Recent advances in machine learning are transforming weather and climate science, from the emergence of large‑scale foundation models (e.g. Aurora, ORBIT, WeatherGenerator and Walrus) to the rapid development of explainable and trustworthy AI methods that aim to make these models scientifically credible and operationally usable. This session brings together contributions on the development, evaluation, and application of large‑scale and foundation‑style machine learning systems, alongside state‑of‑the‑art research on interpretability, trust, diagnostics, and validation of ML models across Earth system applications. We welcome studies that address the methodological and scientific challenges associated with pre‑training and scaling ML models on diverse atmospheric and climate datasets; the assessment of training strategies, physical consistency, and model behaviour at scale; and post/pre‑training adaptation approaches such as fine‑tuning, distillation, and latent‑space steering. We equally encourage contributions that advance explainable AI (XAI) for weather and climate science, including feature attribution, causal inference, model bias diagnosis, uncertainty communication, human‑in‑the‑loop validation, and stakeholder‑oriented interpretability. Contributions that develop scalable, robust XAI techniques for high‑dimensional geoscientific problems are particularly welcome. By bridging foundation‑model development with explainability, trust, and scientific insight, this session aims to support a more transparent, reliable, and physically grounded development of ML tools for weather, climate, and environmental applications that push the boundary in terms of skill and quality.

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.

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.

Recent advances in advanced machine learning models, agentic systems, and generative AI are opening up possibilities for addressing complex geoscientific challenges. These approaches enable novel ways to analyse data, support decision-making, and enhance scientific workflows, while raising important questions about alignment with human expertise, values, and responsibility. Generative AI enables the creation of new content across modalities, agentic AI allows autonomous systems of agents to act with minimal supervision and leverage tools, and hybrid intelligence integrates human contextual, causal, and ethical reasoning with AI’s computational power. In practice, causal reasoning is often where stakeholders' experience and domain insight are most naturally expressed, beyond what can be captured by model architectures, metrics, or post-hoc explainability alone.

This session explores both practical applications and conceptual frameworks of generative, agentic, and hybrid AI (inclusive of advanced ML/DL models) in the geosciences, with a strong emphasis on human-centred design. Topics include AI-assisted data analysis and modelling, knowledge discovery and curation, decision support, science communication, and AI-enhanced workflows guided by domain expertise. We particularly encourage contributions that demonstrate how human insight and causal reasoning complement AI.

The session also addresses ethical and societal aspects of AI deployment in geosciences, including transparency, bias mitigation, accountability, sustainability, and trustworthiness. The overarching goal is to highlight AI as a tool to empower and extend human expertise—keeping scientists and domain experts at the centre of innovation. Contributions from research, industry, and policy communities are all welcome.

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 in Earth systems, such as Destination Earth, is revolutionizing our approach to understand and manage our planet’s complex dynamics under a changing climate. These advanced simulations enable us to integrate diverse types and sources of data, providing a comprehensive view of Earth-climate dynamics and human-environment interactions. In detail, digital twins allow to replicate a system behaviour, provide an up-to-date status of ongoing physical processes, support informed decision-making. They enable predictive Earth observation, exploring "what if" scenarios or simulating hazard cascades, and testing various adaptation strategies.

This session will explore the role of digital twins for bridging observations and simulations to applications in impact sectors. There will be a special focus on uncertainty quantification, data assimilation, multi-source data streams, hybrid modelling, and decision support. 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. 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, carbon storage, etc…) and will extend to economic, social components and policy considerations. It will act as a forum for researchers and practitioners to share their insights and recent developments in this rapidly evolving field.

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.

Data science, machine learning (ML), and physics-informed modelling are rapidly transforming geothermal energy systems and subsurface resource engineering. These digital approaches enable the integrated interpretation of heterogeneous data, predictive simulation of complex coupled processes, uncertainty-aware decision making, and end-to-end digital workflows across the full lifecycle of subsurface energy projects.

This session invites contributions advancing data-driven, physics-informed, and hybrid physics–ML methodologies for geothermal, geotechnical, and geoenvironmental applications relevant to energy and subsurface resources. Topics include subsurface and site characterization, reservoir engineering, subsurface flow and transport, induced seismicity, coupled thermo-hydro-mechanical-chemical processes, as well as geotechnical aspects of geothermal infrastructure such as foundations, tunnelling, and slope stability. Contributions employing supervised and unsupervised learning, deep learning, physics-informed neural networks, surrogate and reduced-order models, and inverse modelling approaches are particularly encouraged. We also welcome contributions that integrate laboratory and field experimentation, such as CT imaging, NMR, scattering methods, core- and rock-mechanical testing, and field monitoring, with data science and physics-informed modelling workflows for parameter inference, model calibration, and validation.

