Primary Convener:
Hyunglok Kim, GIST (Gwangju Institute of Science and Technology)

Convener:
Venkataraman (Venkat) Lakshmi, University of Virginia

Early Career Convener:
Ehsan Jalilvand, NASA Goddard Space Flight Center

Chair:
ManhHung Le, Hydrological Sciences Laboratory, NASA Goddard Space Flight Centre
Kristen Whitney, NASA Goddard Space Flight Center

Hydrology is at the forefront of Earth system science, propelled by rapid advancements in satellite remote sensing, physically based modeling, and artificial intelligence. This session explores how the integration of observational data, advanced data assimilation techniques, and state-of-the-art machine learning—including physics-informed and differentiable models—is reshaping our ability to understand the terrestrial water cycle. We welcome contributions focused on: • Physics-informed machine learning, differentiable modeling, and hybrid approaches for simulating hydrologic processes • Integration of remote sensing with land surface and hydrologic models• Uncertainty quantification, spatiotemporal error modeling, and calibration/validation strategies • Hybrid AI–data assimilation (DA) frameworks that leverage deep learning to address the limitations of traditional DA methods, including bias, scalability, and non-Gaussian uncertainty • Detection and forecasting of hydrological extremes, including floods, droughts, and flash droughts This session brings together hydrologists, Earth scientists, and AI practitioners to share advances, address challenges, and foster collaboration toward global water sustainability.

Index Terms
1833 Hydroclimatology
1847 Modeling
1855 Remote sensing
1876 Water budgets

Cross-Listed:
A - Atmospheric Sciences
GC - Global Environmental Change

Neighborhoods:
3. Earth Covering