Skip to main content
SpringerLink
Log in

Topology augmented dynamic spatial-temporal network for passenger flow forecasting in urban rail transit

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Millions of residents travel by urban rail transit (URT) every day, and it is meaningful to accurately predict passenger flows for the purpose of intelligent system management. Considering the high traffic volume and complex spatial-temporal traffic patterns, accurate forecasting is quite challenging. Recently, advanced spatial-temporal graph neural networks that combine graph convolution and recurrent units have achieved superior traffic forecasting performance. However, existing methods either simply use a predefined physical network or directly learn latent static graphs by assigning a large number of trainable parameters. Moreover, they only consider capturing local temporal dependencies. However, the passenger flows of URT exhibit both physical adjacent and virtual distant spatial correlations and both local and global temporal fluctuations. In this paper, we propose a Topology Augmented Dynamic Spatial-Temporal Network (TADSTN) to fully exploit the complex spatial-temporal dependencies of passenger flows and make accurate forecasting in URT. Specifically, we first propose a virtual graph generation algorithm with no training parameters to obtain a topology-augmented URT graph, and we also sample multipattern temporal features from raw passenger flow data. Then, we propose a parallel spatial-temporal learning architecture with a time-aware global-level attention mechanism to simultaneously capture both distant and dynamic spatial dependencies and both local and global temporal dependencies of passenger flows. Finally, we evaluate the effectiveness and efficiency of our TADSTN on two real-world datasets.

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

Similar content being viewed by others

Data Availability

The datasets generated during the current study are available in the followings repositories: The pre-processed passenger flow data of CQURT is available at https://github.com/Peiyu-Yi/CQURT-dataset. HZMetro is a widely used public transportation dataset and can be available at https://github.com/LibCity/Bigscity-LibCity-Datasets.

Notes

  1. https://en.wikipedia.org/wiki/List_of_metro_systems.

  2. The pre-processed passenger flow data of CQURT is available at https://github.com/Peiyu-Yi/CQURT-dataset

  3. HZMetro is a widely used public transportation dataset and can be available at https://github.com/LibCity/Bigscity-LibCity-Datasets

  4. https://pytorch.org/

  5. https://www.statsmodels.org/stable/index.html.

  6. https://scikit-learn.org/

References

  1. Liu L, Chen J, Wu H, Zhen J, Li G, Lin L (2020) Physical-virtual collaboration modeling for intra-and inter-station metro ridership prediction. IEEE Trans Intell Transp Syst 23(4):3377–3391

    Article  Google Scholar 

  2. Noursalehi P, Koutsopoulos HN, Zhao J (2021) Dynamic origin-destination prediction in urban rail systems: A multi-resolution spatio-temporal deep learning approach. IEEE Trans Intell Transp Syst 23(6):5106–5115

    Article  Google Scholar 

  3. Wu JL, Lu M, Wang CY (2023) Forecasting metro rail transit passenger flow with multiple-attention deep neural networks and surrounding vehicle detection devices. Appl Intell 1–16

  4. Wang J, Zhang Y, Wei Y, Hu Y, Piao X, Yin B (2021) Metro passenger flow prediction via dynamic hypergraph convolution networks. IEEE Trans Intell Transp Syst 22(12):7891–7903

    Article  Google Scholar 

  5. Xie P, Li T, Liu J, Du S, Yang X, Zhang J (2020) Urban flow prediction from spatiotemporal data using machine learning: A survey. Information Fusion 59:1–12

    Article  Google Scholar 

  6. Guo S, Lin Y, Wan H, Li X, Cong G (2021) Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting. IEEE Trans Knowl Data Eng 34(11):5415–5428

    Article  Google Scholar 

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

    Article  Google Scholar 

  8. Chung J, Gulcehre C, Cho K, Bengio Y (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. In: NIPS 2014 Workshop on Deep Learning December 2014

  9. Liu Y, Liu Z, Jia R (2019) Deeppf: A deep learning based architecture for metro passenger flow prediction. Transportation Research Part C: Emerging Technologies 101:18–34

