Mapping nationwide concentrations of sulfate and nitrate in ambient PM2.5 in South Korea using machine learning with ground observation data

Abstract

Particulate matter (PM) is a major air pollutant in Northeast Asia, with frequent high PM episodes. To investigate the nationwide spatial distribution maps of PM 2.5 and secondary inorganic aerosols in South Korea, prediction models for mapping SO 4 2- and NO 3 - concentrations in PM 2.5 were developed using machine learning with groundbased observation data. Specifically, the random forest algorithm was used in this study to predict the SO 4 2- and NO 3 - concentrations at 548 air quality monitoring stations located within the representative radii of eight intensive air quality monitoring stations. The average concentrations of PM 2.5 , SO 4 2- , and NO 3 - across the entire nation were 17.2 +/- 2.8, 3.0 +/- 0.6, and 3.4 +/- 1.2 mu g/m 3 , respectively. The spatial distributions of SO 4 2- and NO 3 - concentrations in 2021 revealed elevated concentrations in both the western and central regions of South Korea. This result suggests that SO 4 2- concentrations were primarily influenced by industrial activities rather than vehicle emissions, whereas NO 3 - concentrations were more associated with vehicle emissions. During a high PM 2.5 event (November 19 - 21, 2021), the concentration of SO 4 2- was primarily influenced by SO X emissions from China, while the concentration of NO 3 - was affected by NO X emissions from both China and Korea. The methodology developed in this study can be used to explore the chemical characteristics of PM 2.5 with high spatiotemporal resolution. It can also provide valuable insights for the nationwide mitigation of secondary PM 2.5 pollution.