Project Acronym: GENAI-X
Project Duration: April 2026 – March 2031
Funding Volume: €6,000,000
Supported by: Carl Zeiss Foundation
Overview
GENAI-X tackles a fundamental challenge in artificial intelligence: achieving robust model generalizability in non-stationary environmental systems—those where conditions evolve unpredictably across space and time. The project focuses on hydro-climatic extremes such as floods, landslides, droughts, and late-frost events, which are intensifying under climate change.
Scientific Motivation
Conventional machine learning assumes stable data distributions. Yet in real-world environmental systems, data is often sparse, uncertain, and shaped by changing climatic drivers. This non-stationarity undermines model reliability and calls for AI systems that can adapt to shifting baselines and novel conditions.
Impact and Application
Beyond theoretical development, GENAI-X creates AI-driven tools for environmental monitoring, hazard assessment, and decision support that bridge scientific research and real-world application. These innovative tools aim to improve predictions of hydro-climatic risks, such as floods, droughts, and landslides, and to guide evidence-based policy and management strategies. By integrating satellite observations, in-situ sensor data, and large-scale simulations, the project enables a deeper understanding of dynamic Earth system processes and their socio-economic impacts. The resulting tools support sustainable resource management, biodiversity protection, and ecosystem resilience. In addition, GENAI-X enhances data-driven decision-making through transparent, explainable, and transferable AI models. The project strengthens interdisciplinary collaboration across computer science, geosciences, and environmental research, contributing to global efforts in climate adaptation, disaster risk reduction, and the long-term preservation of natural systems essential for human well-being.
Climate-change-aware landslide susceptibility modeling
Flood risk assessment and early warning
Phenological shifts and ecosystem responses to climate stress
Ecosystem-atmosphere carbon and water fluxes during extreme events
Research Goals
GENAI-X advances cutting-edge AI methodologies that enhance adaptability, resilience, and predictive performance in dynamic Earth and environmental systems. The project integrates five complementary approaches: (AI1) Hybrid modeling (AI2) Causal modeling (AI3) Equation discovery (AI4) Dimension reduction (AI5) Uncertainty quantification.
Broader Relevance
The results of GENAI-X are of importance for achieving social and environmental benefits by developing fundamental AI solutions and implementing them in the domain sciences in the field of hydro-climatic extremes. Beyond the domain-specific AI, multiple ongoing or planned research projects in the domain sciences will directly or indirectly benefit from the proposed advances in environmental AI, including collaboration with government stakeholders
Partner
Principal Investigators
Prof. Dr. Alexander Brenning (FSU) is a full professor of geographic information science, adjunct professor at the University of Waterloo, Canada, Humboldt fellow (2014), and former Dean of the Faculty of Chemistry and Earth Sciences (2017-2020). He is an internationally recognized expert in geospatial modeling of Earth surface processes, in particular natural hazards, focusing on uncertainty quantification and interpretability of spatial statistical and ML models. Having received funding from DFG, Umweltbundesamt, NSERC, BMBF, EU and Carl Zeiss Foundation, his 116 publications have been cited >5500 times (h-index 39).
PD Dr. Solveig Franziska Bucher (SIP, FSU, iDiv) is an ecologist by training and an expert in ecophysiological and phenological adaptations of plants to climate change. Her research examines phenological observations using different methodologies from herbaria to remote sensing with a focus on frost resistance. She received funding from the DFG and Carl Zeiss Foundation and publishes in high-ranking journals (52 publications, h-index 17). She is the speaker of the PopBio chapter of the Ecological Society of Germany, Austria and Switzerland.
Dr. Nuno Carvalhais (MPI-BGC) leads the Model-Data Integration Group at MPI-BGC since 2012, and is an Invited Researcher at the New University of Lisbon. His research interests focus on the dynamics of terrestrial biogeochemical cycles, particularly the improvement of ecosystem modeling through data assimilation and inverse optimization, and on the introduction of DL and hybrid modeling in modeling terrestrial ecosystem processes. Carvalhais has visited Boston University and NASA Goddard Space Flight Center, and has held several international (ESA, EU FP7, H2020) and nationally funded projects. His outstanding publication record (h-index 52, >100 publications, >18k citations) includes contributions to Nature and Science.
Prof. Dr. Joachim Denzler (FSU) is a full professor and head of the Computer Vision group at FSU. His group (particularly Dr. Maha Shadaydeh and Dr. Aishwarya Venkataramanan) focuses on the analysis of sensor data, especially image and videodata, and the development of lifelong learning methods, uncertainty quantification, active learning and anomaly detection. The explainability of black-box models, knowledge integration into ML techniques, uncertainty quantification for model’s predictions and the detection and use of causal relationships have become core areas of the group’s research in recent years. The group contributes to major computer vision and ML journals and conferences and receives competitive external funding (EU, BMBF, DFG), often in collaboration with partners from other disciplines, including several GENAI-X PIs.
Prof. Dr. Joachim Giesen (FSU) was trained in algorithms and data structures, especially in geometric algorithms. His research is guided by the algorithm engineering paradigm of combining theoretical guarantees with efficient implementations. He coordinated the European FP7 FET-Open project Computational Geometric Learning, focusing on efficient algorithms for geometric and topological data analysis. His current research interests include algorithms and data structures for probabilistic modeling. He served as the director of the Institute for Computer Science (2013-2016), and as the Dean of the Faculty of Mathematics and Computer Science (2019-2023).
Prof. Dr. Michael Habeck (JUH, FSU) is a full professor of Microscopic Image Analysis at JUH. He is a former Emmy Noether fellow (2009-2014) and Carl-Zeiss-Stiftungsprofessor (since 2019). Trained as a physicist, Prof. Habeck is an internationally recognized expert in Bayesian statistics, probabilistic ML and image analysis with a particular focus on applications in structural biology. He has participated in two CRCs funded by the DFG, and has received funding from Baden-Württemberg- Stiftung, Carl Zeiss Foundation, DFG and the Max Planck Society. His publications have been cited > 6000 times (h-index 33).
