, and specifically hydrological sciences, with AI, data mining, and knowledge systems, including citizen science, crowd-sourced data, or opportunistic sensing.
• Experimental contributions in hydrology and geosciences relying on AI, such as novel models and algorithms, explainable methods, and comparative studies on domain-specific datasets.
• Feedback from data integration initiatives into domain specific or cross disciplinary repositories.

We particularly encourage contributions that highlight novel practices or conceptual frameworks for dealing with imperfect and multi-source data in complex environmental systems.

The integration of satellite remote sensing and ground-based in-situ observations provides a powerful foundation for understanding environmental variability and change. When coupled with hybrid modeling approaches combining Artificial Intelligence/Machine Learning (AI/ML) with physics-based models, these multi-source datasets enable deeper process-level understanding, improved prediction, and actionable insights. This session emphasizes advances at the intersection of observations and hybrid modeling, focusing on how they improve our ability to analyze, attribute, and predict variability and extremes in environmental time series ranging from precipitation and aerosols to carbon fluxes and land–atmosphere feedbacks.
Recent progress in various satellite-derived products (e.g., precipitation from GPM/IMERG, aerosol optical depth/AOD, black carbon concentrations, vegetation and carbon flux indicators) and ever-expanding ground-based networks has greatly enhanced our capability to detect and monitor environmental parameters and their variability. At the same time, hybrid approaches such as physics-informed ML, data assimilation with AI, explainable AI, and transfer learning are emerging as transformative tools to improve predictive skill for extremes, attribute their sources, and assess long-term trends. Together, these innovations are reshaping how we study historical variability and future projections, and how results are translated into actionable information for climate adaptation and resilience.

In recent years, technologies based on Artificial Intelligence (AI), such as image processing, smart sensors, and intelligent inversion, have garnered significant attention from researchers in the geosciences community. These technologies offer the promise of transitioning geosciences from qualitative to quantitative analysis, unlocking new insights and capabilities previously thought unattainable.
One of the key reasons for the growing popularity of AI in geosciences is its unparalleled ability to efficiently analyze vast datasets within remarkably short timeframes. This capability empowers scientists and researchers to tackle some of the most intricate and challenging issues in fields like Geophysics, Seismology, Hydrology, Planetary Science, Remote Sensing, and Disaster Risk Reduction.
As we stand on the cusp of a new era in geosciences, the integration of artificial intelligence promises to deliver more accurate estimations, efficient predictions, and innovative solutions. By leveraging algorithms and machine learning, AI empowers geoscientists to uncover intricate patterns and relationships within complex data sources, ultimately advancing our understanding of the Earth's dynamic systems. In essence, artificial intelligence has become an indispensable tool in the pursuit of quantitative precision and deeper insights in the fascinating world of geosciences.
For this reason, aim of this session is to explore new advances and approaches of AI in Geosciences.

The rapid growth of missions, observatories, and monitoring systems in the heliosphere, across the Solar System and from terrestrial or airborne facilities has created an unprecedented volume and diversity of data. Making sense of these observations requires methods that can both process large datasets efficiently and extract meaningful physical insight. Machine learning has become an important tool in this effort, complementing established physics-based approaches by enabling new ways of discovering patterns, building predictive models, and working with complex or incomplete measurements.

In recent years, increasing attention has been given to hybrid methods that combine machine learning with physical models. These approaches are now being applied across planetary and heliophysical domains, from forecasting solar eruptions and solar wind conditions, to automating the analysis of planetary surfaces or improving on-board data handling. They demonstrate how data-driven methods can benefit from physical knowledge, while physics-based models can be improved through modern data analysis techniques.

This session aims to provide an inclusive and interdisciplinary forum for researchers applying machine learning in planetary sciences and heliophysics, as well as those developing methods at the intersection between data-driven and physics-based approaches. We particularly encourage contributions that illustrate the wide range of applications, encourage exchange between disciplines and showcase the transition from research to operations.

The recent revolution of data-driven forecasting systems based on artificial intelligence (AI) has opened new research possibilities in weather forecasting, climate science, and various other areas. At the same time, many open questions remain–such as how to properly evaluate the model outputs in terms of generalizability under climate change, whether models extrapolate to unseen extremes, and to what extent they are consistent with physical principles. This session focuses on new scientific approaches emerging from this AI revolution, limitations of current models, and strategies to overcome them. We encourage submissions that explore a wide range of topics, including evaluations of outputs and comparisons to numerical models, technical advancements in initial condition optimization or model fine-tuning, novel techniques from explainable AI, and other relevant studies. Bringing together experts from AI, climate sciences, statistics, and applied math will foster interdisciplinary collaborations and guide scientific progress in this quickly evolving field of research.

Land surface processes play a key role shaping the Earth climate. As a core component of state-of-the-art Earth System Models (ESMs), the representation of these processes critically influences and enables climate feedbacks that are essential for predictions and future climate-change projections, as investigated in international multi-model initiatives such as CMIP6 & CMIP7. However, land hydrology and its numerous interactions with other components of the Earth system (biosphere, biogeochemical cycles, anthropogenic disturbances/practices) is rather poorly represented in most state-of-the-art ESMs, potentially inducing erroneous responses to anthropogenic climate forcings at global, regional and local scales. For instance, ESMs do not represent the decline of groundwater levels that is increasingly observed in water-limited regions, threatening the subsistence of groundwater-dependent ecosystems, and thus leading to the risk of ecosystem shifts and to progressive levels of desertification.
This session is therefore open to observational and modeling contributions aimed at progressing the understanding and the modeling of the hydrological, biophysical and biogeochemical processes and couplings in land surface models. Particular attention will be dedicated to the representation of the interaction between hydrological processes and the biosphere (including the human component) to properly characterize the carbon-water nexus as well as the effects of land-based mitigation/adaptation options to climate change (e.g. involving management of forests, crops and irrigation practices, etc).
The overarching aim of this session is to provide an open and collaborative space that allows to bridge disciplinary gaps between members of the different communities involved in modeling the land surface for climate prediction and climate-change studies. We especially encourage contributions highlighting future priorities, innovative strategies and emerging opportunities to drive the development of next-generation ESMs.

The complex interactions and interdependencies of hydrological and land surface processes within the Earth system pose major challenges for prediction and understanding. Machine learning has become a powerful tool for prediction across these domains, but leveraging its scientific potential goes beyond applying existing algorithms and data. It requires detailed understanding and problem-specific integration of domain knowledge with data-driven techniques to make models more interpretable and enable new process understanding. This session explores how machine learning techniques are currently used to integrate, explain, and complement physical knowledge in hydrology and land surface modeling, including studies of surface and subsurface water dynamics, soil-vegetation interactions, land-atmosphere exchanges, and eco-hydrological processes. Submissions are welcome on topics including, but not limited to:

- Explainability and transparency in data-driven hydrological and land surface modeling;
- Integration of process knowledge and machine learning;
- Domain-specific model development;
- Data assimilation and hybrid modeling approaches;
- Causal learning and inference in machine learning models;
- Data-driven equation discovery;
- Challenges and solutions for hybrid models and explainable AI.

Submissions that present methodological innovation, critically assess limitations, or demonstrate contributions to process understanding across scales are especially encouraged.

Reliability in water research depends on two key aspects: the availability of robust observational data and the rigorous selection and validation of model frameworks. This session highlights the importance of data acquisition, quality control, and curation in supporting reliable methodologies across hydraulic and hydrologic engineering.
In hydraulics, flume experiments provide controlled, high-quality datasets but are resource-intensive and limited in scalability. Numerical modeling offers greater flexibility to simulate diverse flow conditions, yet its accuracy is highly sensitive to parameterization, boundary conditions, and discretization schemes. In hydrology, sparse and uncertain field data further complicate model calibration and validation.
Recent advances in artificial intelligence (AI) and machine learning (ML) allow researchers to analyze large and heterogeneous datasets. However, risks arise when dataset adequacy, representativeness, or validation are overlooked, leading to ambiguous outcomes. These issues intensify when experimental, numerical, and AI-driven approaches are not cross-validated or integrated, weakening robustness and transferability.
This session aims to strengthen understanding of data curation and model selection as critical, though often overlooked, components in solving water resource challenges. Topics of interest include:
1. Strategies for data acquisition, handling, and curation across laboratory, field, numerical, and AI/ML approaches.
2. Best practices in optimization, calibration, and hyper-parameterization to improve model performance.
3. Frameworks for integrating laboratory, field, and computational datasets for consistency and cross-validation.
4. Data curation methods that enhance efficiency, reproducibility, and reliability in modeling.
Through interdisciplinary dialogue, the session seeks to generate methodological insights and practical guidelines that enhance accuracy in data handling and model selection. The overarching goal is to advance high-quality, validated, and context-relevant outcomes that strengthen resilience and reliability in water research.

Water sustainability is becoming a key concern worldwide due to hydrological uncertainty, climate change, landuse landcover changes, and growing water pollution. These drivers greatly influence the catchment hydrology and thus their roles cannot be undermined while assessing both surface and groundwater resources. These aspects draw paramount significance in catchments with large heterogeneity and spatial complexities such as mountainous and urban catchments, data scare regions, and low-income countries where investment in hydrological monitoring network and installation of IoT sensors is very limited. It is therefore warranted to leverage geospatial, machine learning and decision science techniques to improve the understanding of catchment hydrology and the adverse consequences of climate change and anthropogenic drivers on surface and groundwater resources, which may play vital role in intensifying water, food and energy security. The worldwide readily available satellite remote sensing data and global data products of hydrometeorological and biophysical parameters enable us to leverage potential of geospatial and machine learning techniques in addressing challenges associated with climate change, landuse landcover changes, water scarcity, groundwater management, and ecosystem services.

This session aims to bring together professionals from multidisciplinary fields such as hydrology, hydrogeology, geosciences, agriculture, and environmental sciences & engineering to share their innovative ideas, research outcomes, and innovative insights obtained from case studies of different catchment settings by utilizing geospatial, artificial intelligence and machine learning techniques. We solicit novel contributions from the researchers to investigate and manifest revolutionary developments in the catchment hydrology by utilizing Remote Sensing with Satellite and Drone Platforms, GIS, Artificial Intelligence (AI), and Machine Learning (ML) techniques for addressing pressing challenges of water sustainability in mountainous and urban catchments and data scarce regions. The combined use of these technologies is revolutionizing and providing powerful tools in analysing and understanding complicated hydrological processes, which in turn will be very useful in evolving effective water resource management strategies to foster sustainable development and ecosystem-based adaptation to hydrological uncertainty, climate change and anthropogenic drivers.

