Abstract
This study presents the first-ever application of machine learning (ML)-based meteorological normalization and Shapley additive explanations (SHAP) analysis to quantify, separate, and understand the effect of meteorology on PM(2.5) over Greater Bangkok (GBK). Six ML models namely random forest (RF), adaptive boosting (ADB), gradient boosting (GB), extreme gradient boosting (XGB), light gradient boosting machine (LGBM), and cat boosting (CB) were used with meteorological factors, fire activity, land use, and socio-economic data as predictor variables. The LGBM outperformed other models achieving ρ = 0.9 (0.95), MBE = 0 (- 0.01), MAE = 5.5 (3.3) μg m(-3), and RMSE = 8.7 (4.9) μg m(-3) for hourly (daily) PM(2.5) prediction. LGBM was used for spatiotemporal PM(2.5) estimation, and meteorological normalization was applied to calculate PM(2.5_emis) (emission-related PM(2.5)) and PM(2.5_met) (meteorology-related PM(2.5)). Diurnal variation reveals higher PM(2.5) levels in the morning (08-10 LT) due to increased traffic emissions and thermal inversion and a decrease in PM(2.5) as the day progresses due to decreased emission and inversion dissipation. Monthly variation suggests higher PM(2.5) in winter (December and January) due to emissions and stagnant meteorological conditions. Negative PM(2.5_met) during November, March, and April values show meteorology improves air quality, while positive values from December to February indicate stagnant winter conditions worsen it. During winter, PM(2.5_emis) and PM(2.5) showed an increasing trend in 15.6% and 67.8% of the area while decreasing trends fell from 23.2 to 1.9%. In summer, the percentage of areas with an increasing trend rose from 18.7 to 34.6%, and decreasing areas fell from 12.6 to 6.5%. Increase in PM(2.5) despite decreasing emission over a larger area, indicating limited effectiveness of mitigation measures. Winter exhibits greater PM(2.5) variability due to episodic increases from changing meteorological conditions. In Bangkok and nearby areas, higher variability is mainly driven by meteorology, with more consistent emissions in Bangkok compared to rural areas affected by agricultural burning. PM(2.5) and PM(2.5_emis) showed stronger persistence in winter than in summer, with weaker effects in Bangkok. Hurst exponent averages were 0.75, 0.76, and 0.72 for PM(2.5) and 0.79, 0.8, and 0.73 for PM(2.5_emis) in dry, winter, and summer seasons, respectively. SHAP analysis suggested relative humidity, planetary boundary layer height, v wind, temperature, u wind, global radiation, and aerosol optical depth as the key variables affecting PM(2.5) with mean absolute SHAP values of 5.29, 4.79, 4.29, 3.68, 2.37, 2.22, and 2.03, respectively. Based on these findings, some policy recommendations have been proposed.