Difference Equation Model-Based PM2.5 Prediction considering the Spatiotemporal Propagation: A Case Study of Bohai Rim Region, China

Accurate reporting and prediction of PM2.5 concentration are very important for improving public health. In this article, we use a spectral clustering algorithm to cluster 44 cities in the Bohai Rim Region. On this basis, we propose a special difference equation model, especially the use of nonlinear diffusion equations to characterize the temporal and spatial dynamic characteristics of PM2.5 propagation between and within clusters for real-time prediction. For example, through the analysis of PM2.5 concentration data for 92 consecutive days in the Bohai Rim Region, and according to different accuracy definitions, the average prediction accuracy of the difference equation model in all city clusters is 97% or 90%. The mean absolute error (MAE) of the forecast data for each urban agglomeration is within 7 units μg/m3. The experimental results show that the difference equation model can effectively reduce the prediction time, improve the prediction accuracy, and provide decision support for local air pollution early warning and urban comprehensive management.