A machine learning model for predicting PM2.5 and nitrate concentrations based on long-term water-soluble inorganic salts datasets at a road site station

In this study, long-term variations in the concentrations of PM2.5, water-soluble inorganic salts (WIS), and gaseous precursors measured by a roadside air quality monitoring station were investigated from 2017 to February 2021 to examine the formation mechanism of secondary inorganic PM2.5. A new machine learning model using WIS data as input variables was further developed to predict PM2.5 and nitrate concentrations for source tracing and effective control strategy development. The results showed that a reduction in the NOx concentration under VOC-limited O3 formation regime could offset the consumption of OH and O3, causing an increase in secondary NO3- and PM2.5 formation during fall and winter seasons. A good agreement was obtained between the predicted and measured PM2.5 values, with R2, root mean square error (RMSE), and mean absolute error (MAE) values of 0.81, 6.81 μg/m3, and 5.10 μg/m3, respectively. The nitrate ([NO3-]) prediction model could predict ∼59% of the atmospheric nitrate concentration. The sensitivity analysis of the input variables in the present model further revealed that NO3- and VOC were two important pollutants dominating the variation trend of PM2.5. It is recommended that decision makers should focus more on the reduction of VOC and O3 to reduce secondary PM2.5 formation during winter in central Taiwan. Real-time measurements of the chemical composition of PM2.5, taken as the regulatory air quality monitoring items are needed in the future.