{
  "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 5metre 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 performancedriven 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.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "name": "Aman Arora"
    },
    {
      "name": "Pierre Nicolle"
    },
    {
      "name": "Olivier Payrastre"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/930vay22rtc3y.bib",
  "cited_by": 0,
  "doi": "10.1080/19475705.2026.2707816",
  "fulltext_url": null,
  "id": "930vay22rtc3y",
  "issns": [
    "1947-5705",
    "1947-5713"
  ],
  "landing_url": "https://hal.science/hal-05778088v1",
  "language": "en",
  "licence": "CC-BY-NC-4.0",
  "licence_label": "CC BY-NC 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "hal",
      "0.info"
    ],
    [
      "hal",
      "0.sdu"
    ],
    [
      "hal",
      "1.info.info-ai"
    ],
    [
      "hal",
      "1.sdu.stu"
    ],
    [
      "hal",
      "2.sdu.stu.hy"
    ],
    [
      "openalex",
      "2306|Flood Risk Assessment and Management"
    ]
  ],
  "openalex": "W7214951273",
  "pdf_url": "https://hal.science/hal-05778088/document",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-30",
  "publisher": "Taylor & Francis",
  "ris": "https://research.draconitic.com/paper/930vay22rtc3y.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:47Z",
      "native_id": "hal-05778088",
      "source": "hal",
      "url": "https://hal.science/hal-05778088v1"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "hal:2.sdu.stu.hy",
      "subfield": "hydrology-soils"
    }
  ],
  "title": "Machine learning surrogates for flash flood hazard mapping: CSI-optimized feature selection and spatial transferability",
  "title_text": "Machine learning surrogates for flash flood hazard mapping: CSI-optimized feature selection and spatial transferability",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:47Z",
  "url": "https://research.draconitic.com/paper/930vay22rtc3y",
  "venue": "Geomatics, Natural Hazards and Risk",
  "versions": []
}