    Article  Google Scholar 

  10. Zhang J, Chen F, Cui Z, Guo Y, Zhu Y (2021) Deep learning architecture for short-term passenger flow forecasting in urban rail transit. IEEE Trans Intell Transp Syst 22:7004–7014

    Article  Google Scholar 

  11. Sun J, Zhang J, Li Q, Yi X, Liang Y, Zheng Y (2020) Predicting citywide crowd flows in irregular regions using multi-view graph convolutional networks. IEEE Trans Knowl Data Eng 34(5):2348–2359

  12. Zhang X, Sun Y, Guan F, Chen K, Witlox F, Huang H (2022) Forecasting the crowd: An effective and efficient neural network for citywide crowd information prediction at a fine spatio-temporal scale. Transportation Research Part C: Emerging Technologies 143:103854

  13. Zhang J, Chen F, Guo Y, Li X (2020) Multi-graph convolutional network for short-term passenger flow forecasting in urban rail transit. IET Intel Transport Syst 14(10):1210–1217

    Article  Google Scholar 

  14. Bai L, Yao L, Li C, Wang X, Wang C (2020) Adaptive graph convolutional recurrent network for traffic forecasting. Adv Neural Inf Process Syst 33:17804–17815

    Google Scholar 

  15. Wu Z, Pan S, Long G, Jiang J, Zhang C (2019) Graph wavenet for deep spatial-temporal graph modeling. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence pp. 1907–1913

  16. Bui K-HN, Cho J, Yi H (2022) Spatial-temporal graph neural network for traffic forecasting: An overview and open research issues. Appl Intell 52(3):2763–2774

    Article  Google Scholar 

  17. Yuan H, Li G, Bao Z (2022) Route travel time estimation on a road network revisited: Heterogeneity, proximity, periodicity and dynamicity. Proceedings of the VLDB Endowment 16(3):393–405

    Article  Google Scholar 

  18. Huang F, Yi P, Wang J, Li M, Peng J (2022) Time-series forecasting with shape attention. In: 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 3299–3304. IEEE

  19. Zhao L, Song Y, Zhang C, Liu Y, Wang P, Lin T, Deng M, Li H (2019) T-gcn: A temporal graph convolutional network for traffic prediction. IEEE Trans Intell Transp Syst 21(9):3848–3858

    Article  Google Scholar 

  20. Ma D, Song X, Li P (2020) Daily traffic flow forecasting through a contextual convolutional recurrent neural network modeling inter-and intra-day traffic patterns. IEEE Trans Intell Transp Syst 22(5):2627–2636

    Article  Google Scholar 

  21. Tedjopurnomo DA, Bao Z, Zheng B, Choudhury FM, Qin AK (2020) A survey on modern deep neural network for traffic prediction: Trends, methods and challenges. IEEE Trans Knowl Data Eng 34(4):1544–1561

    Google Scholar 

  22. Fang Z, Cheng Q, Jia R, Liu Z (2018) Urban rail transit demand analysis and prediction: A review of recent studies. In: International Conference on Intelligent Interactive Multimedia Systems and Services pp. 300–309. Springer

  23. Wang X, Zhang N, Zhang Y, Shi Z (2018) Forecasting of short-term metro ridership with support vector machine online model. J Adv Transp 2018

  24. He K, Ren G, Zhang S (2020) Passenger flow prediction for urban rail transit stations considering weather conditions. In: Green, Smart and Connected Transportation Systems: Proceedings of the 9th International Conference on Green Intelligent Transportation Systems and Safety pp. 661–673. Springer

  25. Chen C, Li K, Teo SG, Zou X, Li K, Zeng Z (2020) Citywide traffic flow prediction based on multiple gated spatio-temporal convolutional neural networks. ACM Transactions on Knowledge Discovery from Data (TKDD) 14(4):1–23

    Article  Google Scholar 

  26. Wei Q, Qiu Y, Wen Y (2022) Cluster-based spatiotemporal dual self-adaptive network for short-term subway passenger flow forecasting. Appl Intell 52(12):14137–14152

