Climate change intensifies hydro-geological hazards by altering precipitation and temperature patterns, affecting soil moisture, vegetation, groundwater, and surface runoff. These changes generate spatially and temporally variable triggers for floods, landslides, and droughts, challenging traditional methods based on historical records. Artificial intelligence (AI) offers a promising pathway by integrating multi-source observations with physics-informed learning to capture complex processes and incorporating future climate scenarios to enhance community resilience. This session explores AI integration for hydro-geological hazards under a climate-driven context, focusing on modeling, evaluation, and decision support. Key questions include: How can AI models account for complex physical processes and dynamically update triggering thresholds? How can multi-timescale climate variability and CMIP6 scenarios be embedded while preserving physical consistency? How can predictions remain robust under nonstationarity and inform early warning and climate-resilient planning?
We invite contributions addressing these challenges, with interest in AI, climate scenarios, and multi-scale process coupling. Topics include: 1) AI for hydro-geological hazards:
• Prediction and early warning of floods, landslides, and droughts using machine/deep learning for susceptibility mapping, monitoring, and real-time alerts.
• AI-driven coupled hazard modeling integrating rainfall, surface water, groundwater, and geological processes using multi-source data.
• Remote sensing and big data applications for hazard detection, evolution tracking, and mapping from satellite, UAV, or radar data.
• Assessing impacts of climate variability and extreme events on hazard occurrence.
• AI methods integrating CMIP6 scenarios with bias correction and downscaling for training and inference.
• Modeling physical processes, e.g., hydrological interactions among atmosphere, vegetation, and soil.
• Explainable AI and decision support systems for transparent hazard management, urban planning, and engineering measures.
2) Evaluation and decision support under climate change:
• AI-driven or GIS-based decision support platforms for adaptive management, policy-making, and disaster risk reduction.
• Assessing socio-economic vulnerability, resilience, and adaptation trade-offs under climate change.
• Evaluating nature-based and sustainable solutions as strategies for climate-resilient planning.

Recent advances in computational science and data-intensive methods are significantly improving our ability to detect, model, and respond to natural hazards in real/near-real time. From earthquakes, tsunamis and floods to wildfires, volcanic eruptions, and extreme weather events, the integration of high-performance computing, predictive modeling, and intelligent systems is enabling more effective and timely emergency response and operational frameworks and services, as illustrated from the outcomes of several EU-funded projects (e.g. ChEESE, doi: 10.3030/101093038; DT-GEO, doi:10.3030/101058129; or the EU-India partnership GANANA, doi:10.3030/101196247).
This session focuses on the role of scalable, adaptive, and AI-enhanced computing approaches in supporting the entire natural hazard management cycle: from early detection and warning to modelling, impact forecasting and decision support. We invite contributions that explore but not limited to innovative methods and real-world applications across the areas such as:
(i) Early detection and rapid warning systems, leveraging sensor networks, remote sensing, and predictive analytics, (ii)Time-critical simulations and forecasting models, (iii) AI applications in natural hazard contexts, including real-time/near real-time earthquake signal analysis, landslide and wildfire risk mapping, flood extent detection, and uncertainty-aware forecasting using ML-based ensemble models, (iv) Operational platforms and decision-support tools, integrating real-time data streams with adaptive modeling and, (v) Case studies demonstrating the application of such methods etc.
We invite contributions that showcase novel approaches in computational science, AI / machine learning, modeling systems, or hybrid workflows that improve readiness and responsiveness during natural disasters. We particularly encourage interdisciplinary submissions that highlight collaborative work across geoscience, computer science, and emergency management. This session aims to bring together researchers, practitioners, and system developers working at the intersection of geoscience and urgent computing to advance the state of natural hazard mitigation and civil protection.

Artificial intelligence has become central to Earth system science, yet a core challenge remains: how can we move from models that learn correlations to those that capture and reason with structure, especially under hazards and compound extremes? Many current methods swing between flexible learners that overfit and complex explainers that rationalise black boxes. This limits both understanding and robustness as system complexity, data diversity, and societal stakes grow.

