Heterogeneous spatiotemporal copula-based kriging for air pollution prediction

Air pollutants have a significant negative impact on human health, especially cardiovascular and respiratory. An efficient and effective spatiotemporal model for air pollution prediction is urgently needed to help strengthen air pollution control and improve air quality. Empirical statistical models have been widely applied for spatiotemporal prediction. However, they are not capable of dealing well with space-time heterogeneity and dependency, thereby achieving lower accuracy. Here, a hybrid frame named heterogeneous spatiotemporal copula-based kriging is proposed for fine particulate matter (PM2.5) concentration prediction; it is a multi-time, multi-site kriging model based on spatiotemporal clustering. The proposed model is capable of addressing spatiotemporal heterogeneity effectively and accounting for the spatiotemporal dependence by copula-based covariance functions. To evaluate the effectiveness of the proposed approach, an experiment on daily PM2.5 data in China in 2016 was carried out. The results (MAE = 6.48, RMSE = 10.68, R2 = 0.919) show that the proposed model can achieve good performance in PM2.5 prediction, which is of great significance in regional air quality management.