Satellite-based prediction of daily SO₂ exposure across China using a high-quality random forest-spatiotemporal Kriging (RF-STK) model for health risk assessment

China has been suffered from the severe sulfur dioxide (SO₂) pollution in the past decades. The spatiotemporal estimation and health effect assessment of SO₂ using two-stage machine learning models have not been performed yet. In this study, a high-quality model named random forest coupled with spatiotemporal Kriging (RF-STK) model was developed to estimate the daily SO₂ concentration across the entire China from May 2014 to May 2015 based on the satellite data and geographic covariates. Compared with other statistical methods, the RF-STK model showed the better explanatory performance, with the 10-fold cross-validation R² = 0.62 (root-mean-square error (RMSE) = 10.36 μg/m³) for daily estimations. The annually mean population-weighted SO₂ concentration was estimated to be 30.49 ± 10.83 μg/m³ (mean ± standard deviation). The SO₂ levels displayed the remarkably seasonal variation with the peak in winter (47.27 ± 22.64 μg/m³), followed by ones in autumn (28.41 ± 10.41 μg/m³) and spring (25.92 ± 7.95 μg/m³), and in summer (21.33 ± 6.51 μg/m³). At the national scale, only 20.31% of the population lived in the safe regions (population-weighted SO₂ concentration < 20 μg/m³). The higher population-weighted SO₂ concentrations were mainly concentrated on some provinces of North China Plain (NCP) (e.g., Shanxi, Hebei, Shandong), followed by the provinces of Northeast China, and the lowest one in Hainan (8.31 ± 1.38 μg/m³). The mean all-cause mortalities due to excessive SO₂ exposure were estimated to be 131,957 cases, accounting for 0.009% of the whole Chinese population. Among all of the diseases, the mortalities per year were in the order of respiratory disease (RD) (11913 cases) > cardiovascular disease (CVD) (11386 cases) > chronic obstructive pulmonary disease (COPD) (8112 cases) > cerebrovascular disease (CEVD) (2188 cases). The statistical modelling of SO₂ at a national scale provided the valuable data for epidemiological research and air pollution prevention.