    Article  Google Scholar 

  27. Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2008) The graph neural network model. IEEE Trans Neural Networks 20(1):61–80

    Article  Google Scholar 

  28. Bruna J, Zaremba W, Szlam A, LeCun Y (2014) Spectral networks and deep locally connected networks on graphs. In: 2nd International Conference on Learning Representations, ICLR 2014

  29. Jiang W, Luo J (2022) Graph neural network for traffic forecasting: A survey. Expert Syst Appl 207:117921. https://doi.org/10.1016/j.eswa.2022.117921

  30. Liu L, Zhen J, Li G, Zhan G, He Z, Du B, Lin L (2020) Dynamic spatial-temporal representation learning for traffic flow prediction. IEEE Trans Intell Transp Syst 22(11):7169–7183

    Article  Google Scholar 

  31. Li Y, Yu R, Shahabi C, Liu Y (2018) Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. In: International Conference on Learning Representations

  32. Yi P, Huang F, Peng J (2021) A fine-grained graph-based spatiotemporal network for bike flow prediction in bike-sharing systems. In: Proceedings of the 2021 SIAM International Conference on Data Mining (SDM) pp. 513–521. SIAM

  33. Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations

  34. Han Y, Wang S, Ren Y, Wang C, Gao P, Chen G (2019) Predicting station-level short-term passenger flow in a citywide metro network using spatiotemporal graph convolutional neural networks. ISPRS Int J Geo Inf 8(6):243

    Article  Google Scholar 

  35. Hao S, Lee D-H, Zhao D (2019) Sequence to sequence learning with attention mechanism for short-term passenger flow prediction in large-scale metro system. Transportation Research Part C: Emerging Technologies 107:287–300

    Article  Google Scholar 

  36. Huang F, Yi P, Wang J, Li M, Peng J, Xiong X (2022) A dynamical spatial-temporal graph neural network for traffic demand prediction. Inf Sci 594:286–304

    Article  Google Scholar 

  37. Huang F, Qiao S, Peng J, Guo B, Xiong X, Han N (2019) A movement model for air passengers based on trip purpose. Physica A 525:798–808

    Article  MATH  Google Scholar 

  38. Tobler WR (1970) A computer movie simulating urban growth in the detroit region. Econ Geogr 46(sup1):234–240

    Article  Google Scholar 

  39. Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. Adv Neural Inf Process Syst 29:3844–3852

    Google Scholar 

  40. Atwood J, Towsley D (2016) Diffusion-convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1993–2001

  41. Yuan H, Li G, Bao Z, Feng L (2021) An effective joint prediction model for travel demands and traffic flows. In: 2021 IEEE 37th International Conference on Data Engineering (ICDE) pp. 348–359. IEEE

  42. 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: Proceedings of The Web Conference 2020 pp. 1082–1092

  43. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. In: Advances in Neural Information Processing Systems pp. 5998–6008

Download references

Acknowledgements

This work is partially supported by the Sichuan Science and Technology Program (2022YFG0034, 2023YFG0112), the Postdoctoral Interdisciplinary Innovation Fund (10822041A2137), the Intelligent Terminal Key Laboratory of Sichuan Province (SCITLAB-20001), and the Cooperative Program of Sichuan University and Yibin (2020CDYB-30).

Author information

Authors and Affiliations

  1. College of Computer Science, Sichuan University, Chengdu, 610065, China

    Peiyu Yi, Feihu Huang, Jince Wang & Jian Peng

Authors
  1. Peiyu Yi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Feihu Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jince Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jian Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Feihu Huang or Jian Peng.

Ethics declarations

Human Participants

This study does not contain any studies with human participants or animals performed by any of the authors.

Conflict of Interests

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

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yi, P., Huang, F., Wang, J. et al. Topology augmented dynamic spatial-temporal network for passenger flow forecasting in urban rail transit. Appl Intell 53, 24655–24670 (2023). https://doi.org/10.1007/s10489-023-04651-z

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-023-04651-z

Keywords

Search

Navigation