Increasing climate variability and water scarcity are placing unprecedented pressure on agricultural systems worldwide. To address these challenges, the agricultural sector is rapidly adopting precision technologies that combine remote sensing capabilities with artificial intelligence to optimize crop water management. This session focuses on cutting-edge applications of remote sensing technologies and AI-driven analytics in transforming agricultural water management practices. We welcome research that demonstrates innovative approaches to monitoring, predicting, and managing agricultural water resources through the integration of Earth observation satellites, unmanned aerial systems, Internet of Things (IoT) sensors, and advanced computational methods.
Key topics included:
1) Multi-platform remote sensing applications (satellite, UAV, hyperspectral, SAR, thermal infrared) for estimation of soil moisture and crop water requirement.
2) Deep learning and AI-driven crop water stress detection and yield prediction.
3) Precision irrigation systems and automated water management technologies.
4) Multi-sensor data fusion combining space-based, airborne, and ground observations.
5) Real-time monitoring systems and subseasonal-to-seasonal water demand forecasting models.
6) Digital agriculture platforms and decision support tools for sustainable water management.
This session aims to showcase practical solutions that bridge the gap between technological innovation and real-world agricultural applications, emphasizing scalable approaches that support both productivity and environmental sustainability.

This session will provide a platform for showcasing state-of-the-art techniques in the use of remote sensing, AI and physics-based models to address hydro-climatic extremes. Participants will gain insights into how machine learning algorithms, data mining approaches, physical models and satellite data integration can significantly enhance our predictive capabilities for floods, droughts, heatwaves, storms, landslides, and other climate-induced hazards. The session will highlight innovative applications and real-world case studies that demonstrate how these technologies can be applied for disaster risk reduction, emergency response, and climate adaptation. Through discussions on the latest methodologies and practical applications, the session will facilitate cross-disciplinary collaboration between remote sensing experts, climate scientists, AI researchers, hydrologists, and policy makers.
Key Themes:
Remote Sensing and AI Synergies: The integration of satellite observations and machine learning models to enhance the detection, monitoring, and prediction of hydro-climatic extremes.
Data Mining Techniques for Climate Extremes: Harnessing the power of data mining to uncover hidden patterns in large-scale climate data, improving risk assessment and predictive capabilities.
Hybrid Modeling Approaches: Combining physical-based hydrological and climatological models with AI-driven simulations to offer more precise, real-time predictions.
AI for Early Warning Systems: How machine learning models are being employed to build more accurate early warning systems for various hydro-climatic hazards, including floods, droughts, heatwaves, and tropical storms.
Real-Time Risk Assessment: The use of AI to assess risks associated with hydro-climatic extremes, helping policymakers and disaster management agencies to make data-driven decisions quickly and effectively.
Predicting Long-Term Hydro-Climatic Impacts: AI applications in understanding the long-term effects of climate change on water resources, agriculture, and infrastructure, allowing for more sustainable planning and management.
Physics Modelling Based approaches: Physics based hydrological and hydrodynamics models in understanding the flood and drought complexities.
Hydro-climatic Extreme Events: Understanding the impacts of a range of hydro-climatic events, including: Flooding, Droughts, Heatwaves, Storms and Cyclones, Landslides, Wildfires.

Effective and enhanced hydrological monitoring is essential for understanding water-related processes in our rapidly changing world. Image-based river monitoring has proven to be a powerful tool, significantly improving data collection, analysis, and accuracy, while supporting timely decision-making. The integration of remote and proximal sensing technologies with citizen science and artificial intelligence has the potential to revolutionize monitoring practices. To advance this field, it is vital to assess the quality of current research and ongoing initiatives, identifying future trajectories for continued innovation.
We invite submissions focused on hydrological monitoring utilizing advanced technologies, such as remote sensing, AI, machine learning, Unmanned Aerial Systems (UAS), and various camera systems, in combination with citizen science. Topics of interest include, but are not limited to:
• Disruptive and Innovative sensors and technologies in hydrology.
• Advancing opportunistic sensing strategies in hydrology.
• Automated and semi-automated methods.
• Extraction and processing of water quality and river health parameters (e.g., turbidity, plastic transport, water depth, flow velocity).
• New approaches to long-term river monitoring (e.g., citizen science, camera systems—RGB/multispectral/hyperspectral, sensors, image processing, machine learning, data fusion).
• Innovative citizen science and crowd-based methods for monitoring hydrological extremes.
• Novel strategies to enhance the detail and accuracy of observations in remote areas or specific contexts.
The goal of this session is to bring together scientists working to advance hydrological monitoring, fostering a discussion on how to scale these innovations to larger applications.

This session concentrates on extreme rainfall events, surface water dynamics, and flood events, exploring innovative remote sensing, AI, and digital twin technologies for real-time monitoring, risk assessment, and mitigation. It invites submissions on advanced data integration, modeling approaches, early warning systems, and decision-support tools to improve understanding, forecasting, and management of flooding and related surface water hazards.

The integration of AI with digital twin improves the analytical and operational capabilities of geospatial systems, which through the analysis of historical data and the integration of real-time information (IoT) are able to highlight even “hidden patterns” in the data, identifying new models capable of improving forecasts with greater control over the quantification of uncertainty and the variability of the phenomenon analysed.

This session aims to focus on flood hazard and risk assessment, monitoring, and management. This Topic invites the submission of articles focused on, but not limited to, the following areas:
• Monitoring of extreme rainfall events and flood hazards for risk assessment and communication.
• Digital twins (DTs)/prototypes of DTs in flood hazard forecasting, early warning, monitoring, and supporting tools for urban governance.
• DSSs to extract meaningful information in the artificial intelligence era, eventually serving to reduce risk and provide support tools to mitigate flood hazards.
• The role of AI and digital twins to assess the economic impacts of flood hazards and the cost-effectiveness of various mitigation strategies.
• Novel techniques to analyse big data coming from Earth observation platforms, drones, and other geospatial data in order to provide timely information related to the extend, exposure, and impacts of flood hazards.

The global transition towards sustainable energy and green technology is reliant on critical resources -- such as geothermal energy sources and mineral deposits. To maintain and accelerate progress, we require an improved understanding of: (i) how and where these resources arise; (ii) techniques to identify, characterise and constrain prospective locations; and (iii) strategies for effective, sustainable and low-impact resource development. Addressing any of these questions requires advances in our ability to simulate a wide range of geological processes, and in our capacity to generate actionable insights from these models in combination with complex, uncertain observational datasets.

This session focusses on the computational and methodological developments necessary for progress towards more sustainable energy. We welcome submissions that address a diverse range of topics -- including simulation e.g. of themo-chemical flow processes, subsurface imaging, data fusion and AI -- with their application to critical resources as a unifying theme.

Machine learning (ML) and artificial intelligence (AI) are transforming the way we study the cryosphere. These data-driven tools are rapidly increasing in popularity and offer potential impact throughout the scientific workflow, from the way we design studies, observe processes, collect data, model phenomena, and analyse systems to the way we construct and test hypotheses. While ML and AI methods applied across the cryosphere may be originally intended to answer a particular cryospheric question, the solutions developed to solve these specific problems may offer generalisable approaches and transferable insights to issues in other domains of the cryosphere. As such, this session invites contributions using ML and AI from all branches of cryospheric science, including snow and avalanches; permafrost; glaciology; ice caps, ice sheets, ice shelves and icebergs; sea ice; and freshwater ice. We also welcome contributions focusing on dataset development, theoretical research, and community-building initiatives. This session intends to provide a forum for cross-cutting discussions and knowledge exchange, fostering interdisciplinary collaboration and ultimately promoting the efficient and effective application of ML and AI in the cryosphere.

Quantum computing is a rapidly growing field with potential for significant advancements relevant for Earth sciences, such as machine learning or the solution of partial differential equations. This session welcomes submissions on use cases and demonstrations for quantum computing in Earth observations and climate modelling as well as relevant algorithmic developments.
Expected topics include but are not limited to hybrid classical and quantum machine learning algorithms, quantum computing for solving differential equations, quantum algorithms for Earth image analysis and radar data, quantum hardware-specific algorithms, explainable quantum AI, quantum-enhanced training of machine learning models, time series analysis.

Spatio-temporal datasets are constantly growing in size, due to increases in extent and resolution. Because of
this, existing software to read, store, and write datasets, and translate the data may not be able to perform
the work in a timely manner anymore. This limits the potential of numerical simulation models and machine
learning models, for example.

In this session we bring together researchers working on novel software for processing large spatio-temporal
datasets. By presenting their work to their colleagues we aim to further strengthen the field of
high-performance computation in the geosciences.

We invite everybody recognizing the problem and working on ways to solve it to submit an abstract to this
session. Possible topics include, but are not limited to:

- High-performance computing, parallel computing, distributed computing, cloud computing, asynchronous
computing, accelerated computing, green computing
- Algorithms, libraries, frameworks
- Parallel I/O, data models, data formats, data compression, data cubes, HDF5, netCDF, Zarr, COG
- Containerization, Docker, Kubernetes, Singularity, Apptainer
- Physically based modelling, physics informed machine learning, surrogate modelling
- Model coupling, model workflow management
- Large scale hydrology, remote sensing, climate modelling
- Lessons learned from case-studies

We recommend authors to highlight those (generic) aspects of their work that may be especially of interest to
their colleagues.

Cloud computing has emerged as the predominant paradigm, underpinning nearly all industrial applications and a significant portion of academic and research projects. Since its inception and widespread adoption, migrating to cloud computing has posed substantial challenges for numerous organizations and enterprises. Leveraging cloud technologies to process big data near their physical locations represents an ideal use case. These cloud resources provide the necessary infrastructure and tools, especially when combined with high-performance computing (HPC) capabilities. The integration of GPUs and other pervasive technologies—such as application containerization and microservice architecture—across public and private cloud infrastructures further supports computation-intensive AI/ML workloads that used to reside only within HPC environments.
Session Focus
This session focuses on use cases involving both Cloud and HPC computing. The goal is to assess the current landscape and outline the steps needed to facilitate the broader adoption of cloud computing in Earth Observation and Earth Modeling data processing. We invite contributions that explore various cloud computing initiatives within these domains, including but not limited to:
• Big Data Infrastructures and Platforms: Case studies, techniques, models, and algorithms for data processing on the cloud.
• Cloud Federations and Interoperability: Scalability and interoperability across different domains, multi-provenance data management, security, privacy, and green and sustainable computing practices.
• Cloud Applications, Infrastructure, and Platforms: IaaS, PaaS, SaaS, and XaaS solutions.
• Cloud-Native AI/ML Frameworks: Tools and frameworks for processing data using AI and ML on the cloud and/or HPC.
• Cloud Storage and File Systems: Solutions for big data storage and management.
• Operational Systems and Services: Deployment and management of operational systems on the cloud.
• Data Lakes and Warehouses: Implementation and management of data lakes and warehouses on cloud platforms.
• Convergence of Cloud Computing and HPC: Workload unification for Earth Observation (EO) data processing between cloud and HPC
We encourage researchers, practitioners, and industry experts to share their insights, case studies, and innovative solutions that promote the integration of cloud computing and HPC in Earth Observation and Earth Modeling.

Earth System Sciences (ESS) datasets, particularly those generated by high-resolution numerical models, are continuing to increase in terms of resolution and size. These datasets are essential for advancing ESS, supporting critical activities such as climate change policymaking, weather forecasting in the face of increasingly frequent natural disasters, and modern applications like machine learning.