This session focuses on interactions between atmosphere and hydrosphere, highlighting applications to extremes and related water–ecosystem impacts.

We invite contributions that address the transition from learners to knowers, asking for example:
- How can AI models reflect the organising logic of nature, not just the statistical shape of data?
- What happens when predictive skill is high but reasoning is flawed?
- How can models generalise across regions, scales, and regimes while remaining interpretable and trustworthy?

We particularly welcome studies that:
- Embed physical, hydrological, or causal structure into AI models
- Diagnose why current methods fail and what this reveals about their assumptions
- Introduce inductive biases and constraints that promote generalisation under distribution shift
- Move beyond post-hoc explanation toward structurally grounded modelling
- Share FAIR datasets, benchmarks, or reusable tools and workflows
- Explore the role of causal ML, physics-informed networks, or foundation models in linking data and knowledge

Who should submit?
Earth and environmental scientists, hydrologists, hazards researchers, and AI specialists interested in structuring machine learning for process understanding. We welcome both theoretical and applied work; from those developing hybrid or interpretable models to those testing their limits in complex environmental systems. Case studies may span regions or scales but should highlight what makes a model explain rather than merely predict.

Our goal is to redefine how AI advances Earth system science by turning learners into knowers: models that reason with structure, are accountable, and generalise under change.

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

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

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

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

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

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

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

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

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

Machine learning (ML) is being used throughout the geophysical sciences with a wide variety of applications. Advances in big data, deep learning, and other areas of artificial intelligence (AI) have opened up a number of new approaches to traditional problems.

Many fields (climate, ocean, numerical weather prediction, space weather etc.) make use of large numerical models and are now seeking to enhance these by combining them with scientific ML/AI techniques. Examples include ML emulation of computationally intensive processes, data-driven parameterisations for sub-grid processes, ML assisted calibration, and uncertainty quantification of parameters, amongst other applications.

Doing this brings a number of unique challenges, however, including but not limited to:

- enforcing physical compatibility, consistency, and conservation laws
- ensuring numerical stability,
- coupling of numerical models to ML frameworks and language interoperation,
- development and usage of differentiable models and model components,
- handling computer architectures and data transfer,
- adaptation/generalisation to different models, resolutions, or climates,
- explaining, understanding, and evaluating model performance and biases.
- quantifying uncertainties and their sources
- tuning of physical or ML parameters after coupling to numerical models (derivative-free optimisation, Bayesian optimisation, ensemble Kalman methods, etc.)

Addressing these requires knowledge of several areas and builds on advances already made in domain science, numerical simulation, machine learning, high-performance computing, data assimilation etc.

Following success over the past two years at EGU, we again solicit talks that address any topics relating to the above. Anyone working to combine machine learning techniques with numerical modelling is encouraged to participate in this session.

Machine learning (ML) is currently transforming data analysis and modelling of the Earth system. While statistical and data-driven models have been used for a long time, recent advances in machine learning now allow for encoding non-linear, spatio-temporal relationships robustly without sacrificing interpretability. This has the potential to accelerate climate science, by providing new physics-based modelling approaches; improving our understanding of the underlying processes; reducing and better quantifying climate signals, variability, and uncertainty; and even making predictions directly from observations across different spatio-temporal scales. The limitations of machine learning methods need to also be considered, such as requiring, in general, rather large training datasets, data leakage, and/or poor generalisation abilities, so that methods are applied where they are fit for purpose and add value.

