Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction

• Published in: Neural networks Vol. 145; pp. 233 - 247
• Main Authors: Ali, Ahmad, Zhu, Yanmin, Zakarya, Muhammad
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.01.2022
• Subjects: GCN; Humans; LSTM; Neural Networks, Computer; Road safety; Spatial Analysis; Spatial and temporal dependencies; Traffic flow prediction; Weather; Traffic flow prediction; Road safety; GCN; LSTM; Spatial and temporal dependencies
• ISSN: 0893-6080; 1879-2782; 1879-2782
• DOI: 10.1016/j.neunet.2021.10.021

The prediction of crowd flows is an important urban computing issue whose purpose is to predict the future number of incoming and outgoing people in regions. Measuring the complicated spatial–temporal dependencies with external factors, such as weather conditions and surrounding point-of-interest (POI) distribution is the most difficult aspect of predicting crowd flows movement. To overcome the above issue, this paper advises a unified dynamic deep spatio-temporal neural network model based on convolutional neural networks and long short-term memory, termed as (DHSTNet) to simultaneously predict crowd flows in every region of a city. The DHSTNet model is made up of four separate components: a recent, daily, weekly, and an external branch component. Our proposed approach simultaneously assigns various weights to different branches and integrates the four properties’ outputs to generate final predictions. Moreover, to verify the generalization and scalability of the proposed model, we apply a Graph Convolutional Network (GCN) based on Long Short Term Memory (LSTM) with the previously published model, termed as GCN-DHSTNet; to capture the spatial patterns and short-term temporal features; and to illustrate its exceptional accomplishment in predicting the traffic crowd flows. The GCN-DHSTNet model not only depicts the spatio-temporal dependencies but also reveals the influence of different time granularity, which are recent, daily, weekly periodicity and external properties, respectively. Finally, a fully connected neural network is utilized to fuse the spatio-temporal features and external properties together. Using two different real-world traffic datasets, our evaluation suggests that the proposed GCN-DHSTNet method is approximately 7.9%–27.2% and 11.2%–11.9% better than the AAtt-DHSTNet method in terms of RMSE and MAPE metrics, respectively. Furthermore, AAtt-DHSTNet outperforms other state-of-the-art methods. •We design DHSTNet that considers spatio-temporal dependency and external factors of the crowd flows.•We classify temporal features into recent, daily, and weekly components.•We use GCN with DHSTNet, which at once handle dynamic spatio-temporal dependencies of traffic flows.•The spatio-temporal features of traffic flows data are dynamically learned by the proposed model.•Extensive evaluations on two real-world datasets indicate notable improvements over existing methods.