openalexWater2026-07-25
Physics-Informed CNN-LSTM for Street-Scale Urban Flood Prediction: Reconciling Aggregate Accuracy and Street-Level Plausibility
Luc D’Costa, Yidi Wang, Jonathan L. Goodall, Rohan Chandra
Deep learning surrogate models trained with mean-squared-error loss produce statistically accurate but physically unconstrained flood predictions: water may flow uphill, appear spontaneously, or smooth over street-level corridors. In this work, a physics-informed training framewo…