Prediction of PM2.5 Concentration Based on Deep Learning for High-Dimensional Time Series

PM2.5 poses a serious threat to human life and health, so the accurate prediction of PM2.5 concentration is essential for controlling air pollution. However, previous studies lacked the generalization ability to predict high-dimensional PM2.5 concentration time series. Therefore, a new model for predicting PM2.5 concentration was proposed to address this in this paper. Firstly, the linear rectification function with leakage (LeakyRelu) was used to replace the activation function in the Temporal Convolutional Network (TCN) to better capture the dependence of feature data over long distances. Next, the residual structure, dilated rate, and feature-matching convolution position of the TCN were adjusted to improve the performance of the improved TCN (LR-TCN) and reduce the amount of computation. Finally, a new prediction model (GRU-LR-TCN) was established, which adaptively integrated the prediction of the fused Gated Recurrent Unit (GRU) and LR-TCN based on the inverse ratio of root mean square error (RMSE) weighting. The experimental results show that, for monitoring station #1001, LR-TCN increased the RMSE, mean absolute error (MAE), and determination coefficient (R2) by 12.9%, 11.3%, and 3.8%, respectively, compared with baselines. Compared with LR-TCN, GRU-LR-TCN improved the index symmetric mean absolute percentage error (SMAPE) by 7.1%. In addition, by comparing the estimation results with other models on other air quality datasets, all the indicators have advantages, and it is further demonstrated that the GRU-LR-TCN model exhibits superior generalization across various datasets, proving to be more efficient and applicable in predicting urban PM2.5 concentration. This can contribute to enhancing air quality and safeguarding public health.