The storage, usability, transfer and shareability of such datasets have become a pressing concern within the scientific community. State-of-the-art applications now produce outputs so large that even the most advanced data centres and infrastructures struggle not only to store them but also to ensure their usability and processability, including by downstream machine learning. Ongoing and upcoming community initiatives, such as digital twins and the 7th Phase of the Coupled Model Intercomparison Project (CMIP7), are already pushing infrastructures to their limits. With future investment in hardware likely to remain constrained, a critical and viable way forward is to explore (lossy) data compression & reduction that balance efficiency with the needs of diverse stakeholders. Therefore, the interest in compression has grown as a means to 1) make the data volumes more manageable, 2) reduce transfer times and computational costs, while 3) preserving the quality required for downstream scientific analyses.

Nevertheless, many ESS researchers remain cautious about lossy compression, concerned that critical information or features may be lost for specific downstream applications. Identifying these use-case-specific requirements and ensuring they are preserved during compression are essential steps toward building trust so that compression can become widely adopted across the community.

This session will present and discuss recent advances in data compression and reduction for ESS datasets, focusing on:

1) Advances in and reviews of methods, including classical, learning-based, and hybrid approaches, with attention to computational efficiency of compression and decompression.
2) Approaches to enhance shareability and processing of high-volume ESS datasets through data compression (lossless and lossy) and reduction.
3) Inter-disciplinary case studies of compression in ESS workflows.
4) Understanding the domain- and use-case specific requirements, and developing methods that provide these guarantees for lossy compression.

Scientific discovery today increasingly depends on the availability and effective use of digital services and infrastructures that span the entire research workflow. From initial data generation and acquisition, through storage, processing, analysis, and collaboration, to dissemination and long-term preservation, researchers rely on a diverse ecosystem of tools that must interoperate seamlessly. While individual solutions exist for many of these steps, the real potential emerges when services are integrated across providers and disciplines, enabling researchers to work more efficiently, transparently, and at scale.

This session will showcase how e-infrastructure tools, services, and integration projects can support researchers in tackling complex scientific and societal challenges. We aim to highlight how interoperable digital services can complement each other to provide end-to-end support, how integration across infrastructures strengthens research capacity, and how collaboration between providers and communities can foster innovative solutions.
We particularly welcome contributions that:
- Demonstrate practical examples of how digital services and infrastructures enhance research workflows in Earth and environmental sciences.
- Present approaches to integrating tools and services across domains and providers, including outcomes from collaborative projects, to deliver more comprehensive user support.
- Share lessons learned from engaging with research communities, including user-driven design, training, and support strategies.
- Address challenges of interoperability and sustainability of distributed digital services, and highlight pathways to foster collaboration across infrastructures and research domains.

By bringing together diverse perspectives from service providers, research infrastructures, and end users, this session will provide researchers with a unique overview of the digital landscape available to support their work. It will also foster dialogue on how different infrastructures can collaborate more effectively, and how the research community can take full advantage of integrated, sustainable digital solutions to advance both science and society.

Knowledge discovery in Earth System Science (ESS) relies on observational, experimental and simulation data being available for all compartments (atmosphere, land surfaces, ocean, solid Earth, biodiversity) of the Earth system. On top of that, leveraging the potential of large-scale AI tools and generative AI requires data to be interoperable in a machine-actionable, AI-ready way. Towards this goal, several research infrastructures are aggregating, structuring and distributing science data for researchers to be exploited and combined through a portfolio of services. Hereby, programs to foster these activities have been initiated by national as well as international initiatives, resulting in a colorful mix of domain-oriented, geographically-oriented, or target group-oriented research infrastructures.

Shaping the European Open Science Cloud (EOSC), all of them share the goal of offering seamless access to high-quality and reusable research data and services following the FAIR principles and Open Science paradigms. We aim to implement this goal as a network of actors on both the national as well as the international level, making best use of the given opportunities.

The aim of the session is to foster the ongoing discussion on how to jointly shape the European research infrastructure landscape for EES driven by high-level and cross-disciplines scientific use cases and best practice scenarios.

We welcome contributions:
showcasing successful examples of creating synergies among different research infrastructures,
demonstrating efforts in building new products based on integrating services from multiple providers,
identifying gaps by highlighting needs deriving from specific research questions,
presenting use cases which should be taken-up by joining forces among research infrastructures.
Representatives of some international research infrastructures will be invited to elaborate on these actions.

It has become more than evident by now that the increasing complexity and resource intensiveness of performing state-of-the-art Earth System Science (ESS), be it from a modeling or a pure data collection and analysis perspective, requires tools and methods to orchestrate, record and reproduce the technical and scientific process. To this end, workflows are the fundamental tool for scaling, recording, and reproducing both Earth System Model (ESM) simulations and large-volume data handling and analyses.

With the increase in the complexity of computational systems and data handling tasks, such as heterogeneous compute environments, federated access requirements, and sometimes even restrictive policies for data movement, there is a necessity to develop advanced orchestration capabilities to automate the execution of workflows. Moreover, the community is confronted with the challenge of enabling the reproducibility of these workflows to ensure the reproducibility of the scientific output in a FAIR (Findable, Accessible, Interoperable, and Reusable) manner. The aim is to improve data management practices in a data-intensive world.

This session will explore the latest advances in workflow management systems, concepts, and techniques linked to high-performance computing (HPC), data processing and analytics, the use of federated infrastructures and artificial intelligence (AI) application handling in ESS. We will discuss how workflows can manage otherwise unmanageable data volumes and complexities based on concrete use cases of major European and international initiatives pushing the boundaries of what is technically possible and contributing to research and development of workflow methods (such as Destination Earth, DT-GEO, EDITO and others).

On these topics, we invite contributions from researchers as well as data and computational experts presenting current scientific workflow approaches developed, offered and applied to enable and perform cutting edge research in ESS.

Across the geosciences, from seismology and geophysics to hydrology, environmental sciences, and beyond, research increasingly depends on sophisticated software for data analysis, modelling, and interpretation. The rapid development and diversification of these tools create exciting opportunities, but also present challenges in maintaining code quality, ensuring ease of use and comprehensive documentation, achieving sustainability and reproducibility, and enabling seamless interoperability across datasets and disciplines. Addressing these challenges is essential for producing reliable, reusable, and trustworthy scientific results.
This PICO session invites contributions that present software tools, workflows, and platforms that have advanced geoscience research. We welcome:
● New or updated toolboxes, software packages, and workflows that enhance data access, analysis, visualization, modelling, or interpretation in geosciences.
● Case studies demonstrating real-world impact of software in research and operations.
● Methodologies for software testing, continuous integration, versioning, upgrades, deployment, and sustainability.
● Interoperability solutions that enable tools and datasets to work together across disciplines.
Sharing of your resources, reusable workflows, and best practices is strongly encouraged to raise the overall quality, transparency, and reusability of research software. Live demonstrations, videos, and interactive examples are welcome (supplementary materials can be hosted on the EGU26 platform for access after the conference).
We warmly invite geoscientists, software developers, FAIR and Open Science ambassadors and researchers to participate in this session and share their experiences, insights, and solutions. Join us to help build a stronger, more collaborative, and future-ready geoscience software ecosystem!

Nowadays, sensors, simulations and lab experiments are producing increasingly large quantities of data, many tools are available to elaborate and analyse them in often fragmented stand-alone systems that may hinder collaboration and comprehensive understanding.
e-Infrastructures and Virtual Research Environments (VREs) allow researchers located in different places world-wide to collaborate in national and international projects from their home institutions. They rely on digital services enabling collaborations among researchers providing shared access to unique or distributed scientific facilities, including data, instruments, computing and communications.
VREs are revolutionising the way research is conducted by providing a cohesive ecosystem where researchers, often from multiple disciplines, can manage the entire research lifecycle, from data collection and analysis to publication and sharing, in the spirit of Open Science principles.
This session aims to bring together case studies and innovative approaches from the different domains of the earth sciences, both from a technology point of view, and scientific applications based on workflows, virtual laboratories and even digital twins of (parts of) the environment. We seek contributions from all disciplines of the earth sciences that faced the different aspects related to e-infrastructures and VREs. These can range from the implementation of systems from an IT point of view to analysis tools, research software in applications, data being used and collected, modelling practices, but also policies and semantic approaches for VRE and digital infrastructure utilisation. Contributions can highlight scientific results, best practices and lessons learned.

In the face of unprecedented environmental challenges, Earth's dynamic systems are increasingly shaped by both natural and human-driven forces. From declining air quality and rising sea levels to intensifying natural hazards and biodiversity loss, these interconnected crises demand innovative, scalable, and actionable geospatial solutions.
This session invites contributions that harness the power of artificial intelligence (AI), Earth observation (EO), and integrated geospatial infrastructures to address local and global environmental challenges. We focus on the practical application of time-series aerial and satellite remote sensing data, combined with advanced geospatial technologies, to monitor, model, and mitigate impacts related to climate change, natural hazards, and resource management.
We welcome submissions from applied and theoretical domains that emphasize:
• AI and machine learning for land cover change, biomass estimation, and hazard mapping
• Time-series analysis of multi-modal data (optical, SAR, hyperspectral, in-situ)
• Scalable, open-source, and cloud-native geospatial workflows
• 3D geological modeling and dynamic image management
• Integrated geospatial infrastructures for collaborative science and decision-making
Submissions should highlight innovative methodologies and real-world applications using analysis-ready data across the electromagnetic spectrum. The session aims to foster interdisciplinary collaboration and showcase how geospatial technologies can support science-based strategies for resilience and sustainability.

In an era where environmental challenges are increasingly complex, the integration of artificial intelligence (AI) into data-driven approaches is transforming how we understand and address these issues. This session aims to bring together professionals from national and regional agencies and research institutions across Europe who are leveraging AI technologies to enhance environmental research and policy-making.
We invite participants to share their experiences, case studies, and innovative applications of AI in environmental monitoring, data analysis, and policy development. A key focus will be on how to build the necessary infrastructures and frameworks that facilitate the effective implementation of AI applications to support policy-making processes.
Key topics may include:

- Developing robust data infrastructures for AI integration
- AI applications in real-time environmental monitoring
- Creating collaborative frameworks for sharing AI-driven insights across agencies
- Strategies for overcoming challenges in implementing AI technologies in environmental contexts
- The role of AI in data-driven policy consulting and its impact on sustainability

By fostering interdisciplinary dialogue and collaboration, this session aims to identify best practices, explore new opportunities, and enhance the collective capacity of European agencies and research institutions to address pressing environmental challenges through the power of AI. Join us in shaping the future of environmental policy and research in Europe!

Remote sensing products have a high potential to contribute to monitoring and modelling of water resources. Nevertheless, their use by water managers is still limited due to lack of quality, resolution, trust, accessibility, or experience.
In this session, we look for new developments that support the use of remote sensing data for water management applications from local to global scales. We welcome research aimed at improving the quality of remote sensing products, such as higher spatial and/or temporal resolution mapping of land use and/or agricultural practices or improved assessments of river discharge, lake and reservoir volumes, groundwater resources, drought monitoring/modelling and its impacts on water-stressed vegetation, as well as on irrigation volumes monitoring and modelling. We are interested in quality assessment of remote sensing products through uncertainty analysis or evaluations using alternative sources of data. We also welcome contributions using a combination of different techniques (e.g., physically based models or artificial intelligence techniques) or an integration of multiple sources of data (remote sensing and in situ) across various imagery types (satellite, airborne, drone).
Finally, we wish to attract presentations on developments of user-friendly platforms (following FAIR principles), providing smooth access to remote sensing data for water applications. We are particularly interested in applications of remote sensing to determine the human-water interactions and the climate change impacts on the whole water cycle (including the inland and coastal links).

