An explainable machine-learning framework for mapping municipal flood severity: a case study in the Valencian community

Floods are among the most disruptive hazards in Mediterranean regions, and their severity is likely to intensify under climate change. Conventional flood assessments often emphasize either inundation extent or occurrence, overlooking how spatial footprint, duration, and intensity interact to shape impacts. To bridge this gap, this study integrates these three dimensions, derived from satellite, reanalysis, hydrological, and environmental datasets into a unified severity metric.

The modeling framework employs a machine learning approach, trained on a dataset comprising more than 7,500 Flood Severity Index (FSI) observations, derived from 14 documented flood events (2015–2024) detected using Sentinel-1 SAR imagery across 542 municipalities in the Valencian Community, Spain. The dataset was constructed by pairing each flood event with each municipality, so that each observation represents one municipality during one specific flood event. The output variable is the FSI, while input predictors were drawn from topographical, environmental, and hydrological data sources and were harmonized to municipal boundaries. Following preprocessing and multicollinearity screening, the refined dataset was normalized and partitioned into 70% for training and 30% for independent testing. Model performance was evaluated using cross-validation and standard error metrics.

A stacked ensemble combining Gradient Boosting and a multilayer perceptron achieved the best performance, outperforming Random Forest, SVR, and standalone neural networks. The model effectively captured nonlinear relationships, spatial heterogeneity, and the underlying structure of the observed data. It accurately predicted municipal FSI values, including statistically identified clusters of municipalities with exceptionally high FSI compared to others. Model explainability analyses showed that topography (elevation and slope), land use, and vegetation (NDVI) are the primary drivers of flood severity, with vegetated and permeable landscapes mitigating impacts by promoting water infiltration.

The calibrated model was applied to estimate future flood severity under various RCP (RCP2.6 and RCP8.5) scenarios. The projections reveal that most municipalities are expected to maintain their current severity class, while a smaller but notable subset is projected to experience an upward shift. Only a limited fraction shows indications of reduced severity. Overall, the results indicate a regional shift toward higher severity classes and highlight locations where climate-driven pressures on flood risk are likely to increase. These results demonstrate that herein developed machine-learning framework provide a decision-support tool for municipal authorities, enabling prioritization of investments in flood mitigation and climate adaptation.