{
  "abstract": "This article describes an open image dataset for active-fire segmentation in satellite imagery. It contains 2148 image-mask pairs from 25 California wildfires, acquired from 23 July 2020 to 21 August 2026. Each image is a 512 × 512-pixel, three-channel composite of Sentinel-2 Level-2A bands B12, B11 and B8A at 20 m sampling. The same linear rendering is applied to every image. Masks distinguish background, SWIR-rule active fire and invalid observations. They were generated from shortwave-infrared brightness and near-infrared contrast, followed by two steps of neighborhood growth. The release includes chip-level metadata and a partition with 18 training, three validation and four test wildfires. Each wildfire belongs to only one partition. Of the image pairs, 841 contain active-fire labels, which occupy 0.0766% of all grid cells. An analyst reviewed 233 test chips without seeing the rule masks. These annotations provide a separate assessment of label agreement at chip and connected-component levels. The accompanying code includes a ResNet-34 U-Net with checkpoint and probability-threshold selection on validation data. The images and masks provide a fixed input for comparing segmentation methods on wildfires excluded from training. Dataset version 1.0.0 is deposited on Zenodo; the preparation and training software is available on GitHub.",
  "abstract_shown": true,
  "affiliations": [
    "California High School, San Ramon, CA, 94583, USA",
    "Department of Biological and Agricultural Engineering, University of California, Davis, CA, 95616, USA; Corresponding author.",
    "Department of Biological and Agricultural Engineering, University of California, Davis, CA, 95616, USA"
  ],
  "article_type": "data paper",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Shreyan Mitra"
    },
    {
      "affs": [
        1
      ],
      "name": "Mohammadreza Narimani"
    },
    {
      "affs": [
        2
      ],
      "name": "Parastoo Farajpoor"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/faj1fxbfhxfaq.bib",
  "cited_by": 0,
  "doi": "10.1016/j.dib.2026.113357",
  "fulltext_url": "http://www.sciencedirect.com/science/article/pii/S2352340926009030",
  "id": "faj1fxbfhxfaq",
  "issns": [
    "2352-3409"
  ],
  "landing_url": "https://doi.org/10.1016/j.dib.2026.113357",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Data Article"
    ],
    [
      "lcc",
      "Q1-390"
    ],
    [
      "lcc",
      "R858-859.7"
    ],
    [
      "openalex",
      "2213|Fire Detection and Safety Systems"
    ]
  ],
  "openalex": "W7221974265",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13720251/pdf/?tool=EBI",
  "pmcid": "PMC13720251",
  "pmid": "42964565",
  "published": "2026-08-01",
  "publisher": "Elsevier",
  "ris": "https://research.draconitic.com/paper/faj1fxbfhxfaq.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T13:44:53Z",
      "native_id": "44773248977b48edbf1f98fda357978e",
      "source": "doaj",
      "url": "https://doi.org/10.1016/j.dib.2026.113357"
    },
    {
      "first_seen": "2026-10-31T12:21:45Z",
      "native_id": "PMC:PMC13720251",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13720251"
    },
    {
      "first_seen": "2026-11-03T12:21:10Z",
      "native_id": "PMC13720251",
      "source": "pmc",
      "url": "https://doi.org/10.1016/j.dib.2026.113357"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "lcc:R858-859.7",
      "subfield": "general"
    }
  ],
  "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": "peer-reviewed",
  "updated_at": "2026-11-03T12:21:10Z",
  "url": "https://research.draconitic.com/paper/faj1fxbfhxfaq",
  "venue": "Data in Brief",
  "versions": [
    {
      "doi": "10.48550/arxiv.2609.16199",
      "pid": "4wj0b51fc5b3b",
      "relation": "preprint",
      "title": "A Sentinel-2 benchmark dataset for deep-learning active-fire segmentation across 25 California wildfires, July 2020-August 2026",
      "venue": "arXiv"
    }
  ]
}