Spatiotemporally continuous PM_2.5 dataset in the Mekong River Basin from 2015 to 2022 using a stacking model

With the potential to cause millions of deaths, PM_2.5 pollution has become a global concern. In Southeast Asia, the Mekong River Basin (MRB) is experiencing heavy PM_2.5 pollution and the existing PM_2.5 studies in the MRB are limited in terms of accuracy and spatiotemporal coverage. To achieve high-accuracy and long-term PM_2.5 monitoring of the MRB, fused aerosol optical depth (AOD) data and multi-source auxiliary data are fed into a stacking model to estimate PM_2.5 concentrations. The proposed stacking model takes advantage of convolutional neural network (CNN) and Light Gradient Boosting Machine (LightGBM) models and can well represent the spatiotemporal heterogeneity of the PM_2.5-AOD relationship. In the cross-validation (CV), comparison with CNN and LightGBM models shows that the stacking model can better suppress overfitting, with a higher coefficient of determination (R²) of 0.92, a lower root mean square error (RMSE) of 5.58 μg/m³, and a lower mean absolute error (MAE) of 3.44 μg/m³. For the first time, the high-accuracy PM_2.5 dataset reveals spatially and temporally continuous PM_2.5 pollution and variations in the MRB from 2015 to 2022. Moreover, the spatiotemporal variations of annual and monthly PM_2.5 pollution are also investigated at the regional and national scales. The dataset will contribute to the analysis of the causes of PM_2.5 pollution and the development of mitigation policies in the MRB.