一个利用遥感影像时间序列绘制巴西塞拉多烧毁区域的多时相数据集
A multi-temporal dataset for mapping burned areas in the Brazilian Cerrado using time series of remote sensing imagery
浏览论文内容
中文总结 AI 辅助
本文提出一个基于CBERS和AMAZONIA卫星WFI传感器影像的多时相数据集，用于绘制巴西塞拉多烧毁区域，并通过随机森林分类验证了其有效性，显示出较高的IoU和与MCD64A1产品可比的结果。
中文摘要 AI 辅助
本文介绍了一个从卫星图像中提取的多时相表格数据集，用于绘制巴西戈亚斯州查帕达-多斯-维阿代罗斯国家公园的烧毁区域，覆盖2020年至2022年。该数据集包含来自CBERS-4A、CBERS-4和AMAZONIA-1卫星上WFI传感器的蓝、绿、红和近红外波段，以及BAI、EVI、GEMI、NDVI和NDWI光谱指数，并按规则网格组织。我们应用随机森林分类器，基于标记为完全烧毁、部分烧毁和未烧毁的样本开发和验证模型。测试了两种分类方法：一种将烧毁和非烧毁区域合并为二分类，另一种区分完全烧毁（TB）、部分烧毁（PB）和未烧毁（NB）三类。七种验证方法评估了不同的分类后组合，重点关注准确率、精确率、召回率和交并比（IoU）指标。结果表明，当TB、PB和NB作为单独类别，且TB被重新分类为烧毁区域（BA）而PB和NB被归为非烧毁时，IoU更高。将该方法的年度结果与MCD64A1产品进行比较，BA类别的遗漏误差在2020年为22%，2021年为28%，2022年为59%，而误报误差分别为46%、43%和46%。该研究强调了WFI传感器在无需星间光谱校准的情况下绘制烧毁区域的实用性，并建议进一步探索其他机器学习算法以评估该数据集的潜力和局限性。
英文摘要
This paper introduces a multi-temporal tabular dataset derived from satellite images to map burned areas in the Chapada dos Veadeiros National Park, in Goiás, Brazil, covering the years 2020 to 2022. The dataset contains blue, green, red, and near-infrared bands, as well as the BAI, EVI, GEMI, NDVI, and NDWI spectral indices from the WFI sensor on the CBERS-4A, CBERS-4, and AMAZONIA-1 satellites, organized into a regular grid. We applied the Random Forest classifier to develop and validate models based on samples labeled as totally burned, partially burned, and non-burned. Two classification approaches were tested: one combining burned and non-burned areas into binary classes and another distinguishing between totally burned (TB), partially burned (PB), and non-burned (NB) classes. Seven validation approaches assessed different post-classification combinations, focusing on accuracy, precision, recall, and intersection over union (IoU) metrics. Results showed higher IoU when TB, PB, and NB were used as individual classes and TB was reclassified as burned area (BA) while PB and NB were grouped as non-burned. Comparing the annual results of this approach to the MCD64A1 product, the errors of omission for the BA class were 22% in 2020, 28% in 2021 and 59% in 2022, while the errors of commission were 46%, 43% and 46%, respectively. The study highlights the utility of the WFI sensor for burned area mapping without inter-satellite spectral calibration and suggests further exploration with other machine learning algorithms to evaluate the dataset potential and limitations.
发表机构
- National Institute for Space Research (INPE)（国家空间研究所）
机构由 AI 辅助整理，请以论文原文为准。
