Dong Pingping, Zhang Xiaoning
Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong; School of Economics and Management, Tongji University, Siping Road 1239, Shanghai, 200092, China.
School of Economics and Management, Tongji University, Siping Road 1239, Shanghai, 200092, China.
Neural Netw. 2025 Oct;190:107623. doi: 10.1016/j.neunet.2025.107623. Epub 2025 May 28.
Accurate traffic prediction has significant implications for traffic optimization and management. However, few studies have thoroughly considered the implicit spatial semantic information and intricate temporal patterns. To address these challenges, we propose a spatio-temporal graph transformer with road network semantic awareness (ST-GTrans) for traffic flow prediction, an architecture that extends the transformer to effectively model spatio-temporal dependencies in traffic data. This model incorporates a multiscale temporal transformer designed to capture historical traffic patterns across multiple time scales, enabling the identification of short- and long-term temporal dependencies. Additionally, ST-GTrans addresses spatial dependencies by separately modeling the dynamic and static traffic components. Dynamic components employ a graph transformer with an edge that captures the semantic interactions between nodes through a multi-head attention mechanism. This mechanism integrates edge features from a semantic matrix constructed using a dynamic time-warping method based on time-series traffic data. For the static components, a multi-hop graph convolutional network was used to model the spatial dependencies rooted in the road network. Finally, a generative decoder was incorporated to mitigate error accumulation in long-term predictions. Extensive experiments on diverse datasets, including the PeMS03 traffic dataset (California freeway traffic data), the Shanghai metro flow dataset, and the Hong Kong traffic dataset, validated the effectiveness of ST-GTrans in capturing complex spatio-temporal patterns and demonstrated significant improvements over state-of-the-art baseline methods across multiple metrics.
准确的交通流量预测对交通优化与管理具有重要意义。然而，很少有研究充分考虑隐含的空间语义信息和复杂的时间模式。为应对这些挑战，我们提出了一种具有道路网络语义感知的时空图变换器（ST-GTrans）用于交通流量预测，该架构扩展了变换器以有效建模交通数据中的时空依赖性。此模型包含一个多尺度时间变换器，旨在捕捉多个时间尺度上的历史交通模式，从而能够识别短期和长期的时间依赖性。此外，ST-GTrans通过分别对动态和静态交通组件进行建模来处理空间依赖性。动态组件采用带有边的图变换器，该边通过多头注意力机制捕捉节点之间的语义交互。这种机制整合了基于时间序列交通数据使用动态时间规整方法构建的语义矩阵中的边特征。对于静态组件，使用多跳图卷积网络对源于道路网络的空间依赖性进行建模。最后，引入了一个生成解码器以减轻长期预测中的误差累积。在包括PeMS03交通数据集（加利福尼亚高速公路交通数据）、上海地铁客流量数据集和香港交通数据集等不同数据集上进行的大量实验，验证了ST-GTrans在捕捉复杂时空模式方面的有效性，并在多个指标上展示了相对于现有最先进基线方法的显著改进。