This session aims to provide a venue to present the latest progress in the use of ML applied to all aspects of climate science and we welcome abstracts focussed on, but not limited to:
- Causal discovery and inference: causal impact assessment, interventions, counterfactual analysis
- Learning (causal) process, equations, and feature representations in observations or across models and observations
- Hybrid models (physically informed ML, emulation, data-model integration)
- Novel detection and attribution approaches, including for extreme events
- Probabilistic modelling and uncertainty quantification
- ML-based super-resolution and bias-correction for climate downscaling
- Explainable AI applications to climate data science and climate modelling
- Distributional robustness, transfer learning and/or out-of-distribution generalisation tasks in climate science

Machine learning (ML) methods have emerged as powerful tools to tackle various challenges in ocean science, encompassing physical oceanography, biogeochemistry, and sea ice research.
This session aims to explore the application of ML methods in ocean science, with a focus on advancing our understanding and addressing key challenges in the field. Our objective is to foster discussions, share recent advancements, and explore future directions in the field of ML methods for ocean science.
A wide range of machine learning techniques can be considered including supervised learning, unsupervised learning, interpretable techniques, and physics-informed and generative models. The applications to be addressed span both observational and modeling approaches.

Observational approaches include for example:
- Identifying patterns and features in oceanic fields
- Filling observational gaps of in-situ or satellite observations
- Inferring unobserved variables or unobserved scales
- Automating quality control of data

- Modeling approaches can address (but are not restricted to):
- Designing new parameterization schemes in ocean models
- Emulating partially or completely ocean models
- Parameter tuning and model uncertainty

The session also welcomes submissions at the interface between modeling and observations, such as data assimilation, data-model fusion, or bias correction.

Researchers and practitioners working in the domain of ocean science, as well as those interested in the application of ML methods, are encouraged to attend and participate in this session.

Carbon monitoring is becoming ever more critical as climate change accelerates and society turns to carbon management strategies, ranging from carbon credits to the preservation and restoration of natural carbon sinks. Yet the success of these approaches depends on robust science: measurements must be accurate, verification must be rigorous, and promises must be grounded in evidence. Machine learning (ML) is rapidly transforming carbon cycle research, offering new opportunities to integrate diverse data streams, harness remote sensing, and connect multiple lines of evidence across scales. This session will highlight recent advances in ML applications for investigating, monitoring, and managing the carbon cycle, spanning satellite-based greenhouse gas estimation, biomass and forest monitoring, soil and peatland carbon dynamics, wetland and ecosystem restoration, and the mapping of terrestrial and oceanic carbon storage. We particularly encourage contributions that address hybrid modeling, uncertainty quantification, ecological mapping, knowledge-guided and trustworthy ML in carbon markets and policy contexts. By bringing together advances from Earth observation, process modeling, and policy-relevant applications, this session aims to explore both the promises and challenges of ML in delivering actionable insights for carbon management and climate mitigation.

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

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

Rural communities and nature-based tourism destinations are facing growing uncertainties related to climate change, natural hazards and pressures on natural environments stemming from tourism and outdoor recreation on both biodiversity and geodiversity. Industry, government and stakeholders must make decisions now to secure a sustainable and resilient future. This session, brings together transdisciplinary and interdisciplinary research which leverages data-driven approaches to support decision-makers in strategy development. The focus is on the protection geo- and biodiversity along with recreational landscapes, addressing climate change and fostering trust in data to ensure informed and impactful decision-making for regions characterized by nature-based tourism and outdoor recreation. Topics of interest include:
• Linking Geoscience and social science methods in tourism and recreation research, studies and development
• Importance of geodiversity, biodiversity and ecosystem services in nature-based tourism
• Natural hazards, visitors’ perception and preparedness planning in nature-based tourism management
• Climate change adaptation and resilience in tourism destinations
• Resilient communities through sustainable tourism development
• Strategic decision-making
• Citizen and participatory approaches
• Using local knowledge for sustainable development and climate change mitigation
• Sustainable land use for touristic purposes
• Environmental and tourism policy and governance aspects
This inter- and transdisciplinary session brings together research on climate change, tourism and landscape development to form stronger links between geosciences and social sciences in order to foster an environment of data-driven decision-making and transdisciplinary collaboration.

Downscaling aims to process and refine global climate model output to provide information at spatial and temporal scales suitable for impact studies. In response to the current challenges posed by climate change and variability, downscaling techniques continue to play an important role in the development of new services and products. While the refinement of downscaling techniques proceeds at an unprecedented pace, users of climate information are facing the novel challenge of how to select amongst the choice of available datasets or how to assess their credibility with respect to a particular application. In this context, model evaluation and verification is growing in relevance and advances in the field will likely require close collaboration between various disciplines.

