| 摘 要： |
Accurate estimation of PM2.5 concentrations is critical to understanding and counteracting air pollution. In the past decade, various machine learning models, especially deep learning models, have been widely used in PM2.5 remote sensing estimation and have achieved remarkable performance. However, a typical pitfall of deep learning models is the problem of high-value underestimation, i.e., the models often underestimate high-level PM2.5 concentrations. Alleviating the problem of high-value underestimation and improving the estimation ac-curacy of high PM2.5 concentrations are crucial. This study developed a new deep learning model that combines data augmentation and a particle size constraint to improve the high-level PM2.5 estimation. Based on the re-sidual neural network (ResNet), this study used random oversampling to construct a data-augmented deep re-sidual learning model (AugResNet). In addition, a deep residual neural network model with a particle size constraint was established and called ConResNet. Then, the data augmentation and particle size constraint were incorporated into the deep residual neural network model (denoted as Aug_ConResNet). We evaluated the above four models across China with the 10-fold site-based cross-validation approach. In terms of the estimation ac-curacy for high PM2.5 concentrations (> 75 mu g/m3), AugResNet (R2 = 0.813, RMSE = 19.152 mu g/m3), ConResNet (R2 = 0.796, RMSE = 20.841 mu g/m(3)) and Aug_ConResNet (R2 = 0.820, RMSE = 18.810 mu g/m3) outperformed ResNet (R2 = 0.780, RMSE = 21.628 mu g/m3). Results showed that the data augmentation and particle size constraint alleviated the problem of high-value underestimation and improved the estimation accuracy for high PM2.5 concentrations. The accurate estimation of high PM2.5 concentrations has important application potential for remote sensing monitoring of polluted weather. |
在线留言
联系我们
所长信箱