ChinaHighPM1 (Version 1)

The high-resolution (1 km) and high-quality PM₁ data set in China (i.e., ChinaHighPM₁ data set) from 2014 to 2018 are generated for the first time. This data set is generated using a newly developed space-time extremely randomized trees (STET) model based on the newly released MODIS Collection 6 MAIAC 1-km AOD products, meteorological variables, emissions, and auxiliary data. The STET model can derive daily PM₁ concentrations with an average across-validation coefficient of determination of 0.77, a low root-mean-square error of 14.6 μg/m³, and a mean absolute error of 8.9 μg/m³. The STET model, incorporating the spatiotemporal information, shows superior performance in PM₁ estimates relative to previous studies. The ChinaHighPM₁ data set can be greatly useful for air pollution studies in medium- or small-scale areas. <strong>Note that this dataset is closed since a new version is published at </strong>10.5281/zenodo.3538555<strong>.</strong>全球首次构建了2014—2018年中国区域高分辨率（1千米）、高质量的PM₁数据集（即ChinaHighPM₁数据集）。本数据集依托最新发布的MODIS Collection 6 MAIAC 1千米气溶胶光学厚度（AOD）产品、气象要素、排放源数据及辅助数据，采用全新开发的时空极端随机树（STET）模型生成。该模型可反演逐日PM₁浓度，其交叉验证平均决定系数达0.77，均方根误差为14.6 μg/m³，平均绝对误差为8.9 μg/m³。融合时空信息的STET模型，相较于既往研究，在PM₁浓度估算方面展现出更优异的性能。ChinaHighPM₁数据集可广泛应用于中小尺度区域的大气污染研究。**请注意：本数据集已停止公开获取，新版本已发布于10.5281/zenodo.3538555**。