Virtual, and augmented, and mixed reality (VR/AR/MR), along with immersive visualization environments, and related interactive techniques are rapidly transforming the way we communicate, teach, explore, and conduct geoscientific research. These technologies allow learners, stakeholders, and researchers to experience complex processes and datasets in new and engaging ways, from exploring outcrops and landscapes virtually to interacting with model simulations in three dimensions. Their potential spans education and outreach, where they enhance accessibility and engagement for diverse audiences, as well as scientific research itself, where immersive environments can provide novel perspectives on data analysis, hypothesis testing, and collaborative work.

This session invites contributions showcasing innovative uses of virtual reality, augmented reality, mixed reality, and other immersive techniques across the geosciences. We particularly welcome examples from education, outreach, citizen science, and communication, as well as case studies and technical developments that demonstrate the added value of immersive approaches for scientific discovery. We also encourage critical perspectives addressing challenges such as accessibility, reproducibility, sustainability, and pedagogy. The session aims to foster exchange between developers and users, between research and education, and across disciplinary boundaries to highlight best practices and future opportunities for immersive technologies in geoscience.

Open Science is essential for addressing the exponential growth of research data, answering calls for reproducibility, and promoting interdisciplinary collaboration. Guided by the FAIR and CARE data principles, Open Science approaches enhance research transparency and contribute to solving the global environmental and social challenges outlined in the UN Sustainable Development Goals (SDGs). Scientific unions such as EGU, AGU, and JpGU play a crucial role in incentivizing the required cultural change in scientific practice. Technical challenges, such as data volumes, metadata harmonization, and interoperable infrastructures, as well as human challenges, including cultural differences, incentives, and capacity building, have to be addressed.

We invite submissions that showcase innovative platforms, interoperable infrastructures, successful stakeholder engagement activities, and collaborative networks that enable the implementation of local solutions that contribute to overcoming global challenges such as climate change, natural disasters, and biodiversity loss.

Making data Findable, Accessible, Interoperable and Reusable (FAIR) is now widely recognised as essential to advance open and reproducible research. However, it is very difficult to translate these principles into practical data management guidelines across disciplines. The goal of the session is to explore how best data management practices are developed, implemented, and adopted across disciplines. As part of this session, we invite submissions that:
1) Share good or bad experiences developing, implementing, and adopting data practices that align with both FAIR principles and the evolving needs of specific research communities.
2) Propose strategies for engaging researchers in adopting and refining best practices.
3) Explore the role of cultural change in enabling adoption of sustainable data practices.
4) Highlight efforts that harmonise data formats and workflows across disciplines while respecting domain-specific requirements.
This session is aligned with the objectives of the Research Data Alliance (RDA) Earth, Space, and Environmental Sciences (ESES) Data Community of Practice, and aims to foster cross-disciplinary dialogue, particularly among researchers in hydrology, seismology, and ocean sciences. However, we welcome contributions from all disciplines, especially where they provide insights or novel approaches to community engagement.
By learning from diverse experiences, this session seeks to advance collective understanding of how to build and sustain data practices that are both FAIR and fit for purpose.

Researchers in Earth System Science (ESS) tackle complex, interdisciplinary challenges that necessitate analysis of diverse data across multiple scales. Robust and user-friendly Research Data Infrastructures (RDIs) are crucial for supporting data management and collaborative analysis, as well as addressing societal issues. This session will explore how RDIs can bridge the gap between user needs and sustainable ESS data solutions by fostering interdisciplinary collaboration and addressing key challenges in data management and interoperability.
We welcome contributions on the following themes:
- User-Centric Infrastructure Development: This includes user stories, storylines and use cases demonstrating the importance of cross-disciplinary and cross-scale data usage, as well as innovative infrastructure concepts designed to meet specific user needs. It also covers methods for developing high-quality user interfaces and portals.
- Interdisciplinary data fusion and stakeholder engagement: We welcome contributions that address how RDI and data centers can facilitate the seamless integration of diverse ESS data in order to tackle complex societal challenges. This includes exploring interdisciplinary data fusion techniques, strategies for engaging different stakeholders, as well as approaches for integrating stakeholder knowledge into RDI development and data management practices.
- Sustainable software solutions and interoperability: This theme focuses on approaches to building and reusing sustainable software solutions that meet the diverse needs of ESS researchers. This includes addressing interoperability challenges between different data sources and platforms and identifying appropriate building blocks. The discussion will also cover operation and sustainability models for diverse ESS data centers, as well as strategies for fostering cooperation and interoperability.
- Transdisciplinary research and public engagement: We welcome contributions exploring how RDIs can support transdisciplinary research into sustainability challenges (e.g., climate change and its impacts, etc.) and facilitate public engagement with ESS issues via initiatives such as citizen science.
- Fostering cultural change and collaboration: This theme focuses on strategies encouraging data sharing, collaboration, and the adoption of the FAIR principles within research communities. It also covers approaches to international collaboration and developing collaborative practices.

Motivation

Although in some communities (e.g., meteorology, climate science) the tradition of software writing has a long history, most scientists are not trained software engineers. For early-stage scientific software projects, which are typically developed within small research groups, there is often little expectation that the code will (1) be used by a larger community, (2) be further developed or extended by others, or (3) be integrated into larger projects. This can lead to an “organic” evolution of code bases that result in challenges related to documentation, maintainability, usability, reusability, and the overall quality of the software and its results.

The wider availability of large computing resources in recent decades, along with the emergence of large datasets and increasingly complex numerical models, has made it more important than ever for scientific software to be well-designed, documented, and maintainable. However, (1) established practices in scientific programming, (2) pressures to produce high-quality results efficiently, and (3) rapidly growing user and developer communities, can make it challenging for scientific software projects to

- follow a common set of standards and a style,
- are fully documented,
- are user-friendly, and
- can be maintained, easily extended or reused.

Session content and objectives

We invite developers or users of software projects to prepare presentations about the challenges and successes in the following topics

- Good practices for developing scientific software
- Modularization
- Documentation
- Linting
- Version control
- Open source and open development
- Automatization of quality checks and unit testing
- Planning new projects
- User requirements and the user-turned-developer problem
- Painless and energy-efficient programming solutions across computing architectures
- Modularization and reliability vs performance and multiplatform capacity
- Large-dataset compression and storage workflows

These presentations will show how different projects across geoscientific fields tackle these problems. We can discuss new strategies for bettering scientific software development and raising awareness within the scientific community that robust and well-structured software development enables meaningful and reproducible results, supports researchers —especially doctoral and post-doctoral students— in their work, and accelerates advances in data- and modelling-driven science.

This session intends to build upon the remarkable 20-year journey of OneGeology since its inception, celebrating its transformational impact on global geoscience data accessibility and its pioneering role in establishing international standards for digital geological mapping. The session will examine OneGeology's evolution from its Brighton Accord inception to its current status as the world's largest geological mapping initiative, while exploring emerging paradigms in AI-driven geoscience, digital twins, and machine learning applications that will define the future of geological research.
OneGeology launched publicly in March 2007 with an ambitious vision to make geological map data globally and seamlessly accessible through web services, targeting 1:1 million scale coverage. The initiative emerged during the International Year of Planet Earth and rapidly exceeded expectations, with 118 countries participating and over 137 organizations representing more than 15,000 earth scientists worldwide. The initiative spawned other successful groups such as the LOOP3D Consortium, more focussed on 3D Modelling and has been the seed behind numerous other initiatives including European and Asian Integration of a wide range of Geoscience Open Data.

Tephra research is inherently multidisciplinary. A single tephra bed may be used to inform the date of an event (tephrochronology), volcanology (e.g. size of an eruption, eruption dynamics, atmospheric dispersal), volcanic source attribution and magma genesis (geochemistry, petrology), relationship between societies and the environment (human geography, archeology), etc. and enable researchers to assess social, environmental, and global impacts (e.g. public health, ecology, landscape evolution, climate, and beyond). Tephra data and metadata are commonly disconnected and stored in different databases inhibiting researchers from accessing available data resources. The premise to utilizing these multidisciplinary data sets relies on the proper collection, management, and documentation of all related products in accessible, ideally integrated formats.

Through cohesive efforts to standardize best practices related to collection, analysis, and reporting of tephra data, we will facilitate answering interdisciplinary questions with global benefits. The global tephra community continues to work towards creating and publishing data that is Findable, Accessible, Interoperable, and Re-usable (FAIR). This has been exemplified through the creation of cyberstructures focused from data collection (e.g. StraboSpot), to data reporting and archiving (e.g. common templates), to data preservation in terminal repositories (e.g. IEDA2’s EarthChem and SESAR, GeoDIVA, and TephraBase), to data (re)analysis (e.g. VICTOR).

In this session, we invite contributions across all fields of tephra science that integrate diverse datasets from multiple disciplines and/or field and laboratory methodologies through data visualization, numerical modeling, and statistical analyses. We especially encourage submissions that present their data work flows, best practices, and advances in cyberinfrastructure (applications, tools, data systems, repositories, etc.).

This session is sponsored by the International Association of Volcanology and Chemistry of the Earth’s Interior (IAVCEI) Commission on Tephrochronology (COT).

Rapid urbanization is intensifying heat-related challenges in global cities, with significant impacts on human health, energy demand, urban infrastructure systems, and long-term urban sustainability. This session emphasizes the critical role of geospatial data including remote sensing, numerical modeling, in-situ measurements, spatial statistics, and socio-economic datasets in advancing the characterization, monitoring, and mitigation of urban heat.
We invite contributions from geospatial science, urban climatology, environmental science, data science, artificial intelligence, and urban studies. The session seeks to highlight innovative approaches that use geospatial data and analytics to quantify urban heat dynamics, evaluate environmental and societal impacts, and support strategies for resilience and sustainability in cities.

Topics of interest include (but are not limited to):
1. AI based methods to monitor, model, and predict urban heat patterns,
2. Geospatial approaches for monitoring and mitigating the urban heat island (UHI) effect,
3. Integrated analysis of urban heat with air quality, health, energy use, and socio-economic factors,
4. Spatial modeling of cooling demand, carbon emissions, and resource efficiency under heat stress,
5. Geospatial analytics for evaluating green infrastructure and nature-based cooling solutions,
6. Climate resilience and adaptation strategies centered on heat-risk reduction,
7. Integration of multi-source datasets (satellite, airborne, in-situ, and socio-economic) for comprehensive assessments of urban heat impacts and responses.

We particularly encourage discussions on the challenges and opportunities of combining advanced geospatial analytics with AI to deliver deep insights into urban climate, resilience pathways, and sustainable planning strategies.