A central focus of the session is digital innovation for geothermal energy systems, spanning exploration, development, monitoring, and operation. Relevant topics include geothermal and subsurface databases; data quality control, uncertainty quantification, and metadata standards; integration of multi-source datasets (geological, geophysical, thermal, geochemical, and operational); and AI/ML approaches for resource assessment, reservoir characterisation and modelling, performance forecasting, and operational risk or failure prediction. Contributions related to open and FAIR data infrastructures, semantic technologies, and European and national initiatives (e.g., GeoERA, DESTRESS, HeatStore, GSEU, GeoMAP, MALEG, WärmeGut) are particularly welcome.

The session also welcomes studies integrating ML and data science with monitoring technologies such as IoT sensor networks, remote sensing, and real-time data streams, as well as the development of digital twins for geothermal and subsurface energy systems.

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.

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 crucial role in shaping the Earth's climate and in modulating hydrometeorological variability as well as the occurrence of compound extreme events. As a core component of state-of-the-art Earth System Models (ESMs), their representation critically influences and enables climate feedbacks essential for predictions and climate-change projections. However, land hydrology and its interactions with other components of the Earth system (e.g. biosphere, biogeochemical cycles, anthropogenic disturbances/practices) remain poorly represented in most ESMs, potentially inducing erroneous responses to anthropogenic climate forcings at global to local scales and leading to misrepresentations of the occurrence, intensity and sequencing of droughts, floods and their compound manifestations. For instance, ESMs do not represent the observed decline of groundwater levels in water-limited regions, threatening the subsistence of groundwater-dependent ecosystems and exacerbating persistence and impact of droughts, thereby increasing the risk of ecosystem shifts and to progressive desertification.
This session is therefore open to observational and modeling contributions advancing the understanding and representation of hydrological, biophysical and biogeochemical processes and couplings in land surface models, including the simulation and predictability of compound extreme events across time scales. 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, human-water feedbacks, and the effects of land-based mitigation/adaptation options to climate change.
The session also welcomes contributions on high-resolution ESMs, advanced observation systems, and emerging data-driven and Artificial Intelligence approaches that enhance early warning capabilities and support resilience to compound hydrometeorological hazards.
The overarching aim of this session is to provide an open and collaborative space to bridge disciplinary gaps within and across communities involved in land surface modeling, and to strengthen links between land surface process representation and downstream applications in climate prediction and climate-change studies, with particular relevance for compound extreme events and transitions, while highlighting priorities and emerging opportunities for 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. Degradation of water quality due to natural and anthropogenic activities poses significant threat to freshwater availability. Space-time modelling of water quality depends on the availability of long-term reliable datasets, which are often found to be incomplete, sparse, or unavailable. Water quality, though monitored frequently, limited knowledge is available about emerging contaminants. Subsurface environments, which are highly heterogeneous, influence flow and transport dynamics and surface-subsurface interaction mechanisms, making model calibration quite challenging. These drivers greatly influence catchment hydrology, hydrodynamics, biogeochemical processes and ecosystem. In dynamic environments, solute transport, sediment dynamics, and vegetation are also coupled through hydrodynamic and biogeochemical feedback for improved understanding of processes, nutrient cycling and ecosystem functioning.
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 and water quality monitoring networks and installation of IoT sensors is very limited. It is therefore warranted to leverage geospatial, machine learning, decision science, statistical and modelling techniques to improve the understanding of catchment hydrology and consequences of climate change and anthropogenic drivers on surface and groundwater resources at various scales. The worldwide readily available satellite remote sensing data and global data products enable us to leverage these techniques in addressing water and environmental challenges.
We solicit novel contributions from researchers in catchment hydrology by utilizing Remote Sensing, GIS, Artificial Intelligence (AI), Machine Learning (ML), Decision Science, and advanced statistical techniques for addressing pressing challenges of water sustainability in mountainous and urban catchments and data scarce regions. The combined use of these technologies will revolutionize understanding of complicated hydrological, hydrodynamic and biogeochemical processes, and will be useful in evolving effective water resource management and ecosystem-based adaptation strategies to foster sustainable development.

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 provides a platform for showcasing state-of-the-art methods and techniques to assess risks associated with hydro-climatic extremes like floods, storms, landslides, and on compound dry hazards such as droughts, heatwaves, and fires. When these events are compounded, overlapping each other in time and spatial coverage, or following one another, their compounded nature generates cascading impacts on water resources, ecosystems, infrastructure, and human systems that cannot be captured by single hazard analyses alone. We aim to exchange knowledge and insights into how machine learning algorithms, data mining techniques, physical models, and the integration of satellite data can significantly enhance predictive capabilities for analyzing the societal risks associated with hydro-climatic extremes and compound hazard events. The session highlights innovative applications and real-world case studies demonstrating 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, ecologists, climate scientists, AI researchers, hydrologists, and decision makers.

