Chen Linlong, Chen Linbiao, Wang Hongyan, Zhao Jian
School of Big Data & Information Engineering, Guiyang Institute of Humanities and Technology, Guiyang, China.
School of Computer & Communication, Lanzhou University of Technology, Lanzhou, China.
PLoS One. 2025 Aug 25;20(8):e0331095. doi: 10.1371/journal.pone.0331095. eCollection 2025.
Accurate traffic flow forecasting plays a critical role in alleviating urban road congestion. Despite the success of existing models (e.g., graph-based or attention-based methods), three key limitations persist: (1) inflexible spatial dependency modeling, where static graph structures fail to adapt to dynamic traffic patterns; (2) decoupled spatiotemporal learning, where spatial and temporal correlations are processed separately, leading to information loss; and (3) limited long-term trend awareness, as traditional attention mechanisms overlook local contextual cues (e.g., rush-hour fluctuations). To address this, a new model of traffic flow forecasting based on Spatiotemporal Interactive Learning and Temporal Attention (STIL-TA) is proposed. This model effectively enhances the accuracy of traffic flow predictions by jointly modeling the spatiotemporal characteristics of road networks. Specifically, STIL-TA consists of two key components: (1) an interactive learning module built upon interactive dynamic graph convolution, which adopts a divide-and-conquer strategy to synchronize interactions and share the dynamically captured spatiotemporal features across different time periods, and (2) a temporal multi-head trend-aware self-attention mechanism, which utilizes local contextual information to transform the numerical sequence, enabling the capture of dynamic temporal dependencies in traffic flow and improving long-term prediction accuracy. Experimental results on four real-world traffic datasets demonstrate that the proposed STIL-TA model outperforms existing approaches, achieving significant improvements in forecasting accuracy.
准确的交通流量预测在缓解城市道路拥堵方面起着关键作用。尽管现有模型（如基于图的方法或基于注意力的方法）取得了成功，但仍存在三个关键限制：（1）空间依赖性建模不灵活，静态图结构无法适应动态交通模式；（2）时空学习解耦，空间和时间相关性被分别处理，导致信息丢失；（3）长期趋势感知有限，因为传统注意力机制忽略了局部上下文线索（如高峰时段的波动）。为了解决这个问题，提出了一种基于时空交互学习和时间注意力（STIL-TA）的交通流量预测新模型。该模型通过联合建模道路网络的时空特征，有效地提高了交通流量预测的准确性。具体来说，STIL-TA由两个关键组件组成：（1）一个基于交互式动态图卷积构建的交互学习模块，它采用分治策略来同步交互并在不同时间段共享动态捕获的时空特征，（2）一个时间多头趋势感知自注意力机制，它利用局部上下文信息来转换数值序列，从而能够捕获交通流量中的动态时间依赖性并提高长期预测准确性。在四个真实世界交通数据集上的实验结果表明，所提出的STIL-TA模型优于现有方法，在预测准确性方面取得了显著提高。
