Identifying and predicting the travel hotspots in urban areas can provide crucial support for building intelligent transportation systems. In this study, we propose to use the potentials of urban mobility field to identify the travel hotspots and develop a K-shape clustering transformer-decoder (KSC-TD) model to predict multi-step potentials. In the KSC-TD model, the K-shape clustering method is used to cluster the grids with similar potential time series, whereas the transformer-decoder model is trained for each cluster of grids by integrating the multi-head masked attention mechanism and the scheduled sampling strategy. The developed KSC-TD model is validated using the license plate recognition (LPR) data of Changsha (a major southern city of China). Results indicate that the proposed KSC-TD model outperforms nine benchmark models in predicting the multi-step potentials of urban mobility field, offering a new and effective approach for anticipating urban travel hotspots.

The traffic speed information of an urban road network is generally estimated using the widely available taxi GPS data. However, taxi usages are preponderantly restricted to areas with high population density, which results in limited spatial coverage of collected taxi GPS data. Moreover, the traffic speeds of taxies are not guaranteed to well represent the traffic speeds of other types of vehicles. In this study, we address these issues by introducing an infinite Gaussian mixture model to estimate traffic speed distribution. The variational inference method is employed to deal with the complicated parameter estimation problem. The proposed mixture model simultaneously combines taxi GPS data, bus GPS data, and mobile phone GPS data, which not only generates the mixed traffic-speed distribution of different types of vehicles but also improves the spatial coverage and the quality of traffic speed estimation. Surprisingly, we find that the incorporation of mobile phone GPS data can considerably improve the model’s ability to sense anomalous traffic conditions. Finally, the mixed traffic-speed distribution is validated using the license plate recognition data.

In many cities, subways are expanding with new or extended lines being built and put into operations. The prediction of future travel demand in subway with the planned expansion is of significant importance because such information is crucial for new line planning and new network operations. In this study, we identify the determinant features from potential influential factors of passenger travel demand and develop a two-step model for predicting passenger travel demand in expanding subways. The proposed model is tested in an actual subway with a new line being put into operations, and achieves higher prediction accuracy than the benchmark models.

While considering the spatial and temporal features of traffic, capturing the impacts of various external factors on travel is an essential step towards achieving accurate traffic forecasting. However, existing studies seldom consider external factors or neglect the effect of the complex correlations among external factors on traffic. Intuitively, knowledge graphs can naturally describe these correlations. Since knowledge graphs and traffic networks are essentially heterogeneous networks, it is challenging to integrate the information in both networks. On this background, this study presents a knowledge representation-driven traffic forecasting method based on spatial-temporal graph convolutional networks. We first construct a knowledge graph for traffic forecasting and derive knowledge representations by a knowledge representation learning method named KR-EAR. Then, we propose the Knowledge Fusion Cell (KF-Cell) to combine the knowledge and traffic features as the input of a spatial-temporal graph convolutional backbone network. Experimental results on the real-world dataset show that our strategy enhances the forecasting performances of backbones at various prediction horizons. The ablation and perturbation analysis further verify the effectiveness and robustness of the proposed method. To the best of our knowledge, this is the first study that constructs and utilizes a knowledge graph to facilitate traffic forecasting; it also offers a promising direction to integrate external information and spatial-temporal information for traffic forecasting. The source code is available athttps://github.com/lehaifeng/T-GCN/tree/master/KST-GCN.

Traffic flow data collected by traffic sensing devices is crucially important for transportation planning and transportation management. However, traffic sensing devices are typically distributed sparsely in road networks owing to their high installation and maintenance costs. The present study combines license plate recognition (LPR) data with taxi GPS trajectory data to develop a data-driven approach for estimating traffic flow in large road networks. The approach is applied to estimate traffic flow for an actual road network comprising 5,495 road segments using the traffic flow records of only 68 road segments (1.2% of the total). Five-fold cross validation is employed to verify the estimated traffic flow, and the data requirements for implementing the proposed method are analyzed. The developed data-driven approach provides an alternative and cost-efficient way of acquiring additional traffic flow information rather than installing more traffic sensing devices on roads.

Accurate and real-time traffic forecasting plays an important role in the intelligent traffic system and is of great significance for urban traffic planning, traffic management, and traffic control. However, traffic forecasting has always been considered an “open” scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time. To capture the spatial and temporal dependences simultaneously, we propose a novel neural network-based traffic forecasting method, the temporal graph convolutional network (T-GCN) model, which is combined with the graph convolutional network (GCN) and the gated recurrent unit (GRU). Specifically, the GCN is used to learn complex topological structures for capturing spatial dependence and the gated recurrent unit is used to learn dynamic changes of traffic data for capturing temporal dependence. Then, the T-GCN model is employed to traffic forecasting based on the urban road network. Experiments demonstrate that our T-GCN model can obtain the spatio-temporal correlation from traffic data and the predictions outperform state-of-art baselines on real-world traffic datasets. Our tensorflow implementation of the T-GCN is available at https://www.github.com/lehaifeng/T-GCN.