High-Resolution Spatiotemporal Modeling for Ambient PM_2.5 Exposure Assessment in China from 2013 to 2019

Abstract

Exposure to fine particulate matter (PM_2.5) has become a major global health concern. Although modeling exposure to PM_2.5 has been examined in China, accurate long-term assessment of PM_2.5 exposure with high spatiotemporal resolution at the national scale is still challenging. We aimed to establish a hybrid spatiotemporal modeling framework for PM_2.5 in China that incorporated extensive predictor variables (satellite, chemical transport model, geographic, and meteorological data) and advanced machine learning methods to support long-term and short-term health studies. The modeling framework included three stages: (1) filling satellite aerosol optical depth (AOD) missing values; (2) modeling 1 km × 1 km daily PM_2.5 concentrations at a national scale using extensive covariates; and (3) downscaling daily PM_2.5 predictions to 100-m resolution at a city scale. We achieved good model performances with spatial cross-validation (CV) <i>R</i>² of 0.92 and temporal CV <i>R</i>² of 0.85 at the air quality sites across the country. We then estimated daily PM_2.5 concentrations in China from 2013 to 2019 at 1 km × 1 km grid cells. The downscaled predictions at 100 m resolution greatly improved the spatial variation of PM_2.5 concentrations at the city scale. The framework and data set generated in this study could be useful to PM_2.5 exposure assessment and epidemiological studies.