Recent developments, including the integration of AI and machine learning applications, the emergence of kilometre-scale simulations, and the widespread availability of open-source downscaling products, add new dimensions to this challenge. These advances raise important questions about the ‘added value’ of downscaling, especially in light of the cascade of uncertainty and the need for robust evaluation frameworks.

In our session, we aim to bring together scientists from the various geoscientific disciplines interrelated through downscaling: atmospheric modeling, climate change impact modeling, machine learning and verification research. We also invite philosophers of climate science to stimulate our discussion about the novel challenges that arise from evaluating complex models and modelling chains in the face of the increasingly heterogeneous needs of the growing user communities.

Contributions to this session may address, but are not limited to:
- newly available downscaling products,
- applications relying on downscaled data and impact assessments,
- downscaling method development and machine learning,
- bias correction and statistical postprocessing,
- challenges in the data management of kilometer-scale simulations,
- verification, uncertainty quantification and the added value of downscaling,
- downscaling approaches in light of computational epistemology.

Understanding where people live, how populations are distributed, and how these patterns change over time is central to many of nowadays most pressing research and policy questions. This session focuses on new developments in gridded population and socio-demographic datasets to help characterize human-environment interactions in relation to the complex world. We invite presentations that present latest research in building and validating these datasets, as well as studies that put them into practice in areas such as climate change adaptation, urban growth, disaster risk management, and public health. Additionally, we encourage interested authors to submit innovative approaches on investigating spatial accuracy and data fusion approaches for future projections under alternative scenarios. The session seeks to showcase both the practical applications and technical advances in demographic data products that can support decision making in an uncertain future.

Recent advances in Large Language Models (LLMs) and Natural Language Processing (NLP) are rapidly changing geosciences research, offering new opportunities for knowledge discovery, data analysis, and real-time monitoring. At the same time, the increasing availability of digital text and image data—from scientific literature and newspaper articles to social media and historical archives—offers unprecedented opportunities to explore new data sources in geosciences research.

This session examines how geoscientists are using LLMs, NLP, and text-as-data approaches across various hydrology, natural hazards research, and the broader earth system sciences research fields. We invite contributions that showcase innovative uses of LLMs and NLP, discuss methodological challenges, or integrate text mining techniques into geoscientific workflows.

We particularly welcome submissions on topics including, but not limited to:
- Chatbots and AI assistants in geosciences
- Assessment of natural hazard impacts (e.g., floods, droughts, landslides, heatwaves, windstorms)
- Real-time disaster monitoring and early warning systems
- Evidence synthesis and literature mapping
- Public sentiment and perception analysis
- Policy tracking and narrative analysis
- Social media analyses
- Enhancement of metadata and data descriptions
- Automation of historical data rescue
- Integration of LLMs with remote sensing or image data
- Methodological challenges in using LLMs and NLP-based analyses, including bias, reproducibility, and interpretability

By sharing case studies, technical developments, and lessons learned, we aim to promote the effective use of these tools while also highlighting the challenges that newcomers may encounter, including issues with data coverage, quality control, and concerns about reproducibility. By sharing best practices, this session aims to inspire collaboration and innovation in harnessing LLMs, NLP, and text-as-data in geosciences.

