{
  "abstract": "Benchmark performance in flood mapping does not reliably predict how a model will behave in a new country. This paper tests that directly. Using the Sen1Floods11 dataset, we evaluate twelve model configurations—two architectures (Vanilla U-Net and ResNet34-encoder U-Net) across three sensing modalities (Sentinel-1 SAR, Sentinel-2 augmented with NDWI and MNDWI spectral indices, and multimodal Fusion)—under a standard random train-test split and a geographically disjoint country-level split where test countries are held out entirely from training. The gap between these two conditions is large and consistent. The worst case is Vanilla U-Net with Sentinel-2: IoU drops from 0.727 under random splitting to 0.464 under country splitting, a 36.2% relative loss. SAR degrades least. ResNet34+Fusion is the strongest country-level configuration, reaching IoU 0.555 and average precision 0.850. NDWI and MNDWI provide the clearest class separation of all input features (mean flood-to-background difference of 2.21 and 2.27 standard deviations respectively), and their inclusion improves country level IoU consistently across architectures. Somalia is harder than Paraguay in every configuration, with SAR-only models showing a 2.4× country ratio that narrows to 1.3× for ResNet34+Fusion. The key finding: the evaluation protocol matters as much as the model design.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "name": "Nitya D Dhagat"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7q5fa1ge23hps.bib",
  "cited_by": 0,
  "doi": "10.31223/x59z2m",
  "fulltext_url": null,
  "id": "7q5fa1ge23hps",
  "issns": [],
  "landing_url": "https://eartharxiv.org/repository/view/15258/",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/legalcode",
  "metadata_licence": null,
  "native_subjects": [
    [
      "bepress",
      "MNDWI"
    ],
    [
      "bepress",
      "NDWI"
    ],
    [
      "bepress",
      "Other Computer Sciences"
    ],
    [
      "bepress",
      "ResNet34"
    ],
    [
      "bepress",
      "SAR"
    ],
    [
      "bepress",
      "Sen1Floods11"
    ],
    [
      "bepress",
      "Sentinel-1"
    ],
    [
      "bepress",
      "Sentinel-2"
    ],
    [
      "bepress",
      "U Net"
    ],
    [
      "bepress",
      "cross-country evaluation"
    ],
    [
      "bepress",
      "domain generalization"
    ],
    [
      "bepress",
      "flood mapping"
    ],
    [
      "bepress",
      "semantic segmentation"
    ],
    [
      "openalex",
      "2306|Flood Risk Assessment and Management"
    ]
  ],
  "openalex": "W7214453424",
  "pdf_url": "https://eartharxiv.org/repository/object/15258/download/26456/",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/7q5fa1ge23hps.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:39Z",
      "native_id": "15258",
      "source": "eartharxiv",
      "url": "https://eartharxiv.org/repository/view/15258/"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "openalex:2306|Flood Risk Assessment and Management",
      "subfield": "climate"
    }
  ],
  "title": "Evaluating Cross-Country Generalization of Deep Learning-Based Flood Mapping Using Sentinel-1 SAR and Sentinel-2 Imagery",
  "title_text": "Evaluating Cross-Country Generalization of Deep Learning-Based Flood Mapping Using Sentinel-1 SAR and Sentinel-2 Imagery",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:39Z",
  "url": "https://research.draconitic.com/paper/7q5fa1ge23hps",
  "venue": "EarthArXiv",
  "versions": []
}