{
  "abstract": "This article describes an open image dataset for developing and evaluating active-fire segmentation methods in satellite imagery. The dataset contains 2,148 image-mask pairs from 25 California wildfires, with acquisitions spanning July 2020 to August 2026. Each image is a 512x512-pixel, three-channel composite derived from Sentinel-2 Level-2A bands B12, B11 and B8A at 20 m spatial sampling. A fixed linear rendering is applied throughout the dataset. Corresponding masks distinguish background, SWIR-rule active fire and invalid observations. The masks were generated from shortwave-infrared brightness and near-infrared contrast, followed by constrained neighborhood growth. The release includes chip-level metadata and an incident-disjoint partition containing 18 training, three validation and four test fires. Among the image pairs, 841 contain active-fire labels; these labels occupy 0.0766% of all grid cells. A mask-blind analyst review covers 233 test chips and provides a separate assessment of the rule-generated labels at chip and connected-component levels. Reference training and evaluation code accompanies the data, including a ResNet-34 U-Net implementation with validation-based checkpoint and threshold selection. The archived images, masks, metadata and review annotations support research on rare-class segmentation, learning from algorithmic labels and transfer across fire incidents. The versioned dataset is deposited on Zenodo, with preparation and reuse software maintained in a public GitHub repository.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "Journal reference: Data in Brief, 69, 113357 (2026)",
  "arxiv": "2609.16199",
  "author_total": 3,
  "authors": [
    {
      "name": "Shreyan Mitra"
    },
    {
      "name": "Mohammadreza Narimani"
    },
    {
      "name": "Parastoo Farajpoor"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/4wj0b51fc5b3b.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.16199",
  "fulltext_url": null,
  "id": "4wj0b51fc5b3b",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.16199",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "eess.IV"
    ],
    [
      "arxiv",
      "eess.SP"
    ],
    [
      "arxiv",
      "physics.geo-ph"
    ],
    [
      "openalex",
      "2213|Fire Detection and Safety Systems"
    ]
  ],
  "openalex": "W7213426282",
  "pdf_url": "https://arxiv.org/pdf/2609.16199",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-24",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/4wj0b51fc5b3b.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:35:35Z",
      "native_id": "2609.16199",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.16199"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "arxiv:physics.geo-ph",
      "subfield": "geophysics"
    }
  ],
  "title": "A Sentinel-2 benchmark dataset for deep-learning active-fire segmentation across 25 California wildfires, July 2020-August 2026",
  "title_text": "A Sentinel-2 benchmark dataset for deep-learning active-fire segmentation across 25 California wildfires, July 2020-August 2026",
  "type": "preprint",
  "updated_at": "2026-10-30T12:35:35Z",
  "url": "https://research.draconitic.com/paper/4wj0b51fc5b3b",
  "venue": "arXiv",
  "versions": [
    {
      "doi": "10.1016/j.dib.2026.113357",
      "pid": "faj1fxbfhxfaq",
      "relation": "published-as",
      "title": "A Sentinel-2 benchmark dataset for deep-learning active-fire segmentation across 25 California wildfires, July 2020–August 2026",
      "venue": "Data in Brief"
    }
  ]
}