Key Themes:

Processes:
Physical processes involved in hydro-climatic extremes and compound hazards (e.g., droughts-heatwaves-fires), their precondition factors, enabling mechanisms, feedbacks, emergent properties, and synergistic effects. Interaction and impact of such events in the physical system, ecosystems, and human population.

Methods & techniques:
Integration of remote sensing, data mining, and machine learning approaches to enhance the detection, monitoring, and prediction of hydro-climatic extremes and compound events. Combination of physically-based hydrological and climatological models with AI-driven simulations, as well as applications across multiple spatial and temporal scales, from local case studies to regional and global assessments.

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.

Spatio-temporal Earth System Science (ESS) datasets are constantly growing in size, particularly those generated by high-resolution numerical models, 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, while future investment in hardware is likely to remain constrained. This limits the potential of numerical simulation models and machine learning models, for example. However, these models and the larger datasets they produce 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.

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

We invite everybody recognizing the problem and working on ways to solve it to participate in 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 cubes, HDF5, netCDF, Zarr, COG
- Data compression, including methods that provide guarantees for lossy compression
- 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.

Solicited authors:
Langwen Huang

To learn more about data compression and try out different compressors in practice, please also join the SC2.5 short course.

Cloud computing and high-performance computing (HPC) have become essential infrastructures for processing large-scale Earth Observation (EO) and Earth System modeling data. The convergence of these paradigms—combined with containerization, AI/ML frameworks, and cloud-native storage—is reshaping how we manage, analyze, and share geoscientific information.
Pangeo (pangeo.io) is a global open community developing scalable, interoperable workflows using tools such as Xarray, Dask, Zarr, and Jupyter. Discrete Global Grid Systems (DGGS) offer a complementary paradigm: equal-area, multi-resolution indexing that enables seamless integration across domains and scales. Together, these approaches support FAIR (Findable, Accessible, Interoperable, Reusable) data management and reproducible, transdisciplinary research.
We invite contributions that explore Cloud and HPC workflows for Earth science, including but not limited to:
• Big data platforms, cloud federations, and interoperable infrastructures (IaaS, PaaS, SaaS)
• Cloud-HPC convergence for EO and modeling workloads
• DGGS-based data organization, indexing, and multi-resolution analysis
• Cloud-native AI/ML applications for geoscientific data
• Reproducible workflows and executable notebooks using Pangeo tools
• Cloud storage solutions, data lakes, and FAIR data management
• Sustainable and green computing practices
We welcome case studies, technical developments, and community-driven initiatives that advance open, scalable, and interoperable Earth data science.

Scientific discovery today increasingly depends on the availability of digital services and infrastructures that span the entire research workflow. While sensors, simulations, and lab experiments produce massive data, many tools for analysis remain fragmented in stand-alone systems, often hindering collaboration and a comprehensive understanding of complex Earth systems.

To address this, e-Infrastructures and Virtual Research Environments (VREs) are revolutionising how research is conducted. By providing a cohesive ecosystem, these platforms allow researchers from diverse disciplines to manage the research lifecycle: from data acquisition and processing to modeling and dissemination in the spirit of Open Science. This integration enables the research community to transition from isolated tools to interoperable systems like Digital Twins.

This session aims to highlight how interoperable e-Infrastructure services can be used to build VREs and Virtual Labs to provide end-to-end support, strengthening research capacity through collaboration between service providers and scientists. We bring together case studies and new approaches from all domains of the Earth sciences, focusing on both technological implementations and scientific applications.

Contributions in this session will:
- Demonstrate practical examples of how digital services, VREs, and e-infrastructures enhance research workflows in Earth and environmental sciences.
- Present innovative approaches to integrating tools across domains and providers, including outcomes from collaborative projects, virtual laboratories, and digital twins.
- Highlight technical implementations, including research software applications, semantic approaches, modeling practices, and the management of large-scale data.
- Share lessons learned from user-driven design, community engagement, training and support strategies.
- Address challenges of interoperability and sustainability in distributed digital services, highlighting pathways to foster collaboration across infrastructures and research domains.

By bringing together service providers, research infrastructures, and end-users, this session will provide a unique overview of the digital landscape and its impact on science. It will foster dialogue on how different infrastructures can collaborate more effectively to provide integrated, sustainable solutions, embedding Open Science principles across the research lifecycle, and 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.
● Tools and best-practices for visualizing complex, high-dimensional and high frequency data
● Developments of open source visualization and exploration techniques for earth system science data
● 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!

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.

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.

Addressing global environmental and societal challenges—ranging from climate change, natural hazards, and biodiversity loss—requires interdisciplinary Earth System Science based on transparent, reproducible, and collaborative research. The rapidly growing volume and diversity of data, coupled with increasing demands for interoperability and societal relevance, the need for robust and user-oriented Research Data Infrastructures (RDIs) and Virtual Research Environments (VREs) as essential components of modern Earth system research is more pressing than ever.

