利用葵花8号卫星资料反演中国东部地区地面PM2.5浓度  

Retrieval of Ground PM_(2.5) Concentrations in Eastern China Using Data from Himawari-8 Satellite

作　　者：刘喆[1,2] 赵威伦 田晓青 桑悦洋 屈永霖 任静静 李成才 LIU Zhe;ZHAO Weilun;TIAN Xiaoqing;SANG Yueyang;QU Yonglin;REN Jingjing;LI Chengcai(Department of Atmospheric and Oceanic Sciences,School of Physics,Peking University,Beijing 100871;94926 PLA Troop,Wuxi 214000)

机构地区：[1]北京大学物理学院大气与海洋科学系,北京100871 [2]94926部队,无锡214000

出　　处：《北京大学学报（自然科学版）》2022年第3期443-452,共10页Acta Scientiarum Naturalium Universitatis Pekinensis

基　　金：国家重点研发计划(2016YFC0202004);国家自然科学基金(42030607,42075133)资助。

摘　　要：为了得到中国东部地区大范围的地面PM_(2.5)浓度分布,用机器学习方法建立一个模型,用2019年葵花8号静止卫星大气顶层反射率数据和欧洲中心气象资料作为输入数据,地面PM_(2.5)浓度作为输出数据。验证结果表明,在不同时间尺度下,该模型对中国东部地区均有较高的精度。对于小时PM_(2.5)的浓度反演,该模型的十折交叉验证的相关系数为0.82,均方根误差为20.11μg/m^(3)。将2019全年卫星‒气象格点数据放入模型,得到中国东部地区全年逐小时的PM_(2.5)格点数据,利用该格点数据分析中国东部地区PM_(2.5)浓度的季节变化和空间分布,取得良好的效果。In order to retrieve the large-scale ground PM_(2.5) concentration distribution in eastern China,a model was built using machine learning.The model used the top-of-atmosphere reflectance data of the Himawari-8 geostationary satellite in 2019 and the meteorological data of the European Center as the input data,and the ground PM_(2.5) concentration was the output data.Validation results showed that the model had high accuracy on different time scales in eastern China.The ten-fold cross-validation of the model had a correlation coefficient of 0.82 and a root-mean-square error of 20.11μg/m3 for hourly PM_(2.5) concentration inversion.The hourly satellite-meteorologi-cal grid data throughout the year of 2019 were input to the model,and the corresponding PM_(2.5) grid data for the eastern China obtained.Good results were achieved for the PM_(2.5) grid data after analyzing the seasonal variation and spatial distribution of PM_(2.5) concentration over eastern China.

关 键 词：卫星遥感 大气层顶反射率 PM_(2.5)浓度 机器学习 

分 类 号：X87[环境科学与工程—环境工程]