Sitting under a tree, you feel the spark of an idea, and suddenly everything falls into place. The following days and tests confirm: you have made a magnificent discovery — so the classical story of scientific genius goes…

But science as a human activity is error-prone, and might be more adequately described as "trial and error". Handling mistakes and setbacks is therefore a key skill of scientists. Yet, we publish only those parts of our research that did work. That is also because a study may have better chances to be accepted for scientific publication if it confirms an accepted theory or reaches a positive result (publication bias). Conversely, the cases that fail in their test of a new method or idea often end up in a drawer (which is why publication bias is also sometimes called the "file drawer effect"). This is potentially a waste of time and resources within our community, as other scientists may set about testing the same idea or model setup without being aware of previous failed attempts.

Thus, we want to turn the story around, and ask you to share 1) those ideas that seemed magnificent but turned out not to be, and 2) the errors, bugs, and mistakes in your work that made the scientific road bumpy. In the spirit of open science and in an interdisciplinary setting, we want to bring the BUGS out of the drawers and into the spotlight. What ideas were torn down or did not work, and what concepts survived in the ashes or were robust despite errors?

We explicitly solicit Blunders, Unexpected Glitches, and Surprises (BUGS) from modeling and field or lab experiments and from all disciplines of the Geosciences.

In a friendly atmosphere, we will learn from each other’s mistakes, understand the impact of errors and abandoned paths on our work, give each other ideas for shared problems, and generate new insights for our science or scientific practice.

Here are some ideas for contributions that we would love to see:
- Ideas that sounded good at first, but turned out to not work.
- Results that presented themselves as great in the first place but turned out to be caused by a bug or measurement error.
- Errors and slip-ups that resulted in insights.
- Failed experiments and negative results.
- Obstacles and dead ends you found and would like to warn others about.

For inspiration, see last year's collection of BUGS - ranging from clay bricks to atmospheric temperature extremes - at https://meetingorganizer.copernicus.org/EGU25/session/52496.

We are experiencing a revolution in earth and environmental data. Satellites, genetic sequencing, long-term in situ sensors, model results and reanalyses, digitized collections, social media, and citizen science are producing massive datasets, requiring students in earth and environmental sciences to learn scientific computing skills to use them. However, many educational institutions are not meeting this need -- most students in these degree programs report only learning these essential skills informally from peers and mentors if they learn them at all. In this session, we invite researchers and educators with innovative solutions to this gap in earth and environmental science education to share their successful programs, courses, and interventions. We are particularly interested in highlighting initiatives with a proven track record of targeting and including intersectional identities traditionally under-represented among earth, environmental and/or computer scientists.

The Earth is a complex and dynamic system shaped by interactions between the atmosphere, oceans, land, and biosphere. Addressing today’s global challenges requires crossing data from multiple disciplines through advanced computational processing. Therefore, demonstrating feasibility should rely on use cases enabled by adapted Virtual Research Environments (VREs) built on multidisciplinary standards. Such examples are essential to move beyond individual efforts and to build a more connected understanding of the Earth System. In this session, we aim to showcase services, infrastructures, and standards that strengthen semantic interoperability and provide integrated Virtual Research Environments (VREs) for Earth and environmental sciences.

With this session we aim at discovering:
• Semantic frameworks and standards that enrich data with annotations, ontologies, and machine-actionable metadata, enabling integration, discovery across disciplines, consistency, and interoperability.
• Virtual Research Environments (VREs) that provide user-friendly, scalable, and standardized platforms for analysing, visualizing, and exploring data collaboratively.
• Training, documentation, to foster adoption of FAIR practices and ensure that services meet scientific and societal needs.
• Strategies for co-design, training, and user engagement that help move from open science to collaborative science.

For each of these points, interdisciplinary use cases illustrating semantics, standards, VREs, and training in your presentation will be particularly valued.
We invite contributions from projects, infrastructures, institutes, associations, and individual researchers showcasing concrete solutions or innovative tools improving semantic interoperability, VRE-powered access, and a FAIR and open ecosystem for Earth and environmental sciences.

We wish to hear during this session about concrete solutions, success stories, and lessons learned, from metadata to working platforms, to inspire the next generation of earth and environmental data science.

Science is becoming increasingly data-driven, interconnected, and transdisciplinary. To ensure that data can be effectively discovered, reused, and linked – not only by humans but also by machines – we need concepts that provide reliability, consistency, and scalability across domains. FAIR Digital Objects (FDOs) address this need by providing a framework to uniquely identify, semantically describe, and connect data, software, models, and other digital resources at scale, making them actionable in complex research environments.
Applications range from improved findability and citability of scientific outputs to the integration of data spaces and fully automated, machine-actionable workflows that open new possibilities for analysis and modelling. In this way, FDOs are emerging as a key enabler of interoperable, open and reproducible science, and sustainable research infrastructures.
This session invites contributions that address both conceptual perspectives and practical implementations of FDOs in the geosciences and beyond, including:

- Conceptual foundations, roadmaps, and recent developments

- Integration into domain-specific research infrastructures and transdisciplinary data spaces and workflows (e.g., demonstrators, pilots)

- Strategies for achieving technical and semantic interoperability

- Machine-actionable workflows and automation enabled by FDOs

- Community adoption and implementation challenges

The session is aimed at researchers, data experts, and infrastructure developers who are interested in shaping the next steps toward a more connected, FAIR, and machine-assisted scientific ecosystem.

The proliferation of Essential Climate Variables (ECVs), Essential Ocean Variables (EOVs), and Essential Biodiversity Variables (EBVs) highlights a paradigm shift towards data-driven environmental monitoring and policy. These Essential Variables (EVs) are central to global frameworks including GCOS, WMO, GEO, Copernicus, IPCC assessments, and the UN Sustainable Development Goals (SDGs). For science, they are a powerful mechanism to track Earth system changes and enable evidence-based decision-making.
Yet, despite broad recognition, the scientific potential of EVs remains underrealised. Persistent gaps in how they are defined, described, managed, and exchanged across domains and infrastructures hamper progress. A lack of semantic and technical interoperability, inconsistent metadata practices, and fragmented governance limit their integration and reduce their impact on policy and action. Without a coherent, interoperable infrastructure, the transformative potential of EVs—to enable cross-domain science, support climate agreements, and monitor sustainability targets—remains out of reach.
This session will explore the technical, infrastructural, and policy advancements required to make EVs the foundational language for global environmental cooperation. We welcome contributions addressing scientific use cases, technical barriers, and emerging solutions under the following themes:
1. Semantic Interoperability: Shared frameworks and vocabularies (e.g., iADOPT, W3C SSN/SOSA) ensuring EVs form a consistent, machine-actionable common language across disciplines and infrastructures.
2. Cross-Domain Data Synergy: Approaches and case studies demonstrating seamless data flow and integration across atmospheric, oceanic, terrestrial, biodiversity, and socio-economic domains, breaking down silos.
3. Infrastructure Integration: Lessons from research infrastructures (e.g., ENVRI, AuScope, US CRDCs, China’s Earth Lab, GERI) in implementing EVs and achieving interoperability with global programmes like GCOS, WMO, GEO, Copernicus, RDA, and CODATA.
4. From Data to Policy: Examples of how FAIR (Findable, Accessible, Interoperable, Reusable) EVs contribute to policy needs, climate reporting, and monitoring of SDG indicators.
We invite scientists, data architects, and policymakers to share insights for building a coherent, actionable, and interoperable global observation system.

Pangeo (pangeo.io) is a global open community of researchers and developers working to solve the challenges of big geoscience data through scalable, interoperable and reproducible workflows, from laptops to HPC and cloud infrastructures.
Discrete Global Grid Systems (DGGS) are a new paradigm for organizing geospatial data—especially for Earth Observation and Earth System modelling—providing equal-area, multi-resolution indexing that supports cross-domain interoperability. Together, Pangeo’s open-source ecosystem and DGGS-based approaches enable a new level of transdisciplinary science under the principles of FAIR (Findable, Accessible, Interoperable, Reusable) data management and open reproducible research.

This session welcomes contributions that either (a) use DGGS approaches in geoscience, (b) showcase applications built with Pangeo’s core packages, or (c) explore both.

We invite abstracts from researchers, technologists and data managers who are:
Building DGGS-based workflows using Pangeo core packages (Xarray, Iris, Dask, Jupyter, Zarr, Kerchunk, Intake) to achieve scalable and reproducible analysis of geoscientific data.
Developing cloud-native geoscience applications and interoperable infrastructures (HPC–cloud convergence, IaaS, PaaS, SaaS, federated cloud platforms) for large multi-provenance datasets.
Applying machine learning and AI to DGGS-organized or cloud-native geoscience data using open-source tools.
Or simply using Pangeo’s tools to build reproducible, FAIR, and community-driven workflows in any domain of Earth, ocean, climate or environmental science.
Demonstrating executable notebooks, reproducible workflows, and sustainable computing practices.

By highlighting both the informatics (DGGS indexing, cloud-native formats, scalable computing) and the community aspects (Pangeo open-source packages and standards), this session aims to catalyse new collaborations across traditional disciplinary boundaries.

The advancement of Open Science and the democratization of computing services allow for the discovery and processing of large amounts of information, blurring traditional discipline boundaries. Being data heterogeneous in format and provenance, the ability to combine them and extract new knowledge to address complex challenges relies on standardisation, integration and interoperability.
Thanks to decades of work in this field, Research infrastructures (RI) worldwide, such as EPOS, Europe's RI for solid Earth science, are key enablers of this paradigm. By providing access to quality-vetted, curated open data, they enable scientists to combine data from different disciplines and data sources into innovative research and apply novel approaches such as Large Language Models (LLM) and AI/ML tools to obtain new insights and solve complex scientific and societal questions.
However, while data-driven science creates enormous opportunities to generate groundbreaking inter- and transdisciplinary results, many challenges and barriers remain.
This session aims to foster cross-fertilization by showcasing real-life scientific studies and research experiences in geosphere studies, especially from Early Career Scientists (ECS) worldwide. We also welcome contributions on challenges and user needs when establishing multi-disciplinary studies, including, e.g., need for reliable and trustworthy AI and the availability of training datasets. The session will not only focus on results, but also on challenges and solutions in connection to data availability, collection, processing, and inter-disciplinary methods.
A non-exhaustive list of topics includes:
- multi-disciplinary studies, involving data from different disciplines (e.g. combining seismology, geodesy, and petrology to understand subduction zone dynamics);
- inter-disciplinary research integrating two or more disciplines into new approaches (e.g. merging geophysics and geochemistry to probe mantle plumes);
- activities that advance interdisciplinarity and open science (e.g. enhancing FAIRness of data and services, enriching data provision, enabling cross-domain AI applications, software and workflows, transnational access and capacity building for ECS);
- experiences that cross disciplinary boundaries, integrate paradigms and engage diverse stakeholders (e.g. bringing together geologists, social scientists, civil engineers and urban planners to define risk maps and prevention measures in urban planning).

