一个用于深度学习活动火灾分割的哨兵二号基准数据集：覆盖加利福尼亚州25起野火
A Sentinel-2 benchmark dataset for deep-learning active-fire segmentation across 25 California wildfires
- California High School（加州高中）
- University of California, Davis（加州大学戴维斯分校）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该文介绍了一个包含25起加州野火、2148对图像-掩膜对的哨兵二号活动火灾分割基准数据集，并提供参考代码，支持稀有类别分割和跨事件迁移研究。
AI中文摘要：
本文描述了一个开放图像数据集，用于开发和评估卫星影像中的活动火灾分割方法。该数据集包含来自加利福尼亚州25起野火的2,148对图像-掩膜对，采集时间跨度从2020年7月到2026年8月。每幅图像为512x512像素、三通道合成影像，由哨兵二号Level-2A波段B12、B11和B8A以20米空间采样生成。整个数据集采用固定的线性渲染。对应的掩膜区分背景、短波红外规则活动火灾和无效观测。掩膜由短波红外亮度和近红外对比度生成，随后进行受限邻域增长。发布内容包含芯片级元数据和一个按火灾事件划分的训练/验证/测试集，其中包含18场训练火灾、3场验证火灾和4场测试火灾。在图像对中，841对包含活动火灾标签；这些标签占所有网格单元的0.0766%。一个掩膜盲分析员审查覆盖233个测试芯片，并在芯片和连通组件级别对规则生成的标签提供独立评估。随数据附有参考训练和评估代码，包括一个基于ResNet-34的U-Net实现，并采用基于验证的检查点和阈值选择。归档的图像、掩膜、元数据和审查注释支持稀有类别分割、从算法标签中学习以及跨火灾事件的迁移研究。该版本化数据集已存放在Zenodo上，制备和重用软件维护在公共GitHub仓库中。
英文摘要：
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.
