Prediction of PM2.5 Hour Concentration Based on U-net Neural Network

• Published in: Beijing da xue xue bao Vol. 56; no. 5; pp. 796 - 804
• Main Authors: Yihang, Li, Weixin, Zhai, Hanqi, Yan, Daoye, Zhu, Xiaochong, Tong, Chengqi, Cheng
• Format: Journal Article
• Language: Chinese
• Published: Beijing Acta Scientiarum Naturalium Universitatis Pekinenis 01.01.2020
• Subjects: Accuracy; Neural networks; Prediction models
• ISSN: 0479-8023
• DOI: 10.13209/j.0479-8023.2020.065

Most of the previous PM2.5 prediction models present unsatisfactory performance in several aspects, including predicting accuracy and generalization ability, especially in case of the sudden change in the value of PM2.5 situation. Therefore, we propose a method based on the U-net neural network to predict the hourly PM2.5 concentration value on the research area, attempting to improve the prediction performance. The proposed model includes two major steps. First, based on the inverse distance interpolation of historical wind field data, discrete station PM2.5 values are interpolated into a PM2.5 grid map; second, the U-net neural network is applied to train the prepared spatiotemporal grid data and make predictions. The model can use the PM2.5 concentration values of the grid map extracted at different time stamps for the PM2.5 prediction. The PM2.5 concentration values at all locations in the research region can be achieved. Specifically, the prediction accuracy and the generalization ability of the model in