Understanding the distribution and drivers of PM2.5 concentrations in the Yangtze River Delta from 2015 to 2020 using Random Forest Regression

Abstract

Understanding the drivers of PM 2.5 is critical for the establishment of PM 2.5 prediction models and the prevention and control of regional air pollution. In this study, the Yangtze River Delta is taken as the research object. Spatial cluster and outlier method was used to analyze the temporal and spatial distribution and variation of surface PM 2.5 in the Yangtze River Delta from 2015 to 2020, and Random Forest was utilized to analyze the drivers of PM 2.5 in this area. The results indicated that (1) based on the spatial cluster distribution of PM 2.5 , the northwest and north of Yangtze River Delta region were mostly highly concentrated and surrounded by high concentrations of PM 2.5 , while lowly concentrated and surrounded by low concentrations areas were distributed in the southern; (2) the relationship between PM 2.5 concentrations and drivers in the Yangtze River Delta was modeled well and the explanatory rate of drivers to PM 2.5 were more than 0.9; (3) temperature, precipitation, and wind speed were the main driving forces of PM 2.5 emission in the Yangtze River Delta. It should be noted that the repercussion of wildfire on PM 2.5 was gradually prominent. When formulating air pollution control measures, the local government normally considers the impact of weather and traffic conditions. In order to reduce PM 2.5 pollution caused by biomass combustion, the influence of wildfire should also be taken into account, especially in the fire season. Meanwhile, high leaf area was conducive to improving air quality, and the increasing green area will help reduce air pollutants. Supplementary information The online version contains supplementary material available at 10.1007/s10661-022-09934-5.

Influencing factors and trend prediction of PM2.5 concentration based on STRIPAT-Scenario analysis in Zhejiang Province, China

“…In 2020, approximately 1/3 of the 337 cities with prefecture-level and above PM 2.5 concentrations still fall below the national Class II standard, and regional heavy pollution weather occurs occasionally. Therefore, it is crucial to investigate the socioeconomic causes of PM 2.5 concentration and forecast the trajectory because it serves as a legally mandated indicator of economic and social growth in the 14th Five-Year Plan (Su et al, 2022 ; Yue et al, 2020 ).…”

“…Meanwhile, factors that include technological innovation progress, environmental regulation and pollution control funding have a positive ameliorating effect on PM 2.5 pollution (Chen et al, 2019 ; Xia et al, 2022 ; Xue et al, 2020 ). These studies have laid a solid foundation for deeper insight into the relationship between socioeconomic development and PM 2.5 and have provided a valuable scientific basis for regional environmental policy formulation (Su et al, 2022 ; Tao et al, 2020 ).…”

“…Recent years have seen steady advancement in computer technology, artificial intelligence and machine learning theory. Consequently, some data mining and computing tools have been widely employed to estimate PM 2.5 mass concentration, such as various neural network models (Biancofiore et al, 2017 ; Zhao et al, 2019 ) and random forest regression (Senthilkumar et al, 2022 ; Su et al, 2022 ).…”

Random Forest Estimation and Trend Analysis of PM2.5 Concentration over the Huaihai Economic Zone, China (2000–2020)

“…China's 337 cities experienced a total of 345 days of severe pollution and 1152 days of serious pollution in 2020, with PM 2.5 pollution accounting for 77.7% of days of serious pollution [5]. Due to the dispersion of air pollution from two neighboring regions (the Beijing-Tianjin-Hebei Region and the Yangtze River Delta Region (Figure 1a)), and severe air pollutant emissions of its own, the Huaihai Economic Zone has serious air pollution [6][7][8][9]. The air quality of the 10 cities in the Huaihai Economic Zone is lower than the national average level for the same period [10].…”

Break point identification and spatiotemporal dynamic evolution of air pollutants: An empirical study from Anhui province, east China

“…The studies that form the existing literature on air pollution have examined many different geographical areas, including YRD, the Pearl River Delta (PRD), the Beijing-Tianjin-Hebei region (BTH), individual cities, and the entire country (Zheng et al, 2009;Gong et al, 2021;Zhou et al, 2021;Deng et al, 2022;Sun et al, 2022). These studies have focused on temporal and spatial distributions (Zheng et al, 2009;Deng et al, 2022;Su et al, 2022;Zhang and Cheng, 2022), composition and source apportionment (Xue et al, 2019;Zhou et al, 2021;Xu et al, 2022), influencing factors and health effects (Geng et al, 2021;Zhao et al, 2022), and air quality and transport models (Sulaymon et al, 2021;Li et al, 2022;Qin et al, 2022), so as to reveal the distribution features, composition forms, transport characteristics, and health risks of air pollutants. The studies on inter-city joint prevention and collaborative governance of air pollutants have the most practical significance.…”