Skip to main content
SpringerLink
Log in

Dynamic temporal position observant graph neural network for traffic forecasting

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Spatio-temporal forecasting has several applications in neurology, climate, and transportation. One classic example of such a learning assignment is traffic forecasting. The task is complex because of traffic’s non-linearity and dynamic nature with shifting road conditions, complex geographic dependence, and the inherent challenges of long-term forecasting. We propose the Dynamic Temporal Position Observant Graph Neural Network (DTPO-GNN). DTPO-GNN considers positional awareness, spatial and temporal reliance on traffic flow for forecasting future traffic speeds. Specifically, DTPO-GNN employs positional awareness via reference nodes to collect global knowledge of graph structure and diffusion convolution employing random walks to gather local information about the structural properties of traffic networks. A controlled sample encoder-decoder architecture and two-way random walks across the graph are used to capture structural and temporal dependency. Combining three large-scale road network traffic statistics from the actual world, we observe a consistent improvement of 11-13 % above baselines from the most recent research.

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

Similar content being viewed by others

Data Availibility Statement

The data used in the experiments of this work are included or references are provided in the article. No additional data are required.

References

  1. Lippi M, Bertini M, Frasconi P (2013) Short-term traffic flow forecasting: An experimental comparison of time-series analysis and supervised learning. IEEE Trans Intell Transpo Syst 14(2):871–882

    Article  Google Scholar 

  2. Crainic TG, Kim KH (2007) Intermodal transportation. Handbooks Oper Res Manag Sci 14:467–537

    Article  Google Scholar 

  3. Lv Y, Duan Y, Kang W, Li Z, Wang F-Y (2014) Traffic flow prediction with big data: a deep learning approach. IEEE Trans Intell Transpo Syst 16(2):865–873

    Google Scholar 

  4. Yu, R, Li, Y, Shahabi, C, Demiryurek, U, Liu, Y (2017) Deep learning: A generic approach for extreme condition traffic forecasting. In: Proceedings of the 2017 SIAM international conference on data mining, SIAM, pp 777–785

  5. Ma X, Dai Z, He Z, Ma J, Wang Y, Wang Y (2017) Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction. Sensors 17(4):818

  6. Wu, Y, Tan, H (2016) Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework. arXiv:1612.01022

  7. Defferrard, M, Bresson, X, Vandergheynst, P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems 29

  8. Bruna, J, Zaremba, W, Szlam, A, LeCun, Y (2013) Spectral networks and locally connected networks on graphs. arXiv:1312.6203

  9. Diao Z, Zhang D, Wang X, Xie K, He S, Lu X, Li Y (2018) A hybrid model for short-term traffic volume prediction in massive transportation systems. IEEE Trans Intell Transpo Syst 20(3):935-946

    Article  Google Scholar 

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

    Article  Google Scholar 

  11. Chen R, Liang C-Y, Hong W-C, Gu D-X (2015) Forecasting holiday daily tourist flow based on seasonal support vector regression with adaptive genetic algorithm. Appl Soft Comput 26:435–443

    Article  Google Scholar 

  12. Zhang, J, Zheng, Y, Qi, D, Li, R, Yi, X (2016) Dnn-based prediction model for spatio-temporal data. In: Proceedings of the 24th ACM SIGSPATIAL international conference on advances in geographic information systems, pp 1–4

  13. Zhang, J, Zheng, Y, Qi, D (2017) Deep spatio-temporal residual networks for citywide crowd flows prediction. In: Proceedings of the AAAI conference on artificial intelligence, vol. 31

  14. Yu, B, Yin, H, Zhu, Z (2017) Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv:1709.04875

  15. Te, G, Hu, W, Zheng, A, Guo, Z (2018) Rgcnn: regularized graph cnn for point cloud segmentation. In: Proceedings of the 26th ACM international conference on multimedia, pp 746–754

  16. Mourad, L, Shen, Y (2023) Spatio-temporal graph mixformer for traffic forecasting. Expert Syst Appl, 120281

  17. Yin, X, Li, F, Wu, G, Wang, P, Shen, Y, Qi, H, Yin, B (2021) Stnn: A spatial-temporal graph neural network for traffic prediction. In: 2021 IEEE 27th international conference on parallel and distributed systems (ICPADS), IEEE, pp 146–152

  18. Lv M, Chen L, Wu X, Chen G (2015) A road congestion detection system using undedicated mobile phones. IEEE Trans Intell Transpo Syst 16(6):3060–3072

    Article  Google Scholar 

  19. Liu Z, Li Z, Li M, Xing W, Lu D (2016) Mining road network correlation for traffic estimation via compressive sensing. IEEE Trans Intell Transpo Syst 17(7):1880–1893

    Article  Google Scholar 

  20. Shao W, Chen L (2018) License plate recognition data-based traffic volume estimation using collaborative tensor decomposition. IEEE Trans Intell Transpo Syst 19(11):3439–3448

    Article  Google Scholar 

  21. Hamed MM, Al-Masaeid HR, Said ZMB (1995) Short-term prediction of traffic volume in urban arterials. J Transpo Eng 121(3):249–254

    Article  Google Scholar 

  22. Cai P, Wang Y, Lu G, Chen P, Ding C, Sun J (2016) A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting. Transpo Res Part C Emerg Technol 62:21-34

