中国PM2.5 1km空间分布数据集（2018-2020年）

目前，在各种大气污染物的模拟中，独立痕量气体的模拟受到关键遥感产品分辨率不足的制约，导致模拟可靠性不足。本研究将空间采样和参数卷积相结合，利用地面观测、遥感产品、气象数据、援助数据和随机 ID 优化 LightGBM。通过上述技术和大气污染物序列模拟，我们得到了 2015-2018 ...

Currently, in the simulation of various atmospheric pollutants, the simulation of independent trace gases is constrained by the insufficient resolution of key remote sensing products, leading to inadequate simulation reliability. This study combines spatial sampling and parameter convolution, and optimizes LightGBM using ground-based observations, remote sensing products, meteorological data, ancillary data and random IDs. Through the above technologies and sequential simulation of atmospheric pollutants, we obtained the data from 2015 to 2018 ...