中国高分辨率高质量PM2.5数据集（2000-2023）

ChinaHighPM2.5数据集是中国高分辨率高质量近地表空气污染物数据集（ChinaHighAirPollutants, CHAP）中PM2.5数据集。该数据集利用人工智能技术，使用模式资料填补了卫星MODIS MAIAC AOD产品的空间缺失值，结合地基观测、大气再分析和排放清单等大数据生产得到2000年至今全国无缝隙地面PM2.5数据。数据十折交叉验证决定系数R2为0.92，均方根误差RMSE为10.76 µg/m3。主要范围为整个中国地区，空间分辨率为1 km，时间分辨率为日、月、年，单位为µg/m3。注意：该数据集持续更新，如需要更多数据，请发邮件联系作者（[e-mail]; [e-mail]）。 数据文件中包含NC转GeoTiff的四种代码（Python、Matlab、IDL和R语言）nc2geotiff codes。The ChinaHighPM2.5 dataset is the PM2.5 subset of the China High-resolution High-quality Near-surface Air Pollutant Dataset (ChinaHighAirPollutants, CHAP). This dataset leverages artificial intelligence technologies, uses model data to fill the spatial missing values of the satellite MODIS MAIAC AOD product, and combines big data sources such as ground-based observations, atmospheric reanalysis datasets, and emission inventories to produce seamless nationwide ground-level PM2.5 data from 2000 to the present. The 10-fold cross-validation coefficient of determination R2 of the dataset is 0.92, with a root mean square error (RMSE) of 10.76 µg/m³. The dataset covers the entire Chinese territory, with a spatial resolution of 1 km, temporal resolutions of daily, monthly, and annual, and the unit is µg/m³. Note: This dataset is continuously updated. If you need more data, please contact the authors via email at [e-mail]; [e-mail]. The data files include four sets of NC-to-GeoTiff conversion codes implemented in Python, Matlab, IDL, and R programming languages, referred to as nc2geotiff codes.

搜集汇总

背景与挑战

背景概述

该数据集是中国高分辨率高质量近地表PM2.5数据，覆盖2000年至2023年，利用人工智能技术融合多源大数据生产，提供全国无缝隙的日、月、年尺度数据。其特点是空间分辨率高达1公里，验证精度高（R2=0.92，RMSE=10.76 µg/m³），并以开放获取方式共享，适用于大气污染研究和政策分析。