Machine Learning-Based Retrieval of PM2.5 Concentrations Using Multi-Source Satellite Data in the Beijing–Tianjin–Hebei Region of China

Abstract

Satellite aerosol optical depth (AOD) provides information for surface PM2.5 retrieval, but its relationship with ground-level concentrations depends on meteorological and environmental conditions. This study evaluated a multi-source PM2.5 retrieval framework for the Beijing–Tianjin–Hebei (BTH) region during 2019–2021. Four input combinations were compared: AOD alone, AOD with meteorological variables, AOD with additional satellite variables, and all eight predictors. The satellite variables included land surface temperature, NDVI, and tropospheric NO2. Random forest, support vector regression, XGBoost, and linear stacking were evaluated using the same samples and an 80:10:10 training–validation–test split. The stacking model was trained using out-of-fold predictions. Across the four models, R2 increased from 0.51–0.54 with AOD alone to 0.83–0.84 with all predictors. Stacking achieved the best performance with all predictors, with R2 = 0.84, RMSE = 12.4 μg/m3, and MAE = 9.7 μg/m3. Annual retrievals showed higher concentrations in southern and southwestern Hebei and lower concentrations in northern BTH, while the 2021 maps showed higher concentrations in winter than in summer. Missing AOD reduced the spatial completeness of PM2.5 retrievals, and future work should assess gap filling to improve coverage and its effects on retrieval accuracy.