ADST: Forecasting Metro Flow Using Attention-Based Deep Spatial-Temporal Networks with Multi-Task Learning

• Published in: Sensors (Basel, Switzerland) Vol. 20; no. 16; p. 4574
• Main Authors: Jia, Hongwei, Luo, Haiyong, Wang, Hao, Zhao, Fang, Ke, Qixue, Wu, Mingyao, Zhao, Yunyun
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 14.08.2020; MDPI
• Subjects: Accuracy; Algorithms; attention mechanism; Big Data; Correlation; Datasets; Deep learning; forecasting passenger flow; multi-task learning; Neural networks; Passengers; Public safety; Safety management; spatiotemporal dependency; spatiotemporal networks; Time series; Traffic congestion; Traffic flow; Traffic management; Weather; Beijing China; China
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s20164574

Passenger flow prediction has drawn increasing attention in the deep learning research field due to its great importance in traffic management and public safety. The major challenge of this essential task lies in multiple spatiotemporal correlations that exhibit complex non-linear correlations. Although both the spatial and temporal perspectives have been considered in modeling, most existing works have ignored complex temporal correlations or underlying spatial similarity. In this paper, we identify the unique spatiotemporal correlation of urban metro flow, and propose an attention-based deep spatiotemporal network with multi-task learning (ADST-Net) at a citywide level to predict the future flow from historical observations. ADST-Net uses three independent channels with the same structure to model the recent, daily-periodic and weekly-periodic complicated spatiotemporal correlations, respectively. Specifically, each channel uses the framework of residual networks, the rectified block and the multi-scale convolutions to mine spatiotemporal correlations. The residual networks can effectively overcome the gradient vanishing problem. The rectified block adopts an attentional mechanism to automatically reweigh measurements at different time intervals, and the multi-scale convolutions are used to extract explicit spatial relationships. ADST-Net also introduces an external embedding mechanism to extract the influence of external factors on flow prediction, such as weather conditions. Furthermore, we enforce multi-task learning to utilize transition passenger flow volume prediction as an auxiliary task during the training process for generalization. Through this model, we can not only capture the steady trend, but also the sudden changes of passenger flow. Extensive experimental results on two real-world traffic flow datasets demonstrate the obvious improvement and superior performance of our proposed algorithm compared with state-of-the-art baselines.