The global community is vastly off track to achieve the UN Sustainable Development Goal 6 on “clean water and sanitation for all” and urgent action is needed to correct this course. However, informed decision making requires sufficient and reliable long-term data and yet, large in situ data gaps still exist on almost all aspects of the hydrological cycle. This was clearly evident in the WMO Status of the Global Water Resources Report for 2023 and is reinforced in this year’s report for 2024.
This session aims to highlight studies that help to close this data gap. This includes the initiation or development of long-term in-situ monitoring programmes, the enhancement of monitoring programmes with novel methodology, or quality improvement of existing data. This session supports a wide range of United Nations programmes, notably the UN Early Warning for All Initiative with its pillar 2 on Detection, Observations, Monitoring, Analysis and Forecasting, output 3.3 of the UNESCO IHP IX (2022 - 2029) which promotes the availability of validated open access water data for sustainable water management, and the WMO Unified Data Policy that aims to implement free and unrestricted data exchange between member states. We invite contributions on the following topics:
1. Developing long-term monitoring:
- Initiation of long-term monitoring programmes emphasizing benefits and challenges
- Extension of existing long-term monitoring programmes, e.g. by combining different components of the hydrological cycle
2. Innovative methods to support long-term monitoring programmes
- Enhancing in-situ monitoring using remote sensing and modelling – reinforcing current monitoring and filling data gaps in the past
- Using citizen science and/or indigenous data sources to strengthen long-term monitoring programmes
- Digitizing written monitoring records applying machine learning and/or crowdsourcing

Earth Observation (EO) offers a powerful means of monitoring changes in climate, ecosystems, and human environments at both global and local scales. These observations generate a wide array of climate and environmental variables, and they are delivered as Analysis-Ready Data (ARD). While ARD is globally accessible and scientifically robust, it might lack the specificity and contextual relevance required to effectively address local challenges. To bridge this gap, ARD must be transformed into Action-Ready Information (ARI): tailored data products and insights that support local decision-making and reflect community priorities. This transformation depends on co-creation, a collaborative process involving local communities, scientists, engineers, policymakers, and private sector stakeholders. For example, by integrating satellite EO with locally collected data from ground, water, and airborne platforms, we can enhance data granularity, validate satellite outputs, and generate customized, equitable, and actionable solutions. This session will explore how data can be harnessed to support environmental monitoring, local climate mitigation and adaptation, and sustainable development. It will emphasize the importance of identifying gaps between global datasets and local needs, and present strategies to close these gaps through innovation (e.g. new technologies and open FAIR science), inclusive engagement, and capacity building. Economic and policy dimensions will also be addressed, including the sustainability of community-led initiatives, the role of citizen science, funding mechanisms, and scalable technologies that enhance data utility for local solutions. The practical implementation challenges confronting policymakers when seeking to engage with EO data, particularly in the context of constrained policy capacities, will also be discussed. We invite participants from across/around the EO ecosystem: researchers in both physical and social sciences, community leaders, and stakeholders from policy and business sectors. We do not limit us only to satellite EO. We do consider non-EO observations and data, and their applications. We will share case studies, identify synergies between global and local efforts, and co-create knowledge that informs both local action and global strategies. By synthesizing diverse experiences, this session aims to advance EO as a tool for addressing the interconnected climate and environmental challenges we face locally and globally.

Earth system dynamics are strongly influenced by land‑surface processes that operate across a wide range of temporal and spatial scales. Sub‑daily land‑atmosphere coupling shapes cloud formation and radiation transfer; seasonal vegetation dynamics modulate evapotranspiration on weekly‑to‑monthly scales and shape the hydrologic cycle; and decade‑to‑century changes in ecosystem composition and soil carbon dynamics affect the global carbon cycle and atmospheric  CO₂. Human activities, such as land‑cover change, land‑management practices, and fossil‑fuel or biomass burning are the most impactful direct and indirect perturbations of the land surface. This session explores how these diverse changes, their impacts, and potential feedbacks operate from the global scale to regional hotspots. It focuses on four interlinked themes (remaining open to related topics), exploring the effects of land changes:

1. Radiative balance, including albedo changes and their effect on the planetary energy budget; modulation of land‑atmosphere coupling and low‑cloud formation; influence of biogenic volatile organic compound emissions on clouds.
2. Water cycle, including moisture recycling over land; trends in soil moisture and lower‑tropospheric humidity; CO₂-driven stomatal conductance and plant water‑stress dynamics; shifts in surface turbulent‑flux partitioning.
3. Carbon cycle, including changes in land carbon uptake and release fluxes, long‑term vegetation shifts, soil and vegetation carbon turnover, CO₂ fertilization, and nutrient dynamics.
4. Human‑societal impacts, including effects on ecosystem services such as water and food security, links between land degradation and societal vulnerability, and potential societal feedbacks.

