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 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.