Recently, there has been a dramatic rise in the demand for accurate temperature forecasts. However, challenges arise from modeling and fusing complex spatial and temporal features in temperature data. In this study, we propose a physics-informed directed-graph-based temperature prediction model to mitigate the challenges of purely data-driven prediction algorithms. Firstly, a directed graph design module was designed and then used to construct an asymmetric adjacency matrix based on the locations of temperature-monitoring stations. This module can capture the asymmetric relations between temperature data at different stations. Then, the directed adjacency matrix was incorporated into the graph attention module and the graph-gating module to extract the spatial and temporal features of the temperature data, and a fusion module was designed to integrate the spatial–temporal features and the directed graph adjacency matrix to provide better temperature prediction performance. Numerical simulations based on a real-world dataset collected in southern China demonstrate that our proposed physics-informed temperature prediction model can deliver superior prediction performance with a mean absolute error of less than 0.75 °C.
Medium-range temperature forecasts are of critical importance for a diverse range of economic activities, e.g., agricultural production, transportation, and industrial operations. The most significant challenge in accurately predicting temperature lies in effectively characterizing the spatiotemporal evolution of temperature characteristics. In this paper, we design a spatial feature module and a gating temporal module based on the location-oriented directed adjacency matrix. Dynamic evolution of both spatial and temporal features is characterized by a graph-based differential equation module. The spatial and temporal feature sequences are integrated by an output fusion module to achieve medium-range temperature prediction. The proposed graph-based differential equation network has been validated on the dataset of South China, which shows superior performance in medium-range temperature prediction.
Significant interest has been sparked in the monitoring and prediction of air quality due to the impact of air quality on human health. However, challenges arise from characterizing the complex spatial features and temporal features of monitored air quality data. In this paper, we develop an air quality forecasting model using spatio-temporal feature fusion over graphs. We use the location information of air quality monitoring stations to construct a directed graph adjacency matrix, which helps in extracting the spatial features of air quality data. A spatio-temporal feature extraction module is designed by explicitly involving the graph adjacency matrix to help characterize the coupled effects between spatial and temporal features of air quality data. Our proposed air quality prediction model was demonstrated using a real-world dataset collected over 35 air monitoring stations in Beijing. Numerical experiments demonstrate that our proposed model improves the air quality prediction over several existing models, e.g., 18.65 percent improvement in 24 h air quality prediction over the MAE metric and 15.91 percent improvement in 24 h prediction over the RMSE metric.