Skip to main content
SpringerLink
Log in

Spatial-temporal graph convolutional networks for traffic flow prediction considering multiple traffic parameters

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Timely and accurate large-scale traffic prediction has gained increasing importance for traffic management. However, it is a challenging task due to the high nonlinearity of traffic flow and complex network topology. This study aims to develop a large-scale traffic flow prediction model exploring the interaction of multiple traffic parameters to improve the prediction performance. To achieve this goal, we proposed a spatiotemporal graph convolution network considering multiple traffic parameters (MP-STGCN). The proposed model consists of a spatial gated linear unit (SGLU) block, a graph convolutional network (GCN) block, and a long short-term memory (LSTM) block. SGLU is used to extract the spatiotemporal features of multi-parameter traffic data including traffic flow, average travel speed, and traffic occupancy. Based on topological linkages, the GCN is utilized to capture the spatial features of traffic data. Additionally, the LSTM is employed to extract the temporal features of the traffic data. The results carried out on PeMS dataset show that the proposed model consistently outperforms the competing models. Furthermore, our model can handle complex nonlinear traffic data and improve the accuracy of large-scale traffic prediction.

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
Fig. 10
Fig. 11

Similar content being viewed by others

Data availability

The datasets analyzed in this paper are available at https://pems.dot.ca.gov/.

References

  1. Mackenzie J, Roddick JF, Zito R (2019) An evaluation of HTM and LSTM for short-term arterial traffic flow prediction. IEEE Trans Intell Transp Syst 20:1847–1857. https://doi.org/10.1109/TITS.2018.2843349

    Article  Google Scholar 

  2. Vlahogianni EI, Karlaftis MG, Golias JC (2014) Short-term traffic forecasting: where we are and where we’re going. Transp Res Part C Emerg Technol 43:3–19. https://doi.org/10.1016/j.trc.2014.01.005

    Article  Google Scholar 

  3. Billy MW, Lester AH (2003) Modeling and forecasting vehicular traffic flow as a seasonal arima process: theoretical basis and empirical results. J Transp Eng 129:664–672

    Article  Google Scholar 

  4. Gaetano F, Chiara C, Natalia I (2016) Short-term speed predictions exploiting big data on large urban road networks. Transp Res Part C 73:183–201

    Article  Google Scholar 

  5. Ojeda LL, Kibangou AY, Wit C (2013) Adaptive Kalman filtering for multi-step ahead traffic flow prediction. In: American control conference (ACC), 2013

  6. Tang J, Chen X, Hu Z et al (2019) Traffic flow prediction based on combination of support vector machine and data denoising schemes. Phys AStatist Mech Appl 534:120642. https://doi.org/10.1016/j.physa.2019.03.007

    Article  Google Scholar 

  7. Sun J, Sun J, Chen P (2014) Use of support vector machine models for real-time prediction of crash risk on urban expressways. Transp Res Rec 2432:91–98. https://doi.org/10.3141/2432-11

    Article  Google Scholar 

  8. Wang J, Shi Q (2013) Short-term traffic speed forecasting hybrid model based on Chaos-Wavelet analysis-support vector machine theory. Transp Res Part C Emerg Technol 27:219–232. https://doi.org/10.1016/j.trc.2012.08.004

    Article  Google Scholar 

  9. Castillo E, Jiménez P, Menéndez JM, Nogal M (2013) A Bayesian method for estimating traffic flows based on plate scanning. Transportation 40:173–201. https://doi.org/10.1007/s11116-012-9443-4

    Article  Google Scholar 

  10. Cai P, Wang Y, Lu G et al (2016) A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting. Transp Res Part C Emerg Technol 62:21–34. https://doi.org/10.1016/j.trc.2015.11.002

    Article  Google Scholar 

  11. Yu B, Song X, Guan F et al (2016) k-nearest neighbor model for multiple-time-step prediction of short-term traffic condition. J Transp Eng 142:04016018. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000816

    Article  Google Scholar 

  12. Zheng Z, Su D (2014) Short-term traffic volume forecasting: a k-nearest neighbor approach enhanced by constrained linearly sewing principle component algorithm. Transp Res Part C: Emerg Technol 43:143–157. https://doi.org/10.1016/j.trc.2014.02.009

    Article  MathSciNet  Google Scholar 

  13. Ma X, Dai Z, He Z et al (2017) Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction. Sensors 17:818. https://doi.org/10.3390/s17040818

    Article  Google Scholar 

  14. Zheng F, Van Zuylen H (2013) Urban link travel time estimation based on sparse probe vehicle data. Trans Res Part C Emerg Technol 31:145–157. https://doi.org/10.1016/j.trc.2012.04.007

    Article  Google Scholar 

  15. Ye Q, Wong SC, Szeto WY (2010) Short-term traffic speed forecasting based on data recorded at irregular intervals. Transp Urban Sustain 601–601

  16. Liu Y, Liu Z, Lyu C, Ye J (2020) Attention-based deep ensemble net for large-scale online taxi-hailing demand prediction. IEEE Trans Intell Transp Syst 21:4798–4807. https://doi.org/10.1109/TITS.2019.2947145

