[Spatio-temporal Evolution of PM Concentration During 2000-2019 in China].

An ensemble estimation model of PM concentration was proposed on the basis of extreme gradient boosting, gradient boosting, random forest model, and stacking model fusion technology. Measured PM data, MERRA-2 AOD and PM reanalysis data, meteorological parameters, and night light data sets were used. On this basis, the spatiotemporal evolution features of PM concentration in China during 2000-2019 were analyzed at monthly, seasonal, and annual temporal scales.

[PM Concentration Influencing Factors in China Based on the Random Forest Model].

In this paper, aerosol optical depth (AOD), elevation (DEM), annual precipitation (PRE), annual average temperature (TEM), annual average wind speed (WS), population density (POP), gross domestic product density (GDP), and normalized difference vegetation index (NDVI) were selected as factors influencing PM concentration. The random forest model, order of feature importance, and partial dependency plots were applied to investigate these factors and their regional differences in PM spatial pattern. The results showed that:① The random forest model was more accurate than multiple regression, generalized additive, and back propagation neural network models in estimating PM concentration, which can be applied to quantifying PM influencing factors.