Flood Hazard Zonation Using 2D HEC-RAS and Explainable Machine Learning in Urban Watersheds

Abstract

Urban flooding has emerged as one of the most critical challenges in rapidly developing cities, driven by climate change, intense rainfall events, and increasing land-use pressures. Accurate flood hazard mapping is essential for informed urban planning and disaster risk reduction, yet traditional approaches often face limitations in capturing complex hydrodynamic processes and ensuring interpretability for decision-makers. This study presents an integrated methodology that combines two-dimensional HEC-RAS hydrodynamic modelling with explainable machine learning (XAI) techniques for flood hazard zonation in urban watersheds. The HEC-RAS model successfully simulated flood depths and flow velocities, validated against observed data with a strong correlation coefficient (R₂ = 0.92) and low error indices. Machine learning models were tested using rainfall intensity, land use, slope, and proximity to rivers as predictors, with Random Forest achieving the highest performance (91% accuracy). To address the ‘black-box’ limitation, Shapley Additive Explanations (SHAP) were applied, identifying rainfall intensity and river proximity as the most significant drivers of flood risk. An integrated hazard map was developed by combining hydrodynamic outputs with Random Forest predictions. Validation against historical flood records yielded an overall accuracy of 89% and a Kappa statistic of 0.84, confirming the robustness of the approach. Sensitivity and statistical analyses further highlighted the impacts of rainfall variability and land-use change on flood susceptibility. The findings demonstrate that integrating hydrodynamic modelling with explainable AI enhances the accuracy, interpretability, and practical utility of flood hazard mapping, offering a valuable framework for urban planners and policymakers in managing flood risks under dynamic climate and land-use scenarios.