青藏高原30米分辨率火烧迹地产品（2023）

1）数据内容：本数据集包含2023年青藏高原地区30米分辨率火烧迹地产品。2）数据来源及加工方法：利用时间序列Landsat卫星数据，选择火烧迹地敏感光谱参量，包括各波段（蓝、绿、红、近红外、短波红外1和短波红外2波段）地表反射率和NRB、NBR2、 BAI、MIRBI、NDVI、GEMI、SAVI和NDMI光谱指数，构建火烧迹地和非火烧迹地样本库，利用机器学习算法（随机森林模型）研发并生产30米分辨率火烧迹地产品；3）数据质量描述：产品总体精度在90%以上。4) 数据应用成果及前景：该数据集可为火灾监测、碳排放研究、生态环境监测、全球变化研究等相关领域的研究和应用提供数据产品支撑。

1) Data Content: This dataset contains 30-meter resolution burned area products over the Qinghai-Tibet Plateau in 2023. 2) Data Source and Processing Method: Time-series Landsat satellite data were utilized, and spectral parameters sensitive to burned areas were selected, including surface reflectance of each band (blue, green, red, near-infrared, shortwave infrared 1 and shortwave infrared 2 bands) and spectral indices such as NRB, NBR2, BAI, MIRBI, NDVI, GEMI, SAVI and NDMI. A sample library of burned and non-burned areas was constructed, and a 30-meter resolution burned area product was developed and produced using a machine learning algorithm (Random Forest model). 3) Data Quality Description: The overall accuracy of the product exceeds 90%. 4) Data Application Achievements and Prospects: This dataset can provide data product support for research and applications in fields such as fire monitoring, carbon emission research, ecological environment monitoring and global change research.

搜集汇总

背景与挑战

背景概述

该数据集是2023年青藏高原地区的30米分辨率火烧迹地产品，基于Landsat卫星数据，利用多种光谱参量和随机森林模型生成，总体精度超过90%。它适用于火灾监测、碳排放研究和生态环境监测等领域，以开放获取方式共享，数据大小为38.31 MB。