Ensemble intelligence for urban resilience: flood susceptibility modeling in Mumbai using advanced machine learning

Urban flooding is a significant issue in coastal megacity Mumbai, where flood susceptibility is exacerbated by rapid urbanization and intense monsoon rainfall. This study develops a high-resolution flood susceptibility map for the Mumbai Metropolitan Region (MMR), using four machine learning algorithms: Random Forest, Artificial Neural Network, XGBoost, and Gradient Boosting Machine. The models were trained and validated using historical flood occurrence points, with nine conditioning factors: elevation, slope, rainfall, land use and land cover, building density, proximity to coastlines, road networks, and blue space. Models were performed with high accuracy, achieving 0.93 for GBM and XGBoost, 0.92 for RF, and 0.89 for ANN, respectively. The ensemble flood map, created based on the mean of four ML models, revealed that 25.3% of MMR is classified as high or very high flood susceptibility, while 34.3% falls into the low-susceptibility category. SHapley Additive exPlanations (SHAP) analysis showed that elevation, rainfall, and proximity to roads were the most influential predictors. Spatial validation revealed excellent overlap with historical flooding hotspots at Kurla, Chembur, and Sion. These findings provide critical policy insights for integrating flood susceptibility mapping into urban planning frameworks, supporting data-driven resilience strategies and sustainable infrastructure development in rapidly growing coastal megacities, like Mumbai.[Figure: see text]