Accurate traffic prediction is crucial for the management of intelligent transportation systems. Recently, researchers have developed spatiotemporal graph neural networks (ST-GNNs), achieving significant progress in performance. However, most ST-GNNs construct the graph adjacency matrix using predefined rules or trainable parameters, without fully leveraging the congestion relationships within traffic flows to guide graph structure learning. Addressing this issue, we propose a dynamic spatiotemporal graph convolutional network (DSTGCN), which adequately considers the impact of traffic congestion on traffic prediction. Firstly, based on the fundamental traffic flow graph model and congestion propagation path algorithm, a congestion propagation matrix among road nodes is constructed. Then, the real-time congestion propagation matrix is fused with the static road adjacency matrix to establish a time-varying dynamic graph neural network structure, enabling dynamic capture of traffic state changes. Finally, complex spatiotemporal correlations are captured through a specially designed spatiotemporal convolutional architecture for multi-horizon traffic prediction. Extensive experiments conducted on real-world datasets demonstrate the effectiveness and interpretability of our approach.

Efficient public transportation systems are fundamental to achieving sustainable urban development. As the backbone of urban mobility, the coordinated development of rail transit and bus systems is crucial. The opening of a new rail transit line inevitably reshapes urban travel patterns, posing significant challenges to the existing bus network. Understanding passenger switch behavior is key to optimizing the competition and cooperation between these two modes. However, existing methods on the switch behavior of bus passengers along the newly opened rail transit line cannot balance the predictive accuracy and model interpretability. To bridge this gap, we propose a CART (classification and regression tree) decision tree-based switch behavior model that incorporates both predictive and interpretive abilities. This paper uses the massive passenger swiping-card data before and after the opening of the rail transit to construct the switch dataset of bus passengers. Subsequently, a data-driven predictive model of passenger switch behavior was established based on a CART decision tree. The experimental findings demonstrate the superiority of the proposed method, with the CART model achieving an overall prediction accuracy of 85%, outperforming traditional logit and other machine learning benchmarks. Moreover, the analysis of factor significance reveals that ‘Transfer times needed after switch’ is the dominant feature (importance: 0.52), and the extracted decision rules provide clear insights into the decision-making mechanisms of bus passengers.

To implement fine-grained progression signal control on arterial, it is essential to have access to the time-varying distribution of the origin–destination (OD) flow of the arterial. However, due to the sparsity of automatic vehicle identification (AVI) devices and the low penetration of connected vehicles (CVs), it is difficult to directly obtain the distribution pattern of arterial OD flow (i.e., path flow). To solve this problem, this paper develops a semi-supervised arterial path flow estimation method considering the consistency of path flow distribution by combining the sparse AVI data and the low permeability CV data. Firstly, this paper proposes a semi-supervised arterial path flow estimation model based on multi-knowledge graphs. It utilizes graph neural networks to combine some arterial AVI OD flow observation information with CV trajectory information to infer the path flow of AVI unobserved OD pairs. Further, to ensure that the estimation results of the multi-knowledge graph path flow estimation model are consistent with the distribution of path flow in real situations, we introduce a generative adversarial network (GAN) architecture to correct the estimation results. The proposed model is extensively tested based on a real signalized arterial. The results show that the proposed model is still able to achieve reliable estimation results under low connected vehicle penetration and with less observed label data.