Contributions of various driving factors to air pollution events: Interpretability analysis from Machine learning perspective.

The air quality in China has been improved substantially, however fine particulate matter (PM) still remain at a high level in many areas. PM pollution is a complex process that is attributed to gaseous precursors, chemical, and meteorological factors. Quantifying the contribution of each variable to air pollution can facilitate the formulation of effective policies to precisely eliminate air pollution. In this study, we first used decision plot to map out the decision process of the Random Forest (RF) model for a single hourly data set and constructed a framework for analyzing the causes of air pollution using multiple interpretable methods. Permutation importance was used to qualitatively analyze the effect of each variable on PM concentrations. The sensitivity of secondary inorganic aerosols (SIA): SO, NO and NH to PM was verified by Partial dependence plot (PDP). Shapley Additive Explanation (Shapley) was used to quantify the contribution of drivers behind the ten air pollution events. The RF model can accurately predict PM concentrations, with determination coefficient (R) of 0.94, root mean square error (RMSE) and mean absolute error (MAE) of 9.4 μg/m and 5.7 μg/m, respectively. This study revealed that the order of sensitivity of SIA to PM was NH＞NO＞SO. Fossil fuel and biomass combustion may be contributing factors to air pollution events in Zibo in 2021 autumn-winter. NH contributed 19.9-65.4 μg/m among ten air pollution events (APs). K, NO, EC and OC were the other main drivers, contributing 8.7 ± 2.7 μg/m, 6.8 ± 7.5 μg/m, 3.6 ± 5.8 μg/m and 2.5 ± 2.0 μg/m, respectively. Lower temperature and higher humidity were vital factors that promoted the formation of NO. Our study may provide a methodological framework for precise air pollution management.