Good scientific practice includes the visualisation and user-friendly exploration of scientific data. However, increasing data complexity and volumes are a result of higher temporal and spatial resolutions of modelling and remote sensing approaches. Earth system science data is becoming increasingly important for decision support for stakeholders and other users. This poses major challenges for the entire process chain, from data storage to web-based visualisation. For example: (1) data must be enriched with metadata and made available via appropriate and efficient services; (2) visualisation and exploration tools must access decentralised tools via interfaces that are as standardised as possible; (3) the presentation of essential information must be coordinated with potential end users. This challenge is reflected by the development of tools, interfaces and libraries for modern earth system science data visualisation and exploration.
In this session, we aim to establish a transdisciplinary community of scientists, software-developers and other experts in the field of data visualization in order to give a state-of-the-art overview of tools, interfaces and best-practices. In particular, we look for contributions in the following fields:
- Developments of open source visualization and exploration techniques for earth system science data
- Co-designed visualization solutions enabling transdisciplinary research and decision support for non-scientific stakeholders and end-users
- Tools and best-practices for visualizing complex, high-dimensional and high frequency data
- Services and interfaces for the distribution and presentation of metadata enriched earth system science data
- Data visualization and exploration solutions for decentralized research data infrastructures
All contributions should emphasize the usage of community-driven interfaces and open source solutions and finally contribute to the FAIRification of products from earth system sciences.

Geological mapping and modelling are fundamental pillars of the geosciences, providing the basis for understanding Earth and planetary systems. This session brings together contributions that span the full spectrum of geological mapping and modelling, from traditional field-based methods to cutting-edge approaches, including AI, applied in the most extreme and inaccessible environments on Earth and beyond.
We invite scientists working on:
• Geological field mapping and cross-boundary harmonization
• Mapping of extreme environments such as marine areas, polar regions, deserts, volcanic terrains, high-mountain ranges, and planetary surfaces
• 3D geological modelling in any geological context
• Development of geomodelling methodologies and tools
• Application of AI methods to geological mapping and modelling
• Development of geological information systems
• Remote sensing, geophysical techniques, drilling, sampling, and specialized tools for inaccessible terrains for geological mapping and modelling
The session aims to be highly transdisciplinary, bridging geology, geophysics, geochemistry, mineralogy, hydrogeology, engineering geology, and planetary sciences. By integrating approaches across diverse contexts, from accessible outcrops to remote and hostile terrains, participants will explore common challenges in data acquisition, interpretation, 3D modelling, visualization, and knowledge synthesis.
Outcomes are expected to benefit a wide range of applications and research, including geothermal energy exploration, offshore wind energy, geological risk assessment, groundwater protection, coastal protection, habitat mapping, environmental impact assessment, marine protected area development, mineral and resource exploration, and planetary missions. Ultimately, this session seeks to foster dialogue between communities tackling mapping and modelling challenges in both familiar and extreme environments, to advance scientific understanding and practical applications across the geosciences.

Unmanned Aerial Vehicles (UAVs) have become indispensable platforms for high-resolution monitoring of landslide processes, offering rapid deployment, flexible acquisition strategies, and integration of diverse sensors such as RGB, LiDAR, multispectral, thermal, and hyperspectral systems. Recent advances in data fusion and AI-driven analytics enable UAV-derived products to move beyond traditional photogrammetry toward comprehensive digital twins of landslide-prone environments. This session invites contributions exploring UAV applications for landslide detection, mapping, kinematic monitoring, hazard assessment, and post-event analysis. Topics include novel workflows for integrating multi-sensor datasets, automated feature extraction using computer vision and deep learning, and 3D point cloud fusion for terrain change detection that leverages UAV products. We welcome case studies from a range of geomorphological contexts as well as methodological innovations that address challenges such as vegetation cover, temporal repeatability, and scaling from local to regional assessments. The session aims to bring together researchers and practitioners to showcase cutting-edge UAV solutions that can enhance landslide science.

frequent and impactful weather-related disasters. Conversely, declines in water availability make monitoring surface water dynamics, including seasonal water body variations, wetland extent, and river morphology changes crucial for environmental management, climate change assessment, and sustainable development. Remote sensing is a critical tool for data collection and observation, especially in regions where field surveys and gauging stations are limited, such as remote or conflict ridden areas and data-poor developing nations. The integration of remotely-sensed variables—like digital elevation models, river width, water extent, water level, flow velocities, and land cover—into hydraulic models offers the potential to significantly enhance our understanding of hydrological processes and improve predictive capabilities.
Research has so far focused on optimising the use of satellite observations, supported by both government and commercial initiatives, and numerous datasets from airborne sensors, including aircraft and drones. Recent advancements in Earth observation (EO) and machine learning have further enhanced the monitoring of floods and inland water dynamics, utilising multi-sensor EO data to detect surface water, even in densely vegetated regions. However, despite these advancements, the update frequency and timeliness of most remote sensing data products are still limited for capturing dynamic hydrological processes, which hinders their use in forecasting and data assimilation. This session invites cutting-edge presentations on advancing surface water and flood monitoring and mapping through remotely-sensed data, focusing on:
- Remote sensing for surface water and flood dynamics, flood hazard and risk mapping including commercial satellite missions and airborne sensors
- The use of remotely-sensed data for calibrating or validating hydrological or hydraulic models
- Data assimilation of remotely-sensed data into hydrological and hydraulic models
- Enhancements in river discretization and monitoring through Earth observations
- Surface water and river flow estimation using remote sensing
- Machine learning and deep learning-based water body mapping and flood predictions
- Ideas for developing multi-satellite data products and services to improve the monitoring of surface water dynamics including floods
Early career and underrepresented scientists are particularly encouraged to participate.

Fibre optic based techniques allow probing highly precise point and distributed sensing of the full ground motion wave-field including translation, rotation and strain, as well as environmental parameters such as temperature at a scale and to an extent previously unattainable with conventional geophysical sensors. Considerable improvements in optical and atom interferometry enable new concepts for inertial rotation, translational displacement and acceleration sensing. Laser reflectometry on commercial fibre optic cables allows for the first time spatially dense and temporally continuous sensing of the ocean’s floor, successfully detecting a variety of signals including microseism, local and teleseismic earthquakes, volcanic events, ocean dynamics, etc. Significant breakthrough in the use of fibre optic sensing techniques came from the new ability to interrogate telecommunication cables to high temporal and spatial precision across a wide range of environments. Applications based on this new type of data are numerous, including: seismic source and wave-field characterisation with single point observations in harsh environments such as active volcanoes and the seafloor, seismic ambient noise interferometry, earthquake and tsunami early warning, and infrastructure stability monitoring.

We welcome contributions on developments in instrumental and theoretical advances, applications and processing with fibre optic point and/or distributed multi-sensing techniques, light polarization and transmission analyses, using standard telecommunication and/or engineered fibre cables. We seek studies on theoretical, instrumental, observation and advanced processing across all solid earth fields, including seismology, volcanology, glaciology, geodesy, geophysics, natural hazards, oceanography, urban environment, geothermal applications, laboratory studies, large-scale field tests, planetary exploration, gravitational wave detection, fundamental physics. We encourage contributions on data analysis techniques, novel applications, machine learning, data management, instrumental performance and comparison as well as new experimental, field, laboratory, modelling studies in fibre optic sensing studies.

In recent years, the field of geostatistics has seen significant advancements. These methods are fundamental in understanding spatially and temporally variable hydrological and environmental processes, which are vital for risk assessment, input for other models, and management of extreme events like floods and droughts.
This session aims to provide a comprehensive platform for researchers to present and discuss innovative applications and methodologies of geostatistics and spatio-temporal analysis in hydrology and related fields. The focus will be on traditional approaches and the assessment of uncertainties, whereas Machine Learning approaches have their specific and other dedicated sessions.

We invite contributions that address the following topics (but not limited to):

1. Spatio-temporal Analysis of Hydrological and Environmental Anomalies:
- Methods for detecting and analyzing large-scale anomalies in hydrological and environmental data.
- Techniques to manage and predict extreme events based on spatio-temporal patterns.

2. Innovative Geostatistical Applications:
- Advances in spatial and spatio-temporal modeling.
- Applications in spatial reasoning and data mining.
- Reduced computational complexity methods suitable for large-scale problems.

3. Geostatistical Methods for Hydrological Extremes:
- Techniques for analyzing the dynamics of natural events, such as floods, droughts, and morphological changes.
- Utilization of copulas and other statistical tools to identify spatio-temporal relationships.

4. Optimization and Generalization of Spatial Models:
- Approaches to optimize monitoring networks and spatial models.
- Techniques for predicting regions with limited or unobserved data e.g., using physical-based model simulations or using secondary variables.

5. Uncertainty Assessment in Geostatistics:
- Methods for characterizing and managing uncertainties in spatial data.
- Applications of Bayesian Geostatistical Analysis and Generalized Extreme Value Distributions.

6. Spatial and Spatio-temporal Covariance Analysis:
- Exploring links between hydrological variables and extremes through covariance analysis.
- Applications of Gaussian and non-Gaussian models in spatial analysis and prediction.

The urgency, complexity, and economic implications of greenhouse gas (GHG) emission reductions demand strategic investments in science-based information for planning, implementing, and tracking emission reduction policies and actions. An increasing number of applications succeed by combining activity-based emissions data with atmospheric GHG measurements and analyses – this hybrid approach can yield additional insights and practical information to support mitigation efforts at different scales. Inspired by this potential, the Integrated Global Greenhouse Gas Information System (IG3IS) of the World Meteorological Organization works to identify and document good practice guidelines for informing decisions, while promoting scientific advances and facilitating two-way linkages between practitioners and stakeholders in the policy realm, tailoring research actions to meet policy needs.
Since EGU18, this session continues to showcase how scientific data and analyses can be transformed into actionable information services and successful climate solutions for a wide range of user-communities. Actionable information results from data with the required spatial and temporal granularity and compositional details able to explicitly target, attribute and track GHG emissions and reductions where climate action is achievable.
This session seeks contributions from researchers, inventory compilers, government decision and policy makers, non-government and private sector service providers that show the use and impact of science-based methods for detecting, quantifying, tracking GHG emissions and the resulting climate mitigation. We especially welcome presentations of work guided by IG3IS good practice research guidelines at urban and national scale and for specific economic sectors. The scope of the session spans measurements of all GHGs and from all tiers of observation.

Continuous monitoring of natural physical processes is essential to understand their behaviour. The wide variety of available instruments allows diverse applications to increase data availability for a better understanding of natural physical processes. Long-term data collection allows for a deeper understanding of trends and patterns such as seasonal variation, multi-year cycles and changes due to anthropogenic influence (e.g. deforestation, urbanization and pollution). On the other hand, short-term monitoring is essential for real-time decision-making and rapid response, contributing to hazard assessment improvement, more effective risk management and more accurate warning systems. Appropriate data analysis and innovative instrumentation systems can contribute to developing effective mitigation and adaptation strategies. This session focuses on advances in geophysical instrumentation including long-term and short-term monitoring of natural phenomena.

