A forecasting framework on fusion of spatiotemporal features for multi-station PM2.5

Persistent PM2.5 pollution poses a serious threat to human health. Developing an accurate urban regional PM2.5 forecasting is of practical significance for environmental protection. However, previous studies have mostly focused on individual monitoring stations, neglecting the influence of neighboring stations, which limits forecasting accuracy. Additionally, the PM2.5 of a single monitoring station cannot reflect the overall situation of a region. Therefore, this paper develops a novel PM2.5 spatiotemporal forecasting framework that combines graph convolutional module, temporal convolutional module, linear module. It enables the forecasting of PM2.5 concentrations at multiple stations and multiple time steps in the future. Concretely, we utilize a mixed graph convolutional network to extract the spatial features of PM2.5. Then, an improved temporal convolutional network, the second-order residual temporal convolutional network, is developed to capture complex temporal features. Following the classical "linear and non-linear" modeling strategy, a linear module is added to the forecasting framework. Experiments on the real air pollution dataset from Beijing demonstrate that our framework outperforms the state-of-the-art baselines.