Most of the previous PM_2.5 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 PM_2.5 situation. Therefore, we propose a method based on the U-net neural network to predict the hourly PM_2.5 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 PM_2.5 values are interpolated into a PM_2.5 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 PM_2.5 concentration values of the grid map extracted at different time stamps for the PM_2.5 prediction. The PM_2.5 concentration values at all locations in the research region can be achieved. Specifically, the prediction accuracy and the generalization ability of the model in case of sudden changes are revealed. Experimental results indicate that the proposed method has a 10% improvement in the prediction accuracy of PM_2.5 concentration values in the case of sudden change.

针对目前多数PM_2.5预测模型泛化能力较差的问题, 提出基于U-net神经网络模型的PM_2.5逐小时浓度值预测模型。该模型通过引入历史风场数据, 将离散的监测站点PM_2.5浓度值插值为PM_2.5网格图; 然后将U-net神经网络作为预测模型, 基于实验区域的10小时内的PM_2.5网格图, 预测下一时刻的PM_2.5网格图。该模型可以利用历史不同时刻提取的PM_2.5浓度值网格图, 在预测区域内所有位置PM_2.5浓度值的同时, 还可以提升预测的准确性以及对PM_2.5浓度值突变情况的适应性。实验结果表明, 所提方法在PM_2.5浓度值短时间突变情况下, 预测精度比传统方法有10%左右的提升。