An integrated static and dynamic graph fusion approach for traffic flow prediction

The major challenge in accurate traffic flow prediction lies in effectively capturing the dynamic spatiotemporal correlations within the traffic system. In this paper, we propose a novel traffic flow prediction method based on the fusion of static and dynamic graphs. Firstly, a predefined graph structure is used as the initial static graph. Secondly, a temporal graph convolution module is designed and constructed in a data-driven manner. This module implements a dynamic graph structure that varies with the input data, thoroughly constructing the spatial relations between traffic flow sequence data. Finally, specific spatial and temporal relations are modeled from the perspective of graphs, effectively merging static and dynamic spatial relations. We validated the performance of the proposed method on three real public datasets: PEMS04, PEMS07, and PEMS08. The experimental results show that the model outperforms existing traffic flow prediction models by 7.38% compared to 20 benchmark methods in terms of prediction error. The method is capable of effectively learning the spatiotemporal correlations in traffic flow data, demonstrating good predictive accuracy and execution efficiency, with relevant metrics superior to most existing methods.