Geospatial Foundation Model and Remote Sensing for Hydrologic Prediction Across the Terrestrial Water Cycle
Geospatial Foundation Model and Remote Sensing for Hydrologic Prediction Across the Terrestrial Water Cycle
Session ID#: 280895
Session Description:
Hydrology is shifting toward a paradigm where satellite remote sensing, physics-based modeling, and AI foundation models converge. This session explores the integration of multi-sensor observations with next-generation AI—including geospatial foundation models, physics-informed machine learning, and differentiable modeling—to advance terrestrial water cycle prediction across scales. We emphasize frameworks that unify observation and state space, improve data assimilation, and enable end-to-end Earth system prediction.
We welcome contributions on:
- Physics-informed and hybrid AI for process representation.
- EO foundation models coupling satellite data with climate models.
- Advanced data assimilation and AI-driven observation operators.
- Uncertainty quantification and spatiotemporal error characterization.
- Monitoring hydrological extremes and land-atmosphere interactions.
We encourage studies leveraging missions such as SMAP, SMOS, MetOp, SWOT, GRACE-FO, NISAR, CYGNSS, GPM, Landsat, VIIRS, and Sentinel, alongside commercial constellations. This session aims to bridge the hydrology, remote sensing, and AI communities to build seamlessly integrated learning systems for Earth system science.
Index Terms:
1843 Land/atmosphere interactions [HYDROLOGY]
1847 Modeling [HYDROLOGY]
1855 Remote sensing [HYDROLOGY]
1922 Forecasting [INFORMATICS]
Primary Convener: Hyunglok Kim, GIST Gwangju Institute of Science and Technology, Gwangju, Korea, Republic of (South)
Conveners: Kristen Marie Whitney1, Ehsan Jalilvand, PhD1 and Venkataraman (Venkat) Lakshmi2, (1)NASA Goddard Space Flight Center, Hydrological Sciences Laboratory, Greenbelt, United States(2)University of Virginia, Civil and Environmental Engineering, Charlottesville, United States
Student/Early Career Conveners: Mohammad Saeedi, University of Virginia, Civil and Environmental Engineering, Charlottesville, United States, Ziyue Zhu, University of Virginia, University of Virginia, Engineering Systems and Environment, Charlottesville, VA, United States, Gigi Pavur, U.S. Army Corps of Engineers, Geospatial Research Laboratory, -, United States, Sophia Bakar, University of Virginia, Charlottesville, United States and Mr. Aashutosh Aryal, University of Virginia, Civil and Environmental Engineering, Charlottesville, VA, United States
See more of: Hydrology