PM concentration 7-day prediction in the Beijing-Tianjin-Hebei region using a novel stacking framework.
Journal:
Scientific reports
Published Date:
Jul 1, 2025
Abstract
High-precision prediction of near-surface PM concentration is a significant theoretical prerequisite for effective monitoring and prevention of air pollution, and also provides guiding suggestions for the prevention and control of PM-related health risks. It has been acknowledged that existing PM prediction models predominantly rely on variables influenced by near-surface factors. This inherent limitation could hinder the comprehensive exploration of the continuous spatio-temporal characteristics associated with PM. In this study, an optimal 7-day prediction model for PM concentration based on the Stacking algorithm was constructed based on multi-source data mainly including atmospheric environment ground monitoring station data, MODIS remote sensing-derived aerosol optical depth (AOD) daily data and meteorological factors. The findings indicated that the PM forecasting outcomes derived from this integrated RF-LSTM-Stacking model exhibited a superior fit, with R², RMSE, and MAE values of 0.95, 7.74 µg/m³, and 6.08 µg/m³, correspondingly. This approach enhanced the accuracy of prediction to a degree of approximately 17% in comparison with a solitary machine learning model. The findings of this study demonstrated that the integration of the LSTM-RF model with the fusion-based Stacking algorithm led to a substantial enhancement in the accuracy of PM predictions. This model was found to serve as an effective reference for the monitoring of PM prediction and early warning systems.
Authors
Keywords
No keywords available for this article.