The session aims to disseminate advanced instrumentation research, the use of new technologies to overcome future challenges, including those associated with extreme climatic conditions, and novel approaches from various disciplines to provide efficient monitoring to build historical baselines. The session is an inter- and transdisciplinary (ITS) session. The topics include but are not limited to:

(1) Advanced geophysical techniques and sampling methodologies.
(2) Technical developments and design of monitoring systems to understand natural physical processes.
(3) Continuous real-time monitoring systems to provide smart tools such as an integration of geoscience data with Building Information Models (BIM), digital twins, robotic monitoring, automation systems and computational modelling for better decision-making.
(4) Intelligent data analysis approaches driven by technologies including computer vision and image, signal processing, machine learning.
(5) Advances in the use of network technologies (e.g. long range, LTE-M, NB-IoT) for geoscience.
(6) Advances in data systems for real-time monitoring.

We encourage student submissions of early or ongoing research in order to provide a forum for the exchange of ideas and experiences.

The Earth and Space Sciences Informatics (ESSI) programme focuses on evolving issues related to data management and analysis, technologies and methodologies, large-scale computational experimentation and modelling, and the necessary hardware and software infrastructure. Together, these elements enable us to transform data into knowledge that can advance our understanding of Earth and space sciences. This session invites presentations on all aspects of Earth and Space Science Informatics, particularly topics not covered by other ESSI sessions.

Are you unsure about how to bring order in the extensive program of the General Assembly? Are you wondering how to tackle this week of science? Are you curious about what EGU and the General Assembly have to offer? Then this is the short course for you!

During this course, we will provide you with tips and tricks on how to handle this large conference and how to make the most out of your week at this year's General Assembly. We'll explain the EGU structure, the difference between EGU and the General Assembly, we will dive into the program groups and we will introduce some key persons that help the Union function.

This is a useful short course for first-time attendees, those who have previously only joined us online, and those who haven’t been to Vienna for a while!

Anyone entering the job market or looking for a new job after academia will confront the phrase ‘transferable skills’. PhD candidates and scientists are advised to highlight their transferable skills when applying for non-academic jobs, but it can be hard to know what these skills are. Similarly, for those looking to change scientific research areas or take a leap into a new field for their PhD, it is important to highlight your transferable skills. Big data analysis, communicating your findings, supervising, teaching, project management and budgeting are skills you might have from your research/science career. But there are many more. In this interactive workshop, we will start your journey of identifying your transferable skills and highlighting careers where these will be necessary!

Join our tutorial on discovering, sharing, and learning with Earth System Sciences data: 1) How to find high-quality datasets for your data-driven projects, including scientific and governmental sources, 2) Tips for selecting the right (disciplinary) repository for sharing your data - according to your needs and particularly addressing the FAIRness and Openness principles, and 3) How to find and use open online courses and educational materials (OER) to leverage discovered data.
We will demonstrate tips, tricks, and how-tos using the NFDI4Earth services OneStop4All (https://onestop4all.nfdi4earth.de/) and the Knowledge Hub (https://knowledgehub.nfdi4earth.de/).
You are invited to share your experiences, best practices, or favorite repositories with the community, and take away practical skills and knowledge to enhance your research.

The Meteorological Archival and Retrieval System (MARS) is the world’s largest meteorological archive and ECMWF's main data repository. It stores operational weather analyses and forecasts, reanalyses, observations and research experiments that support a wide range of Earth system science applications.
This short course provides a practical introduction of MARS archive to the new users of the archive. Participants will learn how to explore the MARS data catalogue to identify datasets relevant to their research. The session will demonstrate how to construct and run MARS requests to download data efficiently.
Through step by step examples, attendees will gain a clear understanding of the archive’s structure and the main concepts behind exploring the data and retrieving the data they need for their research.

This short course will train you how to use robust Machine Learning methods to do statistical downscaling of coarse climate model scenarios. A sample dataset will be used: daily surface temperature from one Global Climate Model of the CMIP6 database (historical and future climate time periods), along with a high resolution reanalysis.
Introduction on climate statistical downscaling
Methodology: classical and Machine-Learning based
Steps to perform downscaling
Sample datasets
Results
All material will be made available online, and a sample Jupyter Notebook will be provided.

The majority of multivariate statistics and machine learning algorithms expect Euclidean metrics on unconstrained data spaces. On the other hand, most variables in geosciences are strictly positive and capped by physical constraints, which leads to pointless arithmetic measures. Disobeying these constraints may obscure meaningful patterns, produce spurious correlations, or senseless measures of model quality. Within this short course, useful recipes to overcome common pitfalls in multivariate statistics and machine learning for (a) common physically constrained and (b) compositional data spaces will be presented with hands-on examples.

The course is structured into four topics:
a) Why are common metrics meaningless in constrained data spaces?
b) Challenges of modeling physical extremes
c) Basic recipes for physically constrained data spaces 
d) Meaningful transformation for compositional data

This course is held interactively with interdisciplinary hands-on experience. Advanced statistical/mathematical knowledge is not mandatory, but bringing your own laptop with R, Python, or Matlab environment will help to follow the presented recipes and exercises!

AI is a gamechanger in the quest for better understanding Earth data. ML allows training of models for virtually any purpose, and many of them are published on open platforms like HuggingFace and Kaggle. However, in practice it is not easy particularly for non-experts to use such models, due to several blockers: Models typically need highly specific data preprocessing requiring skillful python coding. Model metadata are sparse and not standardized. In particular, they are not machine-readable so human intervention is required. A model's comfort zone is not always delineated clearly, and outside of it model accuracy and reliability can drop drastically, such as below 20%.

Recent work in research and standardization is aiming at overcoming these obstacles in the quest for easy-to-use, zero-coding, reliable ML use on spatio-temporal Earth Data. Based on ongoing research in the EU-funded FAIRgeo project we discuss AI-Cubes as a novel paradigm which embeds ML inference seamlessly into the geo datacube query standard, WCPS. Further, the concept of Model Fencing aims at deriving hints about a model's comfort zone so that the server can automatically decide about model applicability on the region selected and warn the user.

Live demos, several of which can be recapitulated by the audience, serve to illustrate the challenges and solution approaches. Ample time will be reserved for active discussion with the audience.

Deep learning algorithms have seen rapid and widespread adoption in ocean science. For many tasks, such as classification and error correction, they now represent the state of the art. However, applying deep learning in the field of oceanography also presents unique challenges, including the various temporal scales of oceanic processes, heterogeneously distributed and noisy observational data, and unresolved processes in numerical models.

In this short course, we aim to present a set of best practices for applying and assessing deep learning methods in oceanographic research. We will also highlight common pitfalls and how to avoid them.

The course will be structured around a series of short presentations and practical examples covering key topics, including:

- Types of oceanographic problems suited for deep learning: reconstruction, prediction, …
- Building datasets appropriate for deep learning applications: constitution of - training/validation/test datasets, effect of non-stationnarity, type/quality/number of data, …
- Training strategies and model selection: normalization, supervised training, generative models, …
- Validation and evaluation of ocean products derived from deep learning: accuracy, realism, …
- Ethical considerations: reproducibility, open science, and the environmental impact of deep learning

The advances in geodetic theory made an increased emphasis on mathematical methods necessary (Heiskanen and Moritz, 1956). For several decades a rigorous mathematical framework has been developed - Gauss/Markov BLUE, MLE, DIA - in the context of parameter estimation and statistical testing, thus paving the way for a better understanding of Earth's shape, orientation in space, and gravity field. With the introduction of machine learning, the focus has been shifted from a model-driven to a data-driven approach, also thanks to the large amount of data made available through several different terrestrial and space techniques (e.g. GNSS, InSAR, VLBI, SLR, Altimetry, Gravimetry, etc.).

In this short course we first provide a broad overview of geodetic theory, addressing different mathematical problems and well-established solutions adopted in Geodesy. Therefore, we highlight gaps in the current theoretical framework and introduce machine/deep learning paradigms as potential alternative to classical solutions. In this way, we further discuss key relationships between statistical learning and ML/DL methods, in particular focusing on fundamental issues in the adoption of AI techniques as "black box" solutions. Hence, we provide a clear understanding of the major pitfalls, especially concerning the quantification of uncertainty and confidence levels for ML/DL solutions.

Ultimately, we highlight the key role in science of 'explainability' and 'reproducibility', both often overlooked when adopting AI techniques in Geodesy. Target audience is Geodesy and Earth-science practitioners who deploy or evaluate ML in their research works. The suggested format is 60 minutes (e.g. lunch slot) with 30′ for a mini lecture on theoretical fundamentals, 20′ live demo with relevant geodetic examples, and 10′ for Q&A.

Prerequisites: basic linear algebra; no prior ML/DL knowledge is required.

Data assimilation (DA) is widely used in the study of the atmosphere, the ocean, the land surface, hydrological processes, etc. The powerful technique combines prior information from numerical model simulations with observations to provide a better estimate of the state of the system than either the data or the model alone. This short course will introduce participants to the basics of data assimilation, including the theory and its applications to various disciplines of geoscience. An interactive hands-on example of building a data assimilation system based on a simple numerical model will be given. This will prepare participants to build a data assimilation system for their own numerical models at a later stage after the course.
In summary, the short course introduces the following topics:

(1) DA theory, including basic concepts and selected methodologies.
(2) Examples of DA applications in various geoscience fields.
(3) Hands-on exercise in applying data assimilation to an example numerical model using open-source software.

This short course is aimed at people who are interested in data assimilation but do not necessarily have experience in data assimilation, in particular early career scientists (BSc, MSc, PhD students and postdocs) and people who are new to data assimilation.

Visualisation of scientific data is an integral part of scientific understanding and communication. Scientists have to make decisions about the most effective way to communicate their results every day. How do we best visualise the data to understand it ourselves? How do we best visualise our results to communicate with others? Common pitfalls can be overcrowding, overcomplicated or suboptimal plot types, or inaccessible colour schemes. Scientists may also get overwhelmed by the graphics requirements of different publishers, for presentations, posters, etc. This short course is designed to help scientists improve their data visualisation skills so that the research outputs would be more accessible within their own scientific community and reach a wider audience.
Topics discussed include:
- golden rules of DataViz;
- choosing the most appropriate plot type and designing a good DataViz;
- graphical elements, fonts and layout;
- colour schemes, accessibility and inclusiveness;
- creativity vs simplicity – finding the right balance;
- figures for scientific journals (graphical requirements, rights and permissions);
- tools for effective data visualisation.
This course is co-organized by the Young Hydrologic Society (YHS), enabling networking and skill enhancement of early career researchers worldwide. Our goal is to help you make your figures more accessible to a wider audience, informative and beautiful. If you feel your graphs could be improved, we welcome you to join this short course.