This session explores how data infrastructures and platforms can enhance interdisciplinary and transdisciplinary research by integrating perspectives from Open Science, the FAIR and CARE data principles, sustainable software development, and virtual research environments. Our session is focused on bridging the gap between user needs and sustainable, interoperable solutions by combining technical innovation with cultural change, stakeholder engagement, and capacity building. Scientific unions, research infrastructures, and international frameworks play a pivotal role in facilitating this transformation incentivising open and collaborative research practices.

We invite contributions that demonstrate practical and scalable solutions for integrating, discovering, analysing, and reusing heterogeneous Earth system data across disciplines and scales. We seek contributions showcasing operational platforms, standards, and concrete use cases that turn open data into actionable knowledge.
Topics include user-driven research infrastructures and virtual research environments (VREs); semantic technologies, ontologies, and machine-actionable metadata for interoperability; cross-domain data fusion and stakeholder engagement; sustainable, reusable software components; and robust operational and sustainability models for data centres and infrastructures. We particularly encourage contributions addressing training, documentation, and co-design, as well as innovative approaches to FAIR data practices, collaboration, public engagement, and citizen science.

By highlighting success stories, lessons learned, and mature tools—from metadata and standards to fully operational platforms—this session aims to accelerate the shift from open to truly collaborative science and empower the next generation of Earth and environmental data scientists.

Making data Findable, Accessible, Interoperable and Reusable (FAIR) is now widely recognised as essential to advance open and reproducible research. Increasingly, this requires not only shared principles but also concrete digital implementations that enable interoperability across systems, disciplines, and infrastructures. However, it is very difficult to translate these principles into practical data management guidelines or operational digital solutions across disciplines. The goal of the session is to explore how best data management practices are developed, implemented, and adopted across disciplines, including through interoperable digital objects, persistent identifiers, and emerging data space concepts.

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, with a focus on community-driven approaches to technical standards and infrastructures.
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, for example through interoperable data architectures or research data spaces.
5) Present technical or conceptual approaches that support the transition from data silos to interoperable, FAIR-aligned data ecosystems.

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, from community processes to concrete, interoperable digital implementations.

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.

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.

Climate services are instrumental in translating local knowledge and scientific insights into practical applications, empowering communities at multiple scales to efficiently tackle climate change challenges.

The paradigm of Essential Variables (EVs) - ECVs, EOVs, EBVs - provides a data-driven foundation for global environmental monitoring (GCOS, GEO, UN SDGs). Yet, their full potential is hampered by interoperability gaps, fragmented governance, and siloed infrastructures, limiting integrated use and translation into local action.

Conversely, local demand for actionable information is growing. Earth Observation data, often as Analysis-Ready Data (ARD), must be transformed into locally relevant, co-created Action-Ready Information (ARI) for climate solutions. This requires integrating global EVs with local data and knowledge.

This session bridges these fronts. We explore all aspects of climate service development from the co-creation of climate services that emphasize inclusive and novel methodologies and the integration of multiple knowledge systems, through to the development of usable, equitable and impactful solutions for multiple stakeholder groups a focus on the use of technical, infrastructural, and socio-technical advancements to evolve EVs into a truly interoperable, global common language and ensure their effective translation for local decision-making. We welcome contributions on:

- Interoperability Foundations: Semantic frameworks (iADOPT, SOSA/SSN), FAIR principles, and lessons from research infrastructures (ENVRI, CRDCs) aligning EVs across domains and global programmes.
- From ARD to ARI: Case studies on transforming EV-based products into local insights via co-creation, integrating satellite data with in-situ, citizen science, and indigenous knowledge.
- Cross-Scale Infrastructure: Architectures and platforms (e.g., digital twins) enabling seamless data flow from global systems to local applications.
- Policy and Capacity: How interoperable EVs strengthen global policy (IPCC, SDGs) and how local insights inform action, including funding, capacity building, and governance models.

We invite scientists, data engineers, social scientists, and policymakers to connect the "essential" with the "actionable", forging a coherent path from global observation to local solution.

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).

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.

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.

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 (outlook only)

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 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 commonly need to write code but often 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 online 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 ideally, all code should be put under version control.

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

This short course requires no prior knowledge of git and will introduce the fundamentals of working with git from the command line:
- clone a git repository
- make changes and check for them
- create commits
- back up our code online on Github
- switch between branches
- merge branches

We will show you how to do these steps, and then help you follow along.
Finally, you will have the possibility to put one of your own coding projects into version control.


Looking forward to seeing you at the workshop!

Konstantin, Ben, Philipp


You can find the workshop material here: https://github.com/k-gregor/git-workshop
Further reading: https://doi.org/10.5194/egusphere-2025-1733

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.

To learn more about recent advances in data compression, please also join the ESSI2.2 oral and poster sessions.