Unveiling the source contributions of fine and coarse particulate matter using PM-bound metals and PMF-AI modeling

Abstract

Particle pollution is a critical global concern with significant implications for public health and the environment. Both fine (PM_2.5) and coarse (PM_2.5-10) particles exhibit diverse compositions and origins, leading to distinct health and environmental consequences. In this study, K-means clustering was employed to differentiate between local, regional, and long-range transport (LRT) sources, showing that LRT significantly increases PM_2.5-10 levels, leading to a more than 1.26-fold rise in its annual mean concentration. Using Positive Matrix Factorization (PMF) model, we identified five local and regional source of PM_2.5 and four in case of PM_2.5-10. Further, AutoML model explains up to 70 % and 71 % of the daily variance in PM_2.5 and PM_2.5-10, respectively. The complex relationship of these sources was explained using SHapley Additive ExPlanations (SHAP). Among the five major factors identified, SHAP analysis reveals that oil combustion (24 %), coal burning (18 %), and non-ferrous metal smelting/biomass burning (17 %) are the predominant contributors to PM_2.5. In contrast, ocean spray (28 %) is identified as a significant source of PM_2.5-10 pollution followed by oil, non-ferrous metal smelting/biomass burning (20 %) and traffic related emission (14 %). This study offers a novel and comprehensive methodology for identifying the distinct sources of fine and coarse particulate matter. It provides valuable insights that can inform future policies and regulations, particularly in regions facing challenges related to PM pollution.