REAL-TIME AND SEAMLESS MONITORING OF GROUND-LEVEL PM 2.5 USING SATELLITE REMOTE SENSING
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 R 2 = 0.80, RMSE = 17.49 μg/m 3) for the estimation of PM 2.5. The missing data in satellite-derive PM 2.5 are accurately recovered, with R 2 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.