| With the accelerated urbanization,air pollution has become a serious problem affecting the sustainable development of China’s economy and society and the health of residents.By studying the characteristics and influencing factors of urban air pollution,corresponding policies and measures can be formulated to reduce air pollution,improve people’s quality of life,and provide scientific basis and decision support for policy makers.In this study,the AQI(Air Quality Index)index of air quality in prefecture-level cities and the spatial and temporal distribution characteristics of six major air pollutants PM2.5,PM10,SO2,NO2,CO,and O3 from 2015 to 2020 were studied in 336 prefecture-level cities in China.A machine learning-based random forest model was used for the causal analysis of the temporal variation characteristics of AQI in Chinese cities,and analysis of its spatial distribution characteristics based on the Ggeodetector model to explore its spatial effects.For the sudden new crown epidemic in 2020,the impact of epidemic prevention and control policies on Chinese air quality is analyzed by designing control and experimental groups to further reveal the impact mechanism of Chinese air quality.The main findings of this study are as follows:(1)The overall decrease in the concentration of the remaining air pollutants in Chinese cities from 2015 to 2020,with the decreasing trend of SO2>PM10>PM2.5>CO>NO2,while O3 is the only air pollutant with an increasing trend in concentration.The high value areas of air pollutants in China are mainly concentrated in inland areas such as Hebei Province,Shanxi Province and Kashgar in Xinjiang Uygur Autonomous Region,while the low value areas are mainly distributed in the southeast coastal areas such as Guangdong Province,Guangxi Zhuang Autonomous Region and Hainan Province.Temperature is the main influence factor affecting the spatial and temporal characteristics of the six air pollutants in Chinese cities.Except for North China and Northwest China,which are influenced by precipitation and population size,respectively,the main influencing factor for East China,Central China and South China is GDP,while temperature affects Northeast China and Southwest China.(2)From 2015 to 2020,the overall air pollution situation in Chinese cities improved,with AQI values improving by 50.28%.In terms of seasonal changes,Chinese cities have the best AQI condition in summer,the most polluted AQI condition in winter,and the middle in spring and autumn.From a global perspective,temperature is the main influencing factor on the temporal variation characteristics of AQI in Chinese cities.The analysis from the zonal perspective reveals that the temporal change characteristics of AQI in Northwest China are influenced by the population size,except for Northeast China and Southwest China,where AQI is influenced by temperature,while East China,South China,Central China and North China are influenced by GDP.(3)South China is the region with the best air quality condition in the country(annual average AQI value of 47.13),while North China(78.24)and Central China(76.42)are the worst from 2015 to 2020.There is a significant spatial autocorrelation of AQI values in China.Central and northern China are high-high aggregation areas,and low-low aggregation areas are mainly found in southern and southwestern China.The geodetector model analysis found that GDP,population size,precipitation and temperature are the main factors influencing the spatial variation of air quality in China,and the two-two interaction combination of these influencing factors has an enhanced effect on the interpretation of the spatial variation of AQI.(4)With the new crown epidemic in 2020 as the background,this study conducted a dual model analysis by setting the epidemic-hit areas as the experimental group and the epidemic-light areas as the control group.2019-2020 AQI improved by 8.23%overall,and PM10 was the air pollutant with the most significant decrease in concentration(-11.53%).The overall decreasing trend of atmospheric pollutant concentrations is:PM10>PM2.5>NO2>SO2>CO>O3.In the context of national implementation of prevention and control policies,thermal power generation and gasoline consumption are the main socioeconomic factors affecting the improvement of AQI,PM2.5 and PM10 pollutant concentrations by 5.37%,6.54%and 10.68%,respectively,in the epidemic-prone areas. |