Skip to main content
SpringerLink
Log in

Dual attentive graph neural network for metro passenger flow prediction

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Metro system has been increasingly recognized as a backbone of urban transportation system in many cities around the world. To improve the demand management and operation efficiency, it is crucial to have accurate prediction of real-time metro passenger flow. However, the forecast performance is often subject to the complex spatial and temporal distributions of the metro passenger flow data. To this end, we developed a novel dual attentive graph neural network that can effectively predict the distribution of metro traffic flow considering the spatial and temporal influences. Specifically, two directed complete metro graphs (i.e., inbound and outbound graphs) and the weighted matrix of them are proposed to characterize the inbound (entering the system) and outbound (leaving the system) passenger flow, respectively. The weighted matrix of inbound graph is estimated based on the historical origin-destination demand and that of the outbound graph is estimated based on the similarity metrics between every two stations. Moreover, to capture the dependencies between inbound and outbound flows, multi-layer graph spatial attention networks that incorporate the spatial context are applied to exploit the dynamic inter-station correlations. Then, the acquired dependency features integrated with external factors, such as weather conditions, are filtered by temporal attention and fed into a sequence decoder to produce short-term and long-term passenger flow predictions. Finally, a series experiments are conducted based on a comprehensive empirical dataset. Findings indicated that the proposed model does not only well predict the metro passenger flow, but also effectively detect the emergencies and incidents of metro system.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Notes

  1. https://www.wunderground.com/.

  2. https://www.weibo.com/gzmtr.

References

  1. De Borger B, Kerstens K, Costa A (2002) Public transit performance: What does one learn from frontier studies? Transp Rev 22(1):1–38

    Article  Google Scholar 

  2. Li H, Ding H, Ren G, Xu C (2018) Effects of the london cycle superhighways on the usage of the london cycle hire. Transp Res Pt A-Policy Pract 111:304–315

    Article  Google Scholar 

  3. Ding H, Sze N, Li H, Guo Y (2020) Roles of infrastructure and land use in bicycle crash exposure and frequency: a case study using greater london bike sharing data. Accid Anal Prev 144:105652

    Article  Google Scholar 

  4. Zhong C, Batty M, Manley E, Wang J, Wang Z, Chen F, Schmitt G (2016) Variability in regularity: Mining temporal mobility patterns in london, singapore and beijing using smart-card data. PLoS One 11(2):e0149222

    Article  Google Scholar 

  5. Li Y, Wang X, Sun S, Ma X, Lu G (2017) Forecasting short-term subway passenger flow under special events scenarios using multiscale radial basis function networks. Transp Res Pt C-Emerg Technol 77:306–328

    Article  Google Scholar 

  6. Tang L, Zhao Y, Cabrera J, Ma J, Tsui KL (2018) Forecasting short-term passenger flow: An empirical study on shenzhen metro. IEEE Trans Intell Transp Syst 20(10):3613–3622

    Article  Google Scholar 

  7. Chen E, Ye Z, Wang C, Xu M (2019) Subway passenger flow prediction for special events using smart card data. IEEE Trans Intell Transp Syst 21:1109–1120

    Article  Google Scholar 

  8. Gong Y, Li Z, Zhang J, Liu W, Zheng Y, Kirsch C (2018) Network-wide crowd flow prediction of sydney trains via customized online non-negative matrix factorization. In: CIKM, pp 1243–1252

  9. Ahmed MS, Cook AR (1979) Analysis of freeway traffic time-series data by using box-jenkins techniques. Transp Res Record 722:1–9

    Google Scholar 

  10. Williams BM, Durvasula PK, Brown DE (1998) Urban freeway traffic flow prediction: application of seasonal autoregressive integrated moving average and exponential smoothing models. Transp Res Record 1644(1):132–141

    Article  Google Scholar 

  11. Williams BM, Hoel LA (2003) Modeling and forecasting vehicular traffic flow as a seasonal arima process: theoretical basis and empirical results. J Transp Eng 129(6):664–672

    Article  Google Scholar 

  12. Van Der Voort M, Dougherty M, Watson S (1996) Combining kohonen maps with arima time series models to forecast traffic flow. Transp Res Pt C-Emerg Technol 4(5):307–318

    Article  Google Scholar 

  13. Smith BL, Demetsky MJ (1997) Traffic flow forecasting: comparison of modeling approaches. J Transp Eng 123(4):261–266

    Article  Google Scholar 

  14. Leshem G, Ritov Y (2007) Traffic flow prediction using adaboost algorithm with random forests as a weak learner. WASET, Citeseer 19:193–198

    Google Scholar 

  15. Crosby H, Davis P, Jarvis SA (2016) Spatially-intensive decision tree prediction of traffic flow across the entire uk road network. In: DS-RT, IEEE, pp 116–119

  16. Wu CH, Ho JM, Lee DT (2004) Travel-time prediction with support vector regression. IEEE Trans Intell Transp Syst 5(4):276–281

    Article  Google Scholar 

  17. Xu H, Jiang C (2019) Deep belief network-based support vector regression method for traffic flow forecasting. Neural Comput Appl pp 1–10

  18. Sun S, Zhang C, Yu G (2006) A bayesian network approach to traffic flow forecasting. IEEE Trans Intell Transp Syst 7(1):124–132

    Article  Google Scholar 

  19. Pascale A, Nicoli M (2011) Adaptive bayesian network for traffic flow prediction. In: SSP, IEEE, pp 177–180

  20. Lu Y, He Z, Luo L (2019) Learning trajectories as words: a probabilistic generative model for destination prediction. In: MobiQuitous, pp 464–472

