MaxFloodCast: Ensemble Machine Learning Model for Predicting Peak Inundation Depth And Decoding Influencing Features

TL;DR

MaxFloodCast is an interpretable ensemble machine learning model trained on hydrodynamic simulations that accurately predicts peak flood inundation depths, supporting emergency response and flood management with reduced computational time.

Contribution

The paper introduces MaxFloodCast, a novel ensemble machine learning model that provides accurate, interpretable flood inundation predictions with efficient computation, validated on real flood events.

Findings

Achieved an average R-squared of 0.949 and RMSE of 0.61 ft.

Validated against Hurricane Harvey and Storm Imelda.

Supports near-time floodplain management and emergency operations.

Abstract

Timely, accurate, and reliable information is essential for decision-makers, emergency managers, and infrastructure operators during flood events. This study demonstrates a proposed machine learning model, MaxFloodCast, trained on physics-based hydrodynamic simulations in Harris County, offers efficient and interpretable flood inundation depth predictions. Achieving an average R-squared of 0.949 and a Root Mean Square Error of 0.61 ft on unseen data, it proves reliable in forecasting peak flood inundation depths. Validated against Hurricane Harvey and Storm Imelda, MaxFloodCast shows the potential in supporting near-time floodplain management and emergency operations. The model's interpretability aids decision-makers in offering critical information to inform flood mitigation strategies, to prioritize areas with critical facilities and to examine how rainfall in other watersheds influences flood exposure in one area. The MaxFloodCast model enables accurate and interpretable inundation depth predictions while significantly reducing computational time, thereby supporting emergency response efforts and flood risk management more effectively.