Two-stage model for estimating the spatiotemporal distribution of hourly PM1.0 concentrations over central and east China

Abstract Widespread and severe PM 1.0 (particulate matter ≤1.0 μm) pollution in China has a significant negative influence on human health. However, knowledge of the regional spatiotemporal distribution of PM 1.0 has been hindered by sparsely distributed PM 1.0 concentration data. In this work, a two-stage model (linear mixed effect–bagged tree model) was proposed for estimating hourly PM 1.0 pollution levels from July 2015 to June 2017 over central and east China by using Himawari-8 aerosol products and coincident geographic data, meteorology, and site-based PM 1.0 concentrations from ground monitoring network. The cross-validation for the developed model displayed R 2 and mean absolute error value of 0.80 and 9.3 μg/m 3 , respectively. Validation demonstrated that the model accurately estimated hourly PM 1.0 concentrations with high R 2 of 0.63–0.85 and low bias of 8.7–10.1 μg/m 3 . The estimated PM 1.0 concentrations on daily scale showed peaks with PM 1.0 of 36.9 ± 8.4 μg/m 3 at rush hours during daytime. Seasonal distribution displayed that summer was cleanest with an average PM 1.0 of 20.9 ± 6.8 μg/m 3 and winter was the most polluted season with an average PM 1.0 of 45.6 ± 16.8 μg/m 3 . These results indicated that the proposed satellite-based model can estimate reliable spatial distribution of PM 1.0 concentrations over a large-scale region.