Understanding the distribution and drivers of PM(2.5) concentrations in the Yangtze River Delta from 2015 to 2020 using Random Forest Regression

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.