Contributions should adopt a coupled Earth‑system perspective, investigating processes in interaction rather than isolation. We encourage submissions which (i) quantify the magnitude and direction of biogeophysical and biogeochemical feedbacks, (ii) identify key uncertainties in current CMIP‑style Earth‑system models, and (iii) propose concrete pathways to constrain these uncertainties. Innovative approaches that integrate multi‑stream observational datasets and hybrid or machine‑learning‑enhanced modeling are especially welcome. Join us in this session, hosted in partnership with the Max‑Planck‑Caltech‑Columbia‑Carnegie Center for Earth (mc‑3.org), which emphasizes this holistic view of land processes within the Earth system.

Environmental challenges such as climate change, biodiversity loss, water scarcity, and ocean degradation demand new ways of observing, monitoring, and understanding the Earth system. Research Infrastructures (RIs) in the ENVRI community—spanning atmospheric, marine, terrestrial, and solid earth sciences—provide the backbone of European environmental observation and long-term data stewardship. Yet, the growing complexity of environmental change requires innovative technologies and services to enhance monitoring, strengthen interoperability, and accelerate the translation of knowledge into actionable insights.

This session brings together researchers, technologists, and stakeholders to showcase advances illustrating (1) the role of emerging technologies and (2) service-oriented approaches in shaping the future of environmental monitoring.

Emerging technologies include advanced instrumentation, miniaturized and autonomous sensors for atmospheric, hydrological, soil, and marine processes, as well as unmanned aerial systems, drones, satellite constellations, and IoT networks that link in-situ with remote sensing. Artificial intelligence (AI) is transforming how environmental data are processed, harmonized, and applied in predictive modelling.

The ocean, a key climate regulator, remains critically under-observed for carbon fluxes, particularly beyond shipping routes. Addressing this gap, the GEORGE project—a collaboration between EMSO ERIC, EURO-ARGO ERIC, ICOS ERIC, research institutions, universities, and industry—develops novel tools and methods to measure carbonate chemistry (e.g., pH, alkalinity, dissolved inorganic carbon, pCO₂) across diverse marine environments.

Services are equally vital. Trans-National Access (TNA) schemes offered by ENVRIs provide opportunities for researchers to use state-of-the-art facilities, advanced instrumentation, and high-quality data services beyond national systems. These services foster collaboration, accelerate innovation, and support co-created solutions to pressing challenges. The convergence of cloud-based infrastructures, FAIR data principles, interoperability frameworks, and user-centered service design ensures that resources are not only technically robust but also widely accessible and impactful for science, policy, and society.

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

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).

This session invites contributions that advance the theory, development, and application of digital solutions, such as digital twins, in water resources research and management. Hydrologic digital twins are virtual representations of water systems that are continuously updated with real-time observations, allowing for simulation, analysis, and automatic and autonomous management. These, and other digital solutions are crucial in advancing the application and impact of scientific technical and theoretical findings by end user stake holders. Under changing environmental conditions and risk of regional and global natural hazards, advanced two-ways data transfer and scientific information solutions are more crucial than ever. We welcome presentations on multi-scale digital solutions, such as: physical modelling frameworks; fusion of next-generation hydrologic observations into modelling frameworks, including remote sensing, in-situ, and crowd-sourced data; automated data networking, processing, and assimilation systems; machine learning and hybrid approaches in model-data integration; uncertainty quantification and propagation in data assimilation workflows; real-time forecasting and decision support systems for water resources and disaster management; autonomous processes and embedded devices in water resources management; and case studies of digital twins in water resources research and applications. We are particularly interested in work that supports scale translation in hydrologic systems modelling (both spatial and temporal), and enables the coupling of physical and data-driven models. Submissions from the Digital Waters Flagship and Pilot (https://digitalwaters.fi) are strongly encouraged.