No abstract

PM2.5, which refers to fine particles with an equivalent aerodynamic diameter of less than or equal to 2.5 µm, can not only affect air quality but also endanger public health. Nevertheless, the spatial distribution of PM2.5 is not well understood in data-poor regions where monitoring stations are scarce. Therefore, we constructed a random forest (RF) model and a bagging algorithm model based on ground-monitored PM2.5 data, aerosol optical depth (AOD) and meteorological data, and auxiliary geographical variables to accurately estimate the spatial distribution of PM2.5 concentrations in Xinjiang during 2015–2020 at a resolution of 1 km. Through 10-fold cross-validation (CV), the RF model and bagging algorithm model were verified and compared. The results showed the following: (1) The RF model achieved better model performance and thus can be used to estimate the PM2.5 concentration at a relatively high resolution. (2) The PM2.5 concentrations were high in southern Xinjiang and low in northern Xinjiang. The high values were concentrated mainly in the Tarim Basin, while most areas of northern Xinjiang maintained low PM2.5 levels year-round. (3) The PM2.5 values in Xinjiang showed significant seasonality, with the seasonally averaged concentrations decreasing as follows: winter (71.95 µg m−3) > spring (64.76 µg m−3) > autumn (46.01 µg m−3) > summer (43.40 µg m−3). Our model provides a way to monitor air quality in data-scarce places, thereby advancing efforts to achieve sustainable development in the future.

Knowledge of aerosol dynamics is essential to combating atmospheric aerosol pollution, and there is a growing interest in aerosol changes and their drivers. However, the effects of interactions between natural and anthropogenic drivers of aerosol are not well understood. Here, we analyse changes in aerosol optical depth (AOD) in Xinjiang, China using the multiangle implementation of atmospheric correction aerosol products over 2001–2019 and investigate the driving factors of aerosol dynamics using a random forest (RF) and a geographical detector. The results show the dominant AOD changes in the quasi‐period of 3.21 months, 7.86 months, 1.19 years, for seasonal, half‐year, and interannual variations of aerosols. The increasing and then decreasing nonlinear trends were observed in the interannual AOD variation during 19 years period. The importance ranking results of the two models indicated that meteorological factors dominated the spatial distribution of AOD in Xinjiang (72.73% for RF and 65.78% for the geographic detector), and that interactions between factors enhanced the explanatory power in AOD changes. In addition, the influence of anthropogenic factors on AOD was increasing in North Xinjiang, and the influence of precipitation and population on AOD was increasing in East Xinjiang. However, the influence of drivers on AOD in South Xinjiang was basically constant over time, showing the spatially heterogeneous relationship between AOD and drivers. This study emphasized the spatial heterogeneity and driving factors of small‐scale aerosols in arid regions and so can guide targeted air pollution prevention and control in local areas.

No abstract