Obtaining accurate information about future traffic flows of all links in a traffic network is of great importance for traffic management and control applications. This research studies two particular problems in traffic forecasting: (1) capture the dynamic and non-local spatial correlation between traffic links and (2) model the dynamics of temporal dependency for accurate multiple steps ahead predictions. To address these issues, we propose a deep learning framework named Spatial-Temporal Sequence to Sequence model (STSeq2Seq). This model builds on sequence to sequence (seq2seq) architecture to capture temporal feature and relies on graph convolution for aggregating spatial information. Moreover, STSeq2Seq defines and constructs Pattern-aware Adjacency Matrix (PAM) based on pair-wise similarity of the recent traffic patterns on traffic links and integrates it into graph convolution operation. It also deploys a novel seq2sesq architecture which couples a convolutional encoder and a recurrent decoder with attention mechanism for dynamic modeling of long-range dependence between different time steps. We conduct extensive experiments using two publicly-available large-scale traffic datasets and compare STSeq2Seq with other baseline models. The numerical results demonstrate that the proposed model achieves state-of-the-art forecasting performance in terms of various error measures. The ablation study verifies the effectiveness of PAMs in capturing dynamic non-local spatial correlation and the superiority of proposed seq2seq architecture in modeling non-stationary temporal dependency for multiple steps ahead prediction. Furthermore, qualitative analysis is conducted on PAMs as well as the attention weights for model interpretation.

对于交通管理和控制应用而言，获得有关交通网络中所有链路的未来交通流量的准确信息非常重要。这项研究研究了交通预测中的两个特殊问题：（1）捕获交通链路之间的动态和非局部空间相关性；（2）对时间依赖性的动力学进行建模，以进行准确的多步提前预测。为了解决这些问题，我们提出了一个深度学习框架，称为时空序列到序列模型（STSeq2Seq）。该模型建立在序列到序列（seq2seq）体系结构上以捕获时间特征，并依赖于图卷积来聚合空间信息。此外，STSeq2Seq定义并构造了模式感知邻接矩阵（PAM）基于交通链路上最近交通模式的成对相似性并将其集成到图卷积操作中。它还部署了一种新颖的seq2sesq架构，该架构将卷积编码器和递归解码器与注意力机制结合在一起，可以对不同时间步长之间的长期依赖性进行动态建模。我们使用两个可公开获得的大规模交通数据集进行了广泛的实验，并将STSeq2Seq与其他基准模型进行了比较。数值结果表明，所提出的模型在各种误差度量方面均达到了最新的预测性能。消融研究验证了PAM在捕获动态非局部空间相关性方面的有效性以及拟议的seq2seq体系结构在建模非平稳时间相关性以进行多步提前预测方面的优越性。此外，对PAM进行定性分析以及模型解释的注意力权重。