Dr. Shijie Jiang (MPI-BGC) is an early-career researcher specializing in interactions among climate, water, and ecosystems under changing conditions. His work integrates data and domain knowledge with hybrid and explainable ML methods to advance understanding in these areas. Since his Ph.D. at the National University of Singapore, he has been focusing on addressing challenges in modeling and understanding hydrological cycles and extremes using AI approaches. He has published in Science Advances and leading hydrological journals, with several papers recognized as ESI Highly Cited. He has served as a convener for EGU/AGU sessions on ML in hydrological sciences since 2022.
Prof. Dr.-Ing. Kai Lawonn’s (FSU) research is motivated by scenarios from medical education, treatment planning, intraoperative support, life sciences, and computer graphics. Having a mathematical background, Lawonn has also contributed to important technical aspects of high-performance GPU algorithm development. His research ranges from analyzing an aneurysm to image triangulation in art to supporting architectural preservation. With his experience, he is ideally suited to work with a wide range of disciplines. In 2021 Lawonn received the DFG’s Heinz Maier-Leibnitz Prize.
Prof. Dr. Markus Reichstein (MPI-BGC, FSU) is a world-leading researcher in datadriven Earth system science and was awarded Germany’s most prestigious science award, the Leibniz Prize in 2020. He received the Max Planck Research Prize of the Alexander von Humboldt Foundation, the Piers Sellers mid-career award of the American Geophysical Union. Reichstein is recognized as a highly cited researcher, with >90k citations of his >200 publications (h-index >100). He has been IPCC lead author, and coordinated several international projects.
Prof. Dr. Christine Römermann (FSU, SIP, iDiv) leads the Plant Biodiversity Group at FSU and is director of the SIP; she is affiliated with the German Centre for Integrative Biodiversity Research (iDiv) Halle-Jena-Leipzig and vice president of the Ecological Society of Germany, Austria and Switzerland. With her expertise in functional ecology and phenology, she coordinates the international PhenObs network. Previous work includes the cooperation with scientists from computer vision developing AI methodsto automatically extract plant coverage and plant phenology from images. In general, she is interested in the effects of climate and land-use change on biodiversity and ecosystem functioning using novel methods and interdisciplinary approaches.
Dr. Alexander J. Winkler (MPI-BGC) is an early-career research group leader at the MPI for Biogeochemistry, heading the Atmosphere-Biosphere Coupling, Climate and Causality group (ABC3). A climate scientist by training, he holds a PhD in Earth system modeling with the highest distinction (summa cum laude) from the University of Hamburg / MPI for Meteorology and collaboration with Boston University, USA. His group operates at the intersection of mechanistic and AI-driven modeling, focusing on causal relationships and biosphere-atmosphere feedbacks. He received a Humboldt fellowship and published as lead author of an international team of scientists in outstanding journals (Nature Climate Change, Nature Communications).
Friedrich Schiller University Jena (FSU)
Institute of Geography, Geographic Information Science Group Jena https://www.chemgeo.uni-jena.de/en/30778/giscience
Institute of Computer Science, Computer Vision Group Jena www.inf-cv.uni-jena.de
Institute of Computer Science, Theoretical Computer Science II Group https://www.ti2.uni-jena.de/
Institute of Computer Science,Visualization and Explorative Data Analysis Group https://www.vis.uni-jena.de/
Institute of Ecology & Evolution https://www.plantbiodiv.uni-jena.de/en/
Jena University Hospital (JUH)
Microscopic Image Analysis Group https://microscopic-image-analysis.github.io/
Max Planck Institute for Biogeochemistry (MPI-BGC)
Department of Biogeochemical Integration https://www.bgc-jena.mpg.de/bgi
Senckenberg Institute for Plant Form and Function (SIP)
https://www.senckenberg.de/en/institutes/senckenberg-institute-for-plant-form-and-function-jena-sip
Advisory Board
The project is funded by the Carl Zeiss Foundation (CZS) within the call “CZS Breakthroughs – AI and the Environment.” This program supports innovative university research projects in the field of artificial intelligence, with a particular focus on developing new AI methods for communication and interaction with the environment. The aim is to achieve a deeper understanding of environmental processes by applying computational approaches to fundamental natural phenomena and leveraging existing environmental data. Projects in this program explore new paradigms for understanding environmental systems, design and implement simulations, and develop, train, or adapt foundational models. Possible applications include detecting weather anomalies, creating early warning systems for extreme weather events, improving climate projections, or advancing forest and water protection. The initiative encourages interdisciplinary collaboration between computer science and the natural sciences—especially in the fields of geosciences, physics, and chemistry—as well as participation from researchers in agricultural and forest sciences.
Connection to the ELLIS Unit Jena
The GENAI-X project originated from the ELLIS Unit Jena, reflecting its strong foundation in AI and environmental research. It aims to foster interdisciplinary collaboration and establish the basis for high-impact, integrative follow-up projects centered around this hub within the European Laboratory for Learning and Intelligent Systems (ELLIS) — a pan-European network of excellence founded in 2018 to advance fundamental research, technological innovation, and societal benefit.
A core strategic goal of GENAI-X is to further strengthen the ELLIS Unit Jena as a leading interdisciplinary research center at the forefront of AI-driven environmental science.
Project Website
Coordinator
Bettina Böhm
Uni Jena, Department of Geography, Leutragraben 1, 07743 Jena, Germany
Web: https://www.chemgeo.uni-jena.de/en/30789/team