You would like to discover a simple, powerful and user-friendly software to visualize and process 2-D datasets in a few clicks? PyAnalySeries allows for efficient visualization and processing of 2-D datasets, in particular time-series, without any programming skills. Its simplicity and user-friendly visualization interface make it an extremely valuable software both for research applications and teaching activities.
PyAnalySeries is the new multi-platform version of the former and now obsolete time-series processing program called “AnalySeries” (Paillard et al., 1996). Written in Python, PyAnalySeries is easily portable across platforms (e.g. Linux, MacOS and Windows). Importing 2-D datasets is simple by copy-pasting from an open worksheet. A user-friendly graphical interface and efficient shortcuts rapidly create various types of 2-D data graphs (e.g. plots on the same or different X or Y axes), which can be interactively modified and exported as final figures. PyAnalySeries also gives access to a full set of astronomical series (e.g. precession, obliquity, eccentricity) and insolation series (for a given date or an integrated interval) from several references. The software provides the original possibilities of resampling and smoothing 2-D data, as well as that of interpolation-based correlation with different records of two archives simultaneously, which is classically used to derive age models in paleoclimate studies. PyAnalySeries is available with Open Access on our GitHub repository (https://github.com/PaleoIPSL/PyAnalySeries) and Zenodo (https://zenodo.org/records/15238083). Users are strongly encouraged to post questions and share suggestions of improvement on the GitHub space of discussion.
Beyond its original use in processing paleoclimatic data, PyAnalySeries is useful for any kind of 2-D datasets, such as elemental concentrations on river waters over time, the processing of electromagnetic radiation, any meteorological and climatic time series, biostatistics, sensors, economics. It is also a didactic platform useful in hands-on teaching activities. This makes it a valuable tool for training the next generation of Earth scientists.
During the short course, we will explain to users how to download and install the software, and show the main functionalities of PyAnalySeries using typical 2-D datasets. We also invite participants to bring their own 2-D data and try this simple time-series processing program by themselves.

EUMETView is EUMETSAT’s (European Organisation for the Exploitation of Meteorological Satellites) online data visualization service, offering easy and open access to a wide range of meteorological satellite products in near-real time. It provides an entry point for users who wish to explore environmental data without the need for complex processing or infrastructure, making it a valuable tool for both beginners and more experienced users. In addition to data from EUMETSAT’s own missions, EUMETView also provides access to products from Copernicus Sentinel satellites operated by EUMETSAT, such as Sentinel-3 ocean and atmosphere data.

This short course will provide a beginner-level introduction to EUMETView and its related data access services. Participants will learn how to browse, select and visualise satellite data directly in the EUMETView interface, specifically products related to wildfire events (e.g. MTG Fire Temperature RGB, Copernicus Sentinel 3 Fire Radiative Power). In addition, the course will demonstrate how to programmatically access the EUMETView catalogue through its API using a simple Python notebook, enabling automated queries and download of products.

After retrieving products, participants will learn how to visualize and animate them, create simple time series of images to track the temporal evolution of events, and integrate EUMETView layers through the OGC Web Map Service (WMS) into external tools such as GIS software or Python environments.

The session will start with a short overview of EUMETView and its data streams, followed by live demonstrations and guided exercises. By the end of the course, participants will be familiar with the main functionalities of EUMETView, understand how to access data interactively and via API, and be equipped with practical examples on how to visualize and apply satellite products for wildfire monitoring independently. No prior coding knowledge is required, and all training material will be provided.

Better software leads to better research, and code is read far more often than it is written.
Writing code that is clear, maintainable, and easy to adapt not only improves long-term (re-)usability, but also reduces cognitive load and bugs, leaving more time for scientific research.

Many researchers want to write better software, but don't know where to get started learning the tools or skills to do so. This short course introduces essential software engineering practices, covering aspects like:

Code structure
- Naming
- Smaller units/functions

Environments and dependency management

Code styling and standards
- Coding standards and best practices (through Python PEPs)
- Formatting and static analysis tools
- IDE Tooling and integration

Unit testing

Documentation
- Comments
- Docstrings
- READMEs

Through real-life examples and demonstrations, we will explore how to transform code from convoluted to comprehensible.

The session will combine lecture, demonstration and discussion, giving participants the opportunity to share their own challenges and exchange insights with fellow researchers.

The session will be led by computer scientists and research software engineers experienced in software development, who work principally with and for research projects. We welcome engaged participants of all backgrounds and abilities who want to improve their software skills in research and discuss with others how to apply them in their work.

Your high impact journal demands reproducible research, but your reviewers don't have access to your supercomputer...

You want colleagues in another country to work with the petabytes of data you created, but they cannot access your server easily...

You want your students to run the analysis you did for one region on any other region in the world, but don't want to manage the dependencies on their laptops...

In this short course we will give you hands on experience on how to create, publish and share workflows that are 'reproducible by design'. Using openly published Jupyterbooks, online JupyterHubs, git-pullers, open interfaces and data formats you will build a reproducible workflow in a single short course! Based on a decade of work with the eWaterCycle project for Open and FAIR hydrological modelling, we will teach the best practices in making modelling studies, even when requiring High Performance Computing resources, truly reproducible.

Bring a laptop, but no need to install anything: everything will be online!

The EU-funded project AquaINFRA (https://aquainfra.eu/) aims to help marine and freshwater researchers restore healthy oceans, seas, coastal and inland waters. To achieve this goal, a large part of the work is dedicated to designing and implementing a research data infrastructure composed of the AquaINFRA Interaction Platform (AIP) and the Virtual Research Environment (VRE). This effort is part of the ongoing development of the European Open Science Cloud (EOSC) as an overarching research infrastructure, the EU flagship initiative to enable Open Science practices in Europe.

The AIP is the central gateway for scientific communities to find, access, and reuse aquatic digital resources such as FAIR multi-disciplinary data and analysis workflows. The basis for this is the Data Discovery and Access service which performs a live query to a number of data providers from the aquatic realm, for instance, Copernicus Marine and HELCOM. The data found can be used in the VRE, which is composed of a web API service hosting a number of OGC API Processes, a virtual lab based on the tool MyBinder, and the Galaxy platform as a workflow management system.

In this short course, we will start with providing an overview of the research data infrastructure. Then, we will show how the AIP and VRE can help to find data and use it in the Galaxy platform to create reproducible and readily-shareable analysis workflows. We will use a hydrological demonstrator in the form of a Data-to-Knowledge Package (D2K-Package) for this purpose [1]. The D2K-Package is a collection of links to digital research assets, including data, containerized code enriched by the computational environment, virtual labs, OGC API Processes, and computational workflows.

Although we will use a hydrological demonstrator, the course is not limited to hydrologists but open to everyone interested in making computational research more reusable. To follow this course, the attendees will need to register on Galaxy (https://usegalaxy.eu/login/start). We kindly ask the attendees to do so in advance to avoid delay. No prior knowledge in Hydrology or Galaxy is required to follow this course. Some understanding of scripting languages (e.g., R) can be helpful but the basic concepts do not depend on a particular technology.

Konkol, M. et al. (2025). Encouraging reusability of computational research through Data-to-Knowledge Packages - A hydrological use case https://doi.org/10.12688/openreseurope.20221.2.

Software plays a pivotal role in various scientific disciplines. Research software may include source code files, algorithms, computational workflows, and executables. It refers mainly to code meant to produce data, less so, for example, plotting scripts one might create to analyze this data. An example of research software in our field are computational models of the environment. Models can aid pivotal decision-making by quantifying the outcomes of different scenarios, e.g., varying emission scenarios. How can we ensure the robustness and longevity of such research software? This short course teaches the concept of sustainable research software. Sustainable research software is easy to update and extend. It will be easier to maintain and extend that software with new ideas and stay in sync with the most recent scientific findings. This maintainability should also be possible for researchers who did not originally develop the code, which will ultimately lead to more reproducible science.

This short course will delve into sustainable research software development principles and practices. The topics include:
- Properties and metrics of sustainable research software
- Writing clear, modular, reusable code that adheres to coding standards and best practices of sustainable research software (e.g., documentation, unit testing, FAIR for research software).
- Using simple code quality metrics to develop high-quality code
- Documenting your code using platforms like Sphinx for Python
- Using GIT and Github for version control

We will apply these principles to a case study of a reprogrammed version of the global WaterGAP Hydrological Model (https://github.com/HydrologyFrankfurt/ReWaterGAP). We will showcase its current state in a GitHub environment along with example source code. The model is written in Python but is also accessible to non-python users. The principles demonstrated apply to all coding languages and platforms.

This course is intended for early-career researchers who create and use research models and software. Basic programming or software development experience is required. The course has limited seats available on a first-come-first-served basis.

Scientists often need to write code but usually lack formal training in software engineering.
One key element of professional software engineering is proper version control of code, allowing one to: develop and manage code effectively, backup the code and go back to previous stages, detect introduced bugs faster, and collaborate on a shared codebase.

The undisputed standard tool of version control is git and any code should be under version control.

So if your code is not yet managed with git, this course is for you!

In this short course we will work with git in the command line, it requires no prior knowledge. We will:
- clone a git repository
- make changes and check for them
- create commits
- back up our code on Github
- switch between branches
- merge branches

Finally, you will have the possibility to put one of your own coding projects into version control.

In this training, we will show how to design, develop, and deploy API’s using Django Rest Framework (DRF). The approach will be practical; attendees will learn how to manage their classes (models) and build callable functions through URLs. At the end of the course, the attendees will be able to deploy their own functions in a local server for access through HTTP requests. Python expertise is required.

Short Course syllabus:
- Introduction to Django
- Setting up a Django project
- Introduction to Django Rest Framework
- Basic authentication
- API testing
- API documentation
- Hands-on Exercise

Participant requirements:
- Laptop with Python 3.9+ installed
- Basic Python knowledge
- IDE (VSC is preferable)
- Management of environments (Conda or virtualenv)

Material provided:
- Slides deck
- Step-by-step tutorial
- Environment requirements
- Code example. Attendees are encouraged to bring their own research code.

Earth System Sciences (ESS) datasets, particularly those generated by high-resolution numerical models, are continuing to increase in terms of resolution and size. These datasets are essential for advancing ESS, supporting critical activities such as climate change policymaking, weather forecasting in the face of increasingly frequent natural disasters, and modern applications like machine learning.

The storage, usability, transfer and shareability of such datasets have become a pressing concern within the scientific community. State-of-the-art applications now produce outputs so large that even the most advanced data centres and infrastructures struggle not only to store them but also to ensure their usability and processability, including by downstream machine learning. Ongoing and upcoming community initiatives, such as digital twins and the 7th Phase of the Coupled Model Intercomparison Project (CMIP7), are already pushing infrastructures to their limits. With future investment in hardware likely to remain constrained, a critical and viable way forward is to explore (lossy) data compression & reduction that balance efficiency with the needs of diverse stakeholders. Therefore, the interest in compression has grown as a means to 1) make the data volumes more manageable, 2) reduce transfer times and computational costs, while 3) preserving the quality required for downstream scientific analyses.

Nevertheless, many ESS researchers remain cautious about lossy compression, concerned that critical information or features may be lost for specific downstream applications. Identifying these use-case-specific requirements and ensuring they are preserved during compression are essential steps toward building trust so that compression can become widely adopted across the community.

This short course is designed as a practical introduction to compressing ESS datasets using various compression frameworks and to share tips on preserving important data properties throughout the compression process. After completing the hands-on exercises, using either your own or provided data, time will be set aside for debate and discussion to address questions about lossy compression and to exchange wishes and concerns regarding this family of methods. A short document summarising the discussion will be produced and made freely available afterwards.