TSHDNet: temporal-spatial heterogeneity decoupling network for multi-mode traffic flow prediction

Abstract

Given the intricate spatial dependencies and dynamic trends among diverse road segments, the prediction of spatio-temporal traffic flow data presents a formidable challenge. To address this challenge within the complexity of urban multi-mode transportation systems, this paper introduces an innovative solution. Anchored by the TSHDNet framework, the proposed methodology presents a novel spatio-temporal heterogeneous decoupling network that adeptly captures the inherent relationships between traffic patterns and temporal-spatial fluctuations. By seamlessly integrating temporal and nodal embeddings, dynamic graph learning, and multi-scale representation modules, TSHDNet demonstrates remarkable efficacy in unraveling the subtle dynamics of traffic flow. Empirical evaluations and ablation experiments conducted on four real-world datasets affirm the framework’s capability and the effectiveness of the decoupling approach.The source codes are available at: https://github.com/MeiWu2/TSHDNet.git