Explainable geospatial-artificial intelligence models for the estimation of PM 2.5 concentration variation during commuting rush hours in Taiwan

PM concentrations are higher during rush hours at background stations compared to the average concentration across these stations. Few studies have investigated PM concentration and its spatial distribution during rush hours using machine learning models. This study employs a geospatial-artificial intelligence (Geo-AI) prediction model to estimate the spatial and temporal variations of PM concentrations during morning and dusk rush hours in Taiwan. Mean hourly PM measurements were collected from 2006 to 2020, and aggregated into morning (7 a.m. to 9 a.m.) and dusk (4 p.m. to 6 p.m.) rush-hour mean concentrations. The Geo-AI prediction model was generated by integrating kriging interpolation, land-use regression, machine learning, and a stacking ensemble approach. A forward stepwise variable selection method based on the SHapley Additive exPlanations (SHAP) index was used to identify the most influential variables. The performance of the Geo-AI models for morning and dusk rush hours had accuracy scores of 0.95 and 0.93, respectively and these results were validated, indicating robust model performance. Spatially, PM concentrations were higher in southwestern Taiwan for morning rush hours, and suburban areas for dusk rush hours. Key predictors included kriged PM values, SO concentrations, forest density, and the distance to incinerators for both morning and dusk rush hours. These PM estimates for morning and dusk rush hours can support the development of alternative commuting routes with lower concentrations.