北京大学学报自然科学版 ›› 2022, Vol. 58 ›› Issue (3): 443-452.DOI: 10.13209/j.0479-8023.2022.032

上一篇    下一篇

利用葵花8号卫星资料反演中国东部地区地面PM2.5浓度

刘喆1,2, 赵威伦1, 田晓青1, 桑悦洋1, 屈永霖1, 任静静1, 李成才1,†   

  1. 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
  • 收稿日期:2021-04-11 修回日期:2021-05-12 出版日期:2022-05-20 发布日期:2022-05-20
  • 通讯作者: 李成才, E-mail: ccli(at)pku.edu.cn
  • 基金资助:
    国家重点研发计划(2016YFC0202004)和国家自然科学基金(42030607, 42075133)资助 

Retrieval of Ground PM2.5 Concentrations in Eastern China Using Data from Himawari-8 Satellite

LIU Zhe1,2, ZHAO Weilun1, TIAN Xiaoqing1, SANG Yueyang1, QU Yonglin1, REN Jingjing1, LI Chengcai1,†   

  1. 1. Department of Atmospheric and Oceanic Sciences, School of Physics, Peking University, Beijing 100871 2. 94926 PLA Troop, Wuxi 214000
  • Received:2021-04-11 Revised:2021-05-12 Online:2022-05-20 Published:2022-05-20
  • Contact: LI Chengcai, E-mail: ccli(at)pku.edu.cn

PDF

摘要：

为了得到中国东部地区大范围的地面PM2.5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PM2.5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PM2.5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20.11 μg/m3。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PM2.5格点数据, 利用该格点数据分析中国东部地区PM2.5浓度的季节变化和空间分布, 取得良好的效果。

关键词: 卫星遥感, 大气层顶反射率, PM2.5浓度, 机器学习

Abstract:

In order to retrieve the large-scale ground PM2.5 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 PM2.5 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 20.11 μg/m3 for hourly PM2.5 concentration inversion. The hourly satellite-meteorological grid data throughout the year of 2019 were input to the model, and the corresponding PM2.5 grid data for the eastern China obtained. Good results were achieved for the PM2.5 grid data after analyzing the seasonal variation and spatial distribution of PM2.5 concentration over eastern China.

Key words: satellite remote sensing, top-of-atmosphere reflectance, PM2.5 concentration, machine learning

版权所有 © 《北京大学学报（自然科学版）》编辑部
技术支持：北京玛格泰克科技发展有限公司