Transferable machine learning prediction of urban pluvial flood water depth using multi-resolution digital elevation models

Abstract Machine learning methods, particularly Random Forest (RF), present an effective solution for predicting urban pluvial flood water depth, especially in data-scarce regions where traditional hydrological and hydraulic observations are lacking. This study proposes a DEM-centric RF framework for predicting spatially continuous urban flood water depth across various precipitation return periods, emphasizing its robustness to terrain resolution degradation and spatial transferability. The model is trained and validated in Milan using a 1 m LiDAR-derived DEM and evaluated with a coarser 5 m EU-DEM to assess sensitivity to reduced resolution. Transferability is tested by applying the trained model to Cologne using independent 1 m LiDAR data. Model performance is assessed across five precipitation scenarios (5–100-year return periods) using absolute error metrics, tolerance thresholds, spatial diagnostics, and confidence-stratified analyses. Results show stable performance, with mean absolute errors below 0.30 m and over 58% of grid cells within ± 0.25 m of reference flood depths. Prediction errors are mainly found in hydraulically complex areas, while the majority of the urban domain shows well-constrained predictions. Confidence diagnostics indicate that high- and very-high-confidence predictions comply with tolerance thresholds under both DEM resolution degradation and spatial transfer. These findings suggest that relative terrain structure governs urban pluvial flooding patterns, enabling reliable flood depth predictions with medium-resolution DEMs. This framework offers a scalable tool for urban flood screening, hazard assessment, and climate adaptation planning in areas with limited data.