<p style="font-weight: 400;">Northeast China is a cold industrial and agricultural region where PM<sub>2.5</sub> 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<sub>2.5 </sub>observations from 36 cities during 2015–2025 with ERA5 meteorology, LightGBM models interpreted using Shapley Additive Explanations, and weather normalization. Observed PM<sub>2.5</sub> was separated into a weather-normalized component (PM<sub>emi</sub>), representing non-meteorological variability in the pollution baseline, and a meteorological modulation term (PM<sub>met</sub>). Regional annual mean PM<sub>2.5 </sub>decreased by 39.7 %, from 48.4 μg m<sup><span>−</span>3</sup> in 2015 to 29.2 μg m<sup><span>−</span>3</sup> in 2025. The PM<sub>emi</sub> 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<sub>2.5</sub> changed little after 2022 and remained above 25 μg m<sup><span>−</span>3</sup>. Regional exceedance days decreased from 52 to 12 d yr<sup><span>−</span>1</sup>, but PM<sub>met</sub> was positive on all 229 exceedance days, indicating meteorological amplification during high-pollution episodes. Model interpretation further linked exceedance-day PM<sub>2.5</sub>enhancement 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<sub>2.5</sub> variability during spring and autumn burning seasons. These results show how emission reductions, residual combustion sources, and unfavorable meteorology jointly control PM<sub>2.5</sub> variability in cold industrial and agricultural regions.