Machine learning surrogates for flash flood hazard mapping: CSI-optimized feature selection and spatial transferability
Year: 2026
Type: article
Abstract: Flood Hazard Mapping is constrained by the computational cost of high-resolution hydrodynamic simulation. This study evaluates three Machine Learning (ML) models – Random Forest (RF), eXtreme Gradient Boosting (XGB), and a Feed-Forward Neural Network – as surrogates, addressing two gaps: retrieval of deterministic flood hazard extents from probabilistic maps, and transferability to unseen catchments. Using a 5-metre FLOODOS 2D simulation of the 1,000-year flood in southeastern France, models were trained on the Argens basin and tested on the Gapeau basin. A performance-driven feature selection algorithm – a greedy forward search maximizing the Critical Success Index (CSI) reduced 21 to four factors: discharge, Height Above Nearest Drainage, Distance to Stream, and river slope. Within the training domain, the RF achieved CSI = 0.76 (AUROC = 0.99). During extrapolation, all models maintained AUROC = 0.96, but the CSI declined to ~0.61, with XGB most robust. Notably, high threshold-independent discrimination (AUROC) did not guarantee accurate retrieval of the deterministic flood extent (CSI). Sub-catchment analysis revealed a global–local paradox: aggregate CSI masks systematic failures in upstream tributaries. Covariate shift was the principal barrier to spatial generalization; although the transferability assessment remains preliminary and basin-specific, results point to hybrid physics-informed ML as promising for operational flash-flood hazard assessment.
Authors: Aman Arora, Pierre Nicolle, Olivier Payrastre
Institution: Université Gustave Eiffel
Language: English
Subfield: Global and Planetary Change
Field: Environmental Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,790
Funder: Campus France
OpenAlex ID: W7214951273