Ensemble machine learning models integrating geomorphometry and weather data to predict flood probability with high accuracy.
For the U.S. Army Corps of Engineers, we developed ensemble ML models combining slope, curvature, Stream Power Index (SPI), Topographic Wetness Index (TWI), Euclidean distance to river, geology, land use/cover, soil and surface runoff. Trained on 80% and validated on 20% holdout, the pipeline produced a flood susceptibility map reaching ~97% accuracy against observational inventory.