An Explainable Machine Learning Perspective on Anthropogenic Emission and Meteorology drivers of long-term PM_2.5 Trends over Northeast China

Abstract. Northeast China is a cold industrial and agricultural region where PM_2.5 pollution is influenced by emission changes, winter heating, agricultural burning, and meteorological variability, but long-term city-level evidence of these drivers remains limited. Here we combined hourly PM_2.5 observations from 36 cities during 2015–2025 with ERA5 meteorology, LightGBM models interpreted using Shapley Additive Explanations, and weather normalization. Observed PM_2.5 was separated into a weather-normalized component (PM_emi), representing non-meteorological variability in the pollution baseline, and a meteorological modulation term (PM_met). Regional annual mean PM_2.5 decreased by 39.7 %, from 48.4 μg m⁻³ in 2015 to 29.2 μg m⁻³ in 2025. The PM_emi trend accounted for 95.5 % of the observed linear decrease and showed consistent decreases with independent CEDS emission indices, supporting an important role of anthropogenic emission reductions. However, regional annual mean PM_2.5 changed little after 2022 and remained above 25 μg m⁻³. Regional exceedance days decreased from 52 to 12 d yr⁻¹, but PM_met was positive on all 229 exceedance days, indicating meteorological amplification during high-pollution episodes. Model interpretation further linked exceedance-day PM_2.5enhancement to thermal, pressure, moisture, wind, and boundary-layer conditions. VIIRS fire detections and CO observations indicated that agricultural biomass burning and other combustion sources were associated with short-term PM_2.5 variability during spring and autumn burning seasons. These results show how emission reductions, residual combustion sources, and unfavorable meteorology jointly control PM_2.5 variability in cold industrial and agricultural regions.