Water Resources Research Act Program

Details for Project ID TX-Dehghaninahrkhalaji-FY26

Leveraging satellites, gauge observations, and physics-informed AI for predicting streamflow extremes

Institute: Texas
Year Established: 2025 Start Date: 2026-01-01 End Date: 2026-12-31
Total Federal Funds: $10,000 Total Non-Federal Funds: $10,000

Principal Investigators: Adnan Dehghaninahrkhalaji

Project Summary: Effectively managing water resources in Texas, particularly during extreme floods and drought events, is crucial. This proposal aims to enhance streamflow predictions by integrating satellite-derived data, ground-based gauge observations, and novel physics-informed artificial intelligence (AI). By utilizing high-resolution Earth observation (EO) data, we can now monitor river widths and water surface elevations with unprecedented accuracy. However, effectively assimilating this data into hydrological models poses challenges due to its complexity and the sheer volume of information it provides. Our approach leverages cutting-edge neural operator AI models that are informed by the physical laws governing water flow, ensuring that our predictions are not only based on data patterns but also adhere to hydrological principles. This integration aims to develop a tool that can improve river discharge forecasts during floods and droughts, providing Texan communities and policymakers with more reliable information for water management and emergency preparedness.