Fine particulate matter with an aerodynamic diameter less than 2.5 μm (PM2.5) is one of the major air pollutants risks to human health worldwide. Satellite-based aerosol optical depth (AOD) products are an effective metric for acquiring PM2.5 information, featuring broad coverage and high resolution, which compensate for the sparse and uneven distribution of existing monitoring stations. In this study, a gradient boosting decision tree (GBDT) model for estimating ground PM2.5 concentration directly from AOD products across China in 2017, integrating human activities and various natural variables was proposed. The GBDT model performed well in estimating temporal variability and spatial contrasts in daily PM2.5 concentrations, with relatively high fitted model (10-fold cross-validation) coefficients of determination of 0.98 (0.81), low root mean square errors of 3.82 (11.57) μg/m3, and mean absolute error of 1.44 (7.45) μg/m3. Seasonal examinations revealed that summer had the cleanest air with the highest estimation accuracies, whereas winter had the most polluted air with the lowest estimation accuracies. The model successfully captured the PM2.5 distribution pattern across China in 2017, showing high levels in southwest Xinjiang, the North China Plain, and the Sichuan Basin, especially in winter. Compared with other models, the GBDT model showed the highest performance in the estimation of PM2.5 with a 3-km resolution. This algorithm can be adopted to improve the accuracy of PM2.5 estimation with higher spatial resolution, especially in summer. In general, this study provided a potential method of improving the accuracy of satellite-based ground PM2.5 estimation.
Keywords: Aerosol optical depth; Air pollution; MODIS; Machine learning; Particulate matter.
Copyright © 2020 Elsevier Ltd. All rights reserved.