Short-term passenger flow forecasting is an essential component in urban rail transit operation. Emerging deep learning models provide good insight into improving prediction precision. Therefore, we propose a deep learning architecture combining the residual network (ResNet), graph convolutional network (GCN), and long short-term memory (LSTM) (called ``ResLSTM'') to forecast short-term passenger flow in urban rail transit on a network scale. First, improved methodologies of the ResNet, GCN, and attention LSTM models are presented. Then, the model architecture is proposed, wherein ResNet is used to capture deep abstract spatial correlations between subway stations, GCN is applied to extract network topology information, and attention LSTM is used to extract temporal correlations. The model architecture includes four branches for inflow, outflow, graph-network topology, as well as weather conditions and air quality. To the best of our knowledge, this is the first time that air-quality indicators have been taken into account, and their influences on prediction precision quantified. Finally, ResLSTM is applied to the Beijing subway using three time granularities (10, 15, and 30 min) to conduct short-term passenger flow forecasting. A comparison of the prediction performance of ResLSTM with those of many state-of-the-art models illustrates the advantages and robustness of ResLSTM. Moreover, a comparison of the prediction precisions obtained for time granularities of 10, 15, and 30 min indicates that prediction precision increases with increasing time granularity. This study can provide subway operators with insight into short-term passenger flow forecasting by leveraging deep learning models.

Short‐term passenger flow forecasting is a crucial task for urban rail transit operations. Emerging deep‐learning technologies have become effective methods used to overcome this problem. In this study, the authors propose a deep‐learning architecture called Conv‐GCN that combines a graph convolutional network (GCN) and a three‐dimensional (3D) convolutional neural network (3D CNN). First, they introduce a multi‐graph GCN to deal with three inflow and outflow patterns (recent, daily, and weekly) separately. Multi‐graph GCN networks can capture spatiotemporal correlations and topological information within the entire network. A 3D CNN is then applied to deeply integrate the inflow and outflow information. High‐level spatiotemporal features between different inflow and outflow patterns and between stations that are nearby and far away can be extracted by 3D CNN. Finally, a fully connected layer is used to output results. The Conv‐GCN model is evaluated on smart card data of the Beijing subway under the time interval of 10, 15, and 30 min. Results show that this model yields the best performance compared with seven other models. In terms of the root‐mean‐square errors, the performances under three time intervals have been improved by 9.402, 7.756, and 9.256%, respectively. This study can provide critical insights for subway operators to optimise urban rail transit operations.

Accurate traffic prediction is a challenging task in intelligent transportation systems because of the complex spatio-temporal dependencies in transportation networks. Many existing works utilize sophisticated temporal modeling approaches to incorporate with graph convolution networks (GCNs) for capturing short-term and long-term spatio-temporal dependencies. However, these separated modules with complicated designs could restrict effectiveness and efficiency of spatio-temporal representation learning. Furthermore, most previous works adopt the fixed graph construction methods to characterize the global spatio-temporal relations, which limits the learning capability of the model for different time periods and even different data scenarios. To overcome these limitations, we propose an automated dilated spatio-temporal synchronous graph network, named Auto-DSTSGN for traffic prediction. Specifically, we design an automated dilated spatio-temporal synchronous graph (Auto-DSTSG) module to capture the short-term and long-term spatio-temporal correlations by stacking deeper layers with dilation factors in an increasing order. Further, we propose a graph structure search approach to automatically construct the spatio-temporal synchronous graph that can adapt to different data scenarios. Extensive experiments on four real-world datasets demonstrate that our model can achieve about $10\%$ improvements compared with the state-of-art methods. Source codes are available at https://github.com/jinguangyin/Auto-DSTSGN.

Short-term passenger flow forecasting is an essential component for the operation of urban rail transit (URT). Therefore, it is necessary to obtain a higher prediction precision with the development of URT. As artificial intelligence becomes increasingly prevalent, many prediction methods including the long short-term memory network (LSTM) in the deep learning field have been applied in road transportation systems, which can give critical insights for URT. First, we propose a novel two-step K-Means clustering model to capture not only the passenger flow variation trends but also the ridership volume characteristics. Then, a predictability assessment model is developed to recommend a reasonable time granularity interval to aggregate passenger flows. Based on the clustering results and the recommended time granularity interval, the LSTM model, which is called CB-LSTM model, is proposed to conduct short-term passenger flow forecasting. Results show that the prediction based on subway station clusters can not only avoid the complication of developing numerous models for each of the hundreds of stations, but also improve the prediction performance, which make it possible to predict short-term passenger flow on a network scale using limited dataset. The results provide critical insights for subway operators and transportation policymakers.