    Article  Google Scholar 

  17. Zheng H, Lin F, Feng X, Chen Y (2021) A hybrid deep learning model with attention-based conv-LSTM networks for short-term traffic flow prediction. IEEE Trans Intell Transp Syst 22:6910–6920. https://doi.org/10.1109/TITS.2020.2997352

    Article  Google Scholar 

  18. Zhang Y, Cheng T, Ren Y (2019) A graph deep learning method for short-term traffic forecasting on large road networks. Comput Aided Civil Infrastruct Eng 34:877–896. https://doi.org/10.1111/mice.12450

    Article  Google Scholar 

  19. Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. arXiv:160902907 [cs, stat]

  20. Bogaerts T, Masegosa AD, Angarita-Zapata JS et al (2020) A graph CNN-LSTM neural network for short and long-term traffic forecasting based on trajectory data. Trans Res Part C Emer Technol 112:62–77. https://doi.org/10.1016/j.trc.2020.01.010

    Article  Google Scholar 

  21. Xie Z, Lv W, Huang S et al (2020) Sequential graph neural network for urban road traffic speed prediction. IEEE Access 8:63349–63358. https://doi.org/10.1109/ACCESS.2019.2915364

    Article  Google Scholar 

  22. Zhou X, Zhang Y, Li Z et al (2022) Large-scale cellular traffic prediction based on graph convolutional networks with transfer learning. Neural Comput Appl 34:5549–5559. https://doi.org/10.1007/s00521-021-06708-x

    Article  Google Scholar 

  23. Kerner BS (2004) Three-phase traffic theory and highway capacity. Physica A 333:379–440. https://doi.org/10.1016/j.physa.2003.10.017

    Article  MathSciNet  Google Scholar 

  24. Hu X, Hao X, Wang H et al (2019) Research on on-street temporary parking effects based on cellular automaton model under the framework of Kerner’s three-phase traffic theory. Phys A Stat Mech Appl. https://doi.org/10.1016/j.physa.2019.123725

    Article  Google Scholar 

  25. Du S, Li T, Gong X, Horng S-J (2020) A hybrid method for traffic flow forecasting using multimodal deep learning. IJCIS 13:85. https://doi.org/10.2991/ijcis.d.200120.001

    Article  Google Scholar 

  26. Hu X, Liu T, Hao X et al (2021) Research on the influence of bus bay on traffic flow in adjacent lane: simulations in the framework of Kerner’s three-phase traffic theory. Phys A Stat Mech Appl 563:125495. https://doi.org/10.1016/j.physa.2020.125495

    Article  Google Scholar 

  27. Han L, Du B, Sun L, et al (2021) Dynamic and Multi-faceted spatio-temporal deep learning for traffic speed forecasting. In: Proceedings of the 27th ACM SIGKDD conference on Knowledge Discovery & Data mining. ACM, Virtual Event Singapore, pp 547–555

  28. Hu X, Liu T, Hao X, Lin C (2022) Attention-based Conv-LSTM and Bi-LSTM networks for large-scale traffic speed prediction. J Supercomput 78:12686–12709. https://doi.org/10.1007/s11227-022-04386-7

    Article  Google Scholar 

  29. Shi X, Chen Z, Wang H, et al (2015) Convolutional LSTM network: a machine learning approach for precipitation nowcasting

  30. Ma X, Tao Z, Wang Y et al (2015) Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transp Res Part C Emerg Technol 54:187–197. https://doi.org/10.1016/j.trc.2015.03.014

    Article  Google Scholar 

  31. Brian P, Mandar K (2014) Adaptive traffic speed estimation. Procedia Comp Sci 32:356–363

    Article  Google Scholar 

  32. Hosseini MK, Talebpour A (2019) Traffic prediction using time-space diagram: a convolutional neural network approach. Transp Res Rec: J Transp Res Board 2673:425–435

    Article  Google Scholar 

  33. Lv Y, Duan Y, Kang W et al (2019) Traffic flow prediction with big data: a deep learning approach. IEEE Trans Int Transp Syst. https://doi.org/10.1109/TITS.2014.2345663

    Article  Google Scholar 

  34. Ke R, Li W, Cui Z, Wang Y (2020) Two-stream multi-channel convolutional neural network for multi-lane traffic speed prediction considering traffic volume impact. Transp Res Rec J Transp Res Board 2674:036119812091105

    Article  Google Scholar 

  35. Tampubolon H, Yang CL, Chan AS et al (2019) Optimized capsnet for traffic jam speed prediction using mobile sensor data under urban swarming transportation. Sensors 19(23):5277. https://doi.org/10.3390/s19235277

    Article  Google Scholar 

  36. Xiao Y, Yin H, Zhang Y et al (2021) A dual-stage attention-based Conv-LSTM network for spatio-temporal correlation and multivariate time series prediction. Int J Intell Syst 36:2036–2057. https://doi.org/10.1002/int.22370

