Post-process correction improves the accuracy of satellite PM2.5 retrievals

Abstract

Abstract. Estimates of PM_2.5 levels are crucial for monitoring air quality and studying the epidemiological impact of air quality on the population. Currently, the most precise measurements of PM_2.5 are obtained from ground stations, resulting in limited spatial coverage. In this study, we consider satellite-based PM_2.5 retrieval, which involves conversion of high-resolution satellite retrieval of Aerosol Optical Depth (AOD) into high-resolution PM_2.5 retrieval. To improve the accuracy of the AOD to PM_2.5 conversion, we employ the machine learning based post-process correction to correct the AOD-to-PM conversion ratio derived from Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2) reanalysis model data. The post-process correction approach utilizes a fusion and downscaling of satellite observation and retrieval data, MERRA-2 reanalysis data, various high resolution geographical indicators, meteorological data and ground station observations for learning a predictor for the approximation error in the AOD to PM_2.5 conversion ratio. The corrected conversion ratio is then applied to estimate PM_2.5 levels given the high-resolution satellite AOD retrieval data derived from Sentinel-3 observations. Our model produces PM_2.5 estimates with a spatial resolution of 100 meters at satellite overpass times. Additionally, we have incorporated an ensemble of neural networks to provide error envelopes for machine learning related uncertainty in the PM_2.5 estimates.