As climate variability intensifies and global freshwater demand increases, precise monitoring of agricultural water use and soil moisture has become essential for sustainable food systems. The convergence of Earth Observation (EO) technologies, expanding in-situ sensor networks, and rapidly advancing machine learning (ML) methods is transforming agricultural water monitoring from research-driven analysis into actionable operational tools.

This session invites contributions at the forefront of EO-driven and ML-enhanced approaches for assessing agricultural water dynamics across diverse climates and spatial scales. Topics of interest include satellite-based soil moisture retrieval and validation using missions such as SMAP, Sentinel, and Landsat; hybrid modeling and data assimilation combining physical and ML-based methods; monitoring evapotranspiration, irrigation, and water use; integration of EO, meteorological, and ground observations; real-time and Sub-Seasonal to Seasonal (S2S) forecasting; applied case studies supporting climate resilience and food security; and research addressing scalability, uncertainty, and model interpretability.

• GC - Global Environmental Change