Predicting peak inundation depths with a physics informed machine learning model
Cheng‐Chun Lee, Lipai Huang, Federico Antolini, Matthew Garcia, Andrew Juan, Samuel D. Brody, Ali Mostafavi
During a flood, the best physics-based forecasts can be too slow to guide same-day decisions. This study asks whether a faster learner can preserve the useful part: knowing where water will rise, and why. What if flood prediction could keep the physical model’s realism, but deliver answers fast enough for emergency decisions? This paper tests that idea with MaxFloodCast, a machine-learning surrogate for peak inundation depth.