Explainable Machine Learning for Source-Resolved PM2.5 Oxidative Potential: Implications for Global Mortality Burden

Fine particulate matter (PM_2.5) oxidative potential (OP) is an important indicator of health risk, and it varies substantially across different emission sources. Although concentration–response functions (CRFs) exist that relate PM_2.5 mass to its OP, the absence of source-specific OP  CRFs has limited accurate global risk assessment.

In this study, we developed global source-resolved OP CRFs by combining machine learning, statistical modeling, and extensive datasets on PM_2.5 concentrations, source apportionment across 50 countries, and more than 10,000 OP measurements from 29 countries. Our results show clear differences in the intrinsic OP per unit mass for major emission sectors, with the following ranking: energy > transportation > industry > agriculture and residential combustion.

Using these CRFs with 2017 PM_2.5 source data for 203 countries, we estimated a global average source-resolved OP of 0.78 nmol min⁻¹ m⁻³ (95% confidence interval: 0.39–1.2). The energy sector (33%) and the combined agriculture and residential combustion sector (31%) were the largest contributors at the global scale, though contributions vary widely among countries.

Poisson regression analysis shows that source-resolved OP is a substantially stronger predictor of mortality attributable to PM_2.5 than either PM_2.5 mass concentration or bulk PM_2.5 OP. These findings demonstrate that source-resolved OP provides a more accurate and policy-relevant metric for evaluating mortality risks and guiding targeted air quality interventions.

A full version of this work has been published in the Journal of Environmental Management (2026).