A nonparametric approach to filling gaps in satellite-retrieved aerosol optical depth for estimating ambient PM2.5 levels

Abstract Satellite-retrieved aerosol optical depth (AOD) is commonly used to estimate ambient levels of fine particulate matter (PM 2.5 ), though it is important to mitigate the estimation bias of PM 2.5 due to gaps in satellite-retrieved AOD. A nonparametric approach with two random-forest submodels is proposed to estimate PM 2.5 levels by filling gaps in satellite-retrieved AOD. This novel approach was employed to estimate the spatiotemporal distribution of daily PM 2.5 levels during 2013–2015 in the Sichuan Basin of Southwest China, where the coverage rate of composite AOD retrieved by the Terra and Aqua satellites was only 11.7%. Based on the retrieved AOD and various covariates (including meteorological conditions and land use types), the first random-forest submodel (named AOD-submodel) was trained to fill the gaps in the AOD dataset, giving a cross-validation R 2 of 0.95. Subsequently, the second random-forest submodel (named PM 2.5 -submodel) was trained to estimate the PM 2.5 levels for unmonitored areas/days based on the gap-filled AOD, ground-monitored PM 2.5 levels, and the covariates, and achieved a cross-validation R 2 of 0.86. By comparing the complete and incomplete (i.e., without the days when AOD data were missing) estimates, we found that the monthly PM 2.5 levels could be overestimated by 34.6% if the PM 2.5 values coincident with AOD gaps were not considered. The newly developed approach is valuable for deriving the complete spatiotemporal distribution of daily PM 2.5 from incomplete remote-sensing data, which is essential for air quality management and human exposure assessment.