    Article  Google Scholar 

  37. Shabarek A, Chien S, Hadri S (2020) Deep learning framework for freeway speed prediction in adverse weather. Transp Res Rec 2674:28–41. https://doi.org/10.1177/0361198120947421

    Article  Google Scholar 

  38. Hou Y, Edara P (2018) Network scale travel time prediction using deep learning. Transp Res Rec 2672:115–123. https://doi.org/10.1177/0361198118776139

    Article  Google Scholar 

  39. Hu X, Liu T, Hao X, Lin C (2022) Attention-based Conv-LSTM and Bi-LSTM networks for large-scale traffic speed prediction. J Supercomput. https://doi.org/10.1007/s11227-022-04386-7

    Article  Google Scholar 

  40. Azad R, Asadi-Aghbolaghi M, Fathy M, Escalera S (2019) Bi-directional ConvLSTM U-Net with densley connected convolutions

  41. Wu Y, Tan H, Qin L et al (2018) A hybrid deep learning based traffic flow prediction method and its understanding. Transp Res Part C Emerg Technol 90:166–180. https://doi.org/10.1016/j.trc.2018.03.001

    Article  Google Scholar 

  42. Lu B, Gan X, Jin H, et al (2020) spatiotemporal adaptive gated graph convolution network for urban traffic flow forecasting. In: Proceedings of the 29th ACM international conference on Information & Knowledge Management. ACM, Virtual Event Ireland, pp 1025–1034

  43. Golovnin O, Perevozchikov N (2021) E-STGCN: enhanced spatial-temporal graph convolutional network for road traffic forecasting. In: 2021 international conference on Information Technology and Nanotechnology (ITNT). IEEE, Samara, Russian Federation, pp 1–4

  44. Zhao L, Song Y, Zhang C et al (2020) T-GCN: a temporal graph convolutionalnetwork for traffic prediction. IEEE Trans Intell Transp Syst 21:3848–3858. https://doi.org/10.1109/TITS.2019.2935152

    Article  Google Scholar 

  45. Guo S, Lin Y, Feng N et al (2019) Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. AAAI 33:922–929. https://doi.org/10.1609/aaai.v33i01.3301922

    Article  Google Scholar 

  46. Cui Z, Henrickson K, Ke R, Wang Y (2020) Traffic graph convolutional recurrent neural network: a deep learning framework for network-scale traffic learning and forecasting. IEEE Trans Intell Transp Syst 21:4883–4894. https://doi.org/10.1109/TITS.2019.2950416

    Article  Google Scholar 

  47. Liu D, Xu X, Xu W, Zhu B (2021) Graph convolutional network: traffic speed prediction fused with traffic flow data. Sensors 21:6402. https://doi.org/10.3390/s21196402

    Article  Google Scholar 

  48. Zhu J, Tao C, Deng H, et al (2020) AST-GCN: attribute-augmented spatiotemporal graph convolutional network for traffic forecasting. arXiv:201111004 [cs]

  49. Chen C, Petty K, Skabardonis A et al (2001) Freeway performance measurement system: mining loop detector data. Transp Res Rec 1748:96–102. https://doi.org/10.3141/1748-12

    Article  Google Scholar 

  50. Huang R, Huang C, Liu Y, et al (2021) LSGCN: long short-term traffic prediction with graph convolutional networks. In: Proceedings of the twenty-ninth international joint conference on Artificial Intelligence

  51. Yin X, Wu G, Wei J et al (2021) Multi-stage attention spatial-temporal graph networks for traffic prediction. Neurocomputing 428:42–53. https://doi.org/10.1016/j.neucom.2020.11.038

    Article  Google Scholar 

Download references

Funding

This work was supported by the National Science Foundation of China (No. 52272344), and Jiangsu Provincial Key Research and Development Program (No. BE20187544).

Author information

Authors and Affiliations

  1. Nanjing University of Science and Technology, Nanjing, 210094, China

    Ziyi Su

  2. Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Southeast University, Nanjing, China

    Ziyi Su & Xiaojian Hu

  3. Jiangsu Key Laboratory of Urban ITS, Southeast University, Southeast University Road #2, Nanjing, 211189, China

    Tong Liu, Xiatong Hao & Xiaojian Hu

  4. National Demonstration Center for Experimental Road and Traffic Engineering Education (Southeast University), Nanjing, 211189, China

    Xiaojian Hu

Authors
  1. Ziyi Su
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiatong Hao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xiaojian Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

The authors confirm contribution to the paper as follows: study conception and design were contributed by ZS, XH, and TL; modeling and experimentation were contributed by TL; analysis and interpretation of results were contributed by TL and Xiaojian Hu; draft manuscript preparation was contributed by TL and XH. All authors reviewed the results and approved the final version of the manuscript.

Corresponding author

Correspondence to Tong Liu.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This declaration is not applicable.

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

Su, Z., Liu, T., Hao, X. et al. Spatial-temporal graph convolutional networks for traffic flow prediction considering multiple traffic parameters. J Supercomput 79, 18293–18312 (2023). https://doi.org/10.1007/s11227-023-05383-0

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-023-05383-0

Keywords

Search

Navigation