REAL-TIME AND SEAMLESS MONITORING OF GROUND-LEVEL PM2.5 USING SATELLITE REMOTE SENSING

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences

Chengyue Zhang^1¹  Tongwen Li^1²  Qiangqiang Yuan^2,4³  Huanfeng Shen^1,4⁴ 

[1] School of Geodesy and Geomatics, Wuhan University, Wuhan, China^2;School of Resource and Environmental Sciences, Wuhan University, Wuhan, China^1;The Collaborative Innovation Center for Geospatial Technology, Wuhan, China^4;The State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China^3

关键词: PM2.5;    Satellite remote sensing;    Real-time;    Seamless;    Deep learning;    Spatio-temporal fusion;   

DOI  :  10.5194/isprs-annals-IV-3-143-2018

学科分类：地球科学(综合)

来源: Copernicus Publications

【 摘 要 】

Satellite remote sensing has been reported to be a promising approach for the monitoring of atmospheric PM_2.5. However, the satellite-based monitoring of ground-level PM_2.5 is still challenging. First, the previously used polar-orbiting satellite observations, which can be usually acquired only once per day, are hard to monitor PM_2.5 in real time. Second, many data gaps exist in satellitederived PM_2.5 due to the cloud contamination. In this paper, the hourly geostationary satellite (i.e., Harawari-8) observations were adopted for the real-time monitoring of PM_2.5 in a deep learning architecture. On this basis, the satellite-derived PM_2.5 in conjunction with ground PM_2.5 measurements are incorporated into a spatio-temporal fusion model to fill the data gaps. Using Wuhan Urban Agglomeration as an example, we have successfully derived the real-time and seamless PM_2.5 distributions. The results demonstrate that Harawari-8 satellite-based deep learning model achieves a satisfactory performance (out-of-sample cross-validation R² = 0.80, RMSE = 17.49 μg/m³) for the estimation of PM_2.5. The missing data in satellite-derive PM_2.5 are accurately recovered, with R² between recoveries and ground measurements of 0.75. Overall, this study has inherently provided an effective strategy for the realtime and seamless monitoring of ground-level PM_2.5

【 授权许可】

CC BY