  21. Zhao SZ, Ni TH, Wang Y, Gao XT (2011) A new approach to the prediction of passenger flow in a transit system. Comput Math Appl 61(8):1968–1974

    Article  MathSciNet  Google Scholar 

  22. Hodge VJ, Krishnan R, Austin J, Polak J, Jackson T (2014) Short-term prediction of traffic flow using a binary neural network. Neural Comput Appl 25(7–8):1639–1655

    Article  Google Scholar 

  23. Chen Q, Song Y, Zhao J (2020) Short-term traffic flow prediction based on improved wavelet neural network. Neural Comput Appl

  24. Wu Y, Tan H, Qin L, Ran B, Jiang Z (2018) A hybrid deep learning based traffic flow prediction method and its understanding. Transp Res Pt C-Emerg Technol 90:166–180

    Article  Google Scholar 

  25. Zhang J, Zheng Y, Qi D, Li R, Yi X, Li T (2018) Predicting citywide crowd flows using deep spatio-temporal residual networks. Artif Intell 259:147–166

    Article  MathSciNet  Google Scholar 

  26. Zhang J, Zheng Y, Sun J, Qi D (2019) Flow prediction in spatio-temporal networks based on multitask deep learning. IEEE Trans Knowl Data Eng 32(3):468–478

    Article  Google Scholar 

  27. Zhang Y, Zhou Y, Lu H, Fujita H (2020) Traffic network flow prediction using parallel training for deep convolutional neural networks on spark cloud. IEEE Trans Ind Inform 16:7369–7380

    Article  Google Scholar 

  28. Li Y, Yu R, Shahabi C, Liu Y (2018) Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In: ICLR

  29. Yu B, Yin H, Zhu Z (2018) Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: IJCAI, pp 3634–3640

  30. Chen C, Li K, Teo SG, Zou X, Wang K, Wang J, Zeng Z (2019) Gated residual recurrent graph neural networks for traffic prediction. AAAI 33:485–492

    Article  Google Scholar 

  31. Wang X, Ma Y, Wang Y, Jin W, Wang X, Tang J, Jia C, Yu J (2020) Traffic flow prediction via spatial temporal graph neural network. In: WWW, pp 1082–1092

  32. Zheng C, Fan X, Wang C, Qi J (2020) Gman: A graph multi-attention network for traffic prediction. AAAI 34:1234–1241

    Article  Google Scholar 

  33. Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  34. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323(6088):533–536

    Article  Google Scholar 

  35. Hochreiter S (1998) The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int J Uncertainty Fuzziness Knowl-Based Syst 6(02):107–116

    Article  Google Scholar 

  36. Beck D, Haffari G, Cohn T (2018) Graph-to-sequence learning using gated graph neural networks. In: ACL, pp 273–283

  37. Keogh EJ, Pazzani MJ (2001) Derivative dynamic time warping. In: SDM, SIAM, pp 1–11

  38. Berndt DJ, Clifford J (1994) Using dynamic time warping to find patterns in time series. KDD workshop, Seattle, WA 10:359–370

    Google Scholar 

  39. Veličković P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2017) Graph attention networks. arXiv preprint arXiv:171010903

  40. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: NIPS, vol 31

  41. Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:181004805

  42. Fu J, Liu J, Tian H, Li Y, Bao Y, Fang Z, Lu H (2019) Dual attention network for scene segmentation. In: CVPR, pp 3146–3154

  43. Ji Y, Zhang H, Wu QJ (2018) Salient object detection via multi-scale attention cnn. Neurocomputing 322:130–140

    Article  Google Scholar 

  44. Ji Y, Zhang H, Jie Z, Ma L, Wu QJ (2020) Casnet: a cross-attention siamese network for video salient object detection. IEEE Trans Neural Netw Learn Syst

  45. Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. In: ICML, vol 30, p 3

  46. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp 770–778

  47. Liu Y, Liu Z, Jia R (2019) Deeppf: A deep learning based architecture for metro passenger flow prediction. Transp Res Pt C-Emerg Technol 101:18–34

    Article  Google Scholar 

  48. Liang Y, Ke S, Zhang J, Yi X, Zheng Y (2018) Geoman: Multi-level attention networks for geo-sensory time series prediction. In: IJCAI, pp 3428–3434

  49. Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: ICML, pp 807–814

  50. Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980

  51. Ma X, Zhang J, Du B, Ding C, Sun L (2018) Parallel architecture of convolutional bi-directional lstm neural networks for network-wide metro ridership prediction. IEEE Trans Intell Transp Syst 20(6):2278–2288

    Article  Google Scholar 

  52. Hao S, Lee DH, Zhao D (2019) Sequence to sequence learning with attention mechanism for short-term passenger flow prediction in large-scale metro system. Transp Res Pt C-Emerg Technol 107:287–300

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Intelligent Systems Engineering, Sun Yat-Sen University, Guangzhou, China

    Yuhuan Lu, Shiqian Ji & Zhaocheng He

  2. Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong

    Hongliang Ding & N. N. Sze

Authors
  1. Yuhuan Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hongliang Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shiqian Ji
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. N. N. Sze
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhaocheng He
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhaocheng He.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lu, Y., Ding, H., Ji, S. et al. Dual attentive graph neural network for metro passenger flow prediction. Neural Comput & Applic 33, 13417–13431 (2021). https://doi.org/10.1007/s00521-021-05966-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-05966-z

Keywords

Search

Navigation