Characterizing statistical association patterns and local forecasting of PM_2.5-bound polycyclic aromatic hydrocarbon...

This study developed an integrated pollutant-meteorology-polycyclic aromatic hydrocarbons (PAHs) statistical framework using association rule mining and machine learning to characterize the hourly variability of PAHs bound to fine particulate matter (PM_2.5) in Nagoya, Japan. Association rules identified recurring pollutant-meteorology co-occurrence patterns linked to PAH accumulation, while machine learning models, evaluated via time-blocked cross-validation to avoid leakage from hourly autocorrelation, enabled short-term prediction. Ambient pollutants showed pronounced diurnal patterns, with black carbon and nitrogen oxides peaking during traffic rush hours and photochemical oxidants peaking in the afternoon. Reduced wind speed was the most consistent statistical condition associated with elevated PAH levels, whereas pressure, humidity, and temperature were associated with atmospheric conditions favorable to pollutant accumulation, such as reduced dispersion. Rule structures further revealed shared meteorological patterns and compound-specific association patterns across PAH species. Among the predictive models, eXtreme Gradient Boosting and Random Forest achieved the best performance for high-molecular-weight PAHs (R² = 0.81-0.93, RMSE = 0.02-0.11, MAE = 0.01-0.06), whereas Support Vector Regression and Multilayer Perceptron performed poorly. Pressure, temperature, and humidity dominated feature importance, consistent with the association rule findings. The health-risk assessment showed that benzo[a]pyrene (BaP) dominated carcinogenic toxicity, while estimated incremental lifetime cancer risk values for all population subgroups remained below the U.S. Environmental Protection Agency negligible-risk threshold. Because the identified associations reflect statistical covariation within a limited 10-day observation period, they should be interpreted as site-specific descriptors for local forecasting rather than as evidence of universal atmospheric mechanisms.