Metraipolis › archive › dc_1d40adde1bd2

A Sentinel-2 benchmark dataset for deep-learning active-fire segmentation across 25 California wildfires — arXiv:2609.16199

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16199
License (as archived)
CC0-1.0
Archived
2026-10-15T22:17:59.788Z
SHA-256 of the archived text
1b3323b208849c7e81ce6061488172b4a34cfb9169fd68e12e8008632a10997b
Stable URL of this page
https://metraipolis.com/documento/dc_1d40adde1bd2

How to cite

A Sentinel-2 benchmark dataset for deep-learning active-fire segmentation across 25 California wildfires — arXiv:2609.16199 — arXiv (en), https://arxiv.org/abs/2609.16199 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1d40adde1bd2 (Metraipolis archive dc_1d40adde1bd2, sha256 1b3323b208849c7e81ce6061488172b4a34cfb9169fd68e12e8008632a10997b)
BibTeX
@misc{dc1d40adde1bd2,
  title = {A Sentinel-2 benchmark dataset for deep-learning active-fire segmentation across 25 California wildfires — arXiv:2609.16199},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16199},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1d40adde1bd2; sha256 1b3323b208849c7e81ce6061488172b4a34cfb9169fd68e12e8008632a10997b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16199. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: terra, clima ed energia (retro-catalogo arXiv: annunci del 2026-09-16 in physics.geo-ph).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Signal Processing (eess.SP); Geophysics (physics.geo-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.16199 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T22:03:05.295Z dalla pagina https://arxiv.org/catchup/physics.geo-ph/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).