    Article  Google Scholar 

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

    Article  Google Scholar 

  24. Min W, Wynter L (2011) Real-time road traffic prediction with spatio-temporal correlations. Transpo Res Part C Emerg Technol 19(4):606–616

    Article  Google Scholar 

  25. Yu H, Wu Z, Wang S, Wang Y, Ma X (2017) Spatiotemporal recurrent convolutional networks for traffic prediction in transportation networks. Sensors 17(7):1501

    Article  Google Scholar 

  26. Geng X, Li Y, Wang L, Zhang L, Yang Q, Ye J, Liu Y (2019) Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting. Proceedings of the AAAI conference on artificial intelligence 33:3656–3663

  27. Li, Y, Yu, R, Shahabi, C, Liu, Y (2017) Diffusion convolutional recurrent neural network: data-driven traffic forecasting. In: International conference on learning representations

  28. Zhu J, Wang Q, Tao C, Deng H, Zhao L, Li H (2021) Ast-gcn: Attribute-augmented spatiotemporal graph convolutional network for traffic forecasting. IEEE Access 9:35973–35983

    Article  Google Scholar 

  29. Yang, H, Liu, C, Zhu, M, Ban, X, Wang, Y (2021) How fast you will drive? predicting speed of customized paths by deep neural network. IEEE Transactions on Intelligent Transportation Systems

  30. Wu, Z, Pan, S, Long, G, Jiang, J, Chang, X, Zhang, C (2020) Connecting the dots: Multivariate time series forecasting with graph neural networks. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pp 753–763

  31. Zheng C, Fan X, Wang C, Qi J (2020) Gman: A graph multi-attention network for traffic prediction. Proceedings of the AAAI conference on artificial intelligence 34:1234–1241

    Article  Google Scholar 

  32. Guo S, Lin Y, Feng N, Song C, Wan H (2019) Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. Proceedings of the AAAI conference on artificial intelligence 33:922–929

    Article  Google Scholar 

  33. Shin, Y, Yoon, Y (2020) Incorporating dynamicity of transportation network with multi-weight traffic graph convolutional network for traffic forecasting. IEEE Transactions on Intelligent Transportation Systems

  34. Chen W, Chen L, Xie Y, Cao W, Gao Y, Feng X (2020) Multi-range attentive bicomponent graph convolutional network for traffic forecasting. Proceedings of the AAAI conference on artificial intelligence 34:3529–3536

    Article  Google Scholar 

  35. Cui Z, Ke R, Pu Z, Ma X, Wang Y (2020) Learning traffic as a graph: A gated graph wavelet recurrent neural network for network-scale traffic prediction. Transpo Res Part C Emerg Technol 115:102620

    Article  Google Scholar 

  36. Battaglia, PW, Hamrick, JB, Bapst, V, Sanchez-Gonzalez, A, Zambaldi, V, Malinowski, M, Tacchetti, A, Raposo, D, Santoro, A, Faulkner, R, et al (2018) Relational inductive biases, deep learning, and graph networks. arXiv:1806.01261

  37. Waikhom L, Singh Y, Patgiri R (2023) Po-gnn: Position-observant inductive graph neural networks for position-based prediction. Inf Process Manag 60(3):103333

    Article  Google Scholar 

  38. Zhang J-X, Chen D-B, Dong Q, Zhao Z-D (2016) Identifying a set of influential spreaders in complex networks. Sci Rep 6(1):1–10

    Google Scholar 

  39. Velickovic P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2018) Graph attention networks. Stat 1050:4

    Google Scholar 

  40. Xu, J, Li, Z, Du, B, Zhang, M, Liu, J (2020) Reluplex made more practical: Leaky relu. In: 2020 IEEE symposium on computers and communications (ISCC), IEEE, pp 1–7

  41. Teng, S-H, et al (2016) Scalable algorithms for data and network analysis. Found Trends®Theoretic Comput Sci 12(1-2), 1–274

  42. Chen C, Petty K, Skabardonis A, Varaiya P, Jia Z (2001) Freeway performance measurement system: mining loop detector data. Transpo Res Rec 1748(1):96–102

    Article  Google Scholar 

  43. Sutskever, I, Vinyals, O, Le, QV (2014) Sequence to sequence learning with neural networks. Advances in neural information processing systems 27

  44. Wu, Z, Pan, S, Long, G, Jiang, J, Zhang, C (2019) Graph wavenet for deep spatial-temporal graph modeling. In: The 28th International Joint Conference on Artificial Intelligence (IJCAI). International Joint Conferences on Artificial Intelligence Organization

  45. Xie, Y, Xiong, Y, Zhu, Y (2020) Sast-gnn: a self-attention based spatio-temporal graph neural network for traffic prediction. In: Database systems for advanced applications: 25th international conference, DASFAA 2020, Jeju, South Korea, September 24–27, 2020, Proceedings, Part I 25, Springer, pp 707–714

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science & Engineering, National Institute of Technology Silchar, Silchar, 788010, Assam, India

    Lilapati Waikhom, Ripon Patgiri & Laiphrakpam Dolendro Singh

Authors
  1. Lilapati Waikhom
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ripon Patgiri
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Laiphrakpam Dolendro Singh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lilapati Waikhom.

Ethics declarations

Conflicts of interest

The authors declare 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

Waikhom, L., Patgiri, R. & Singh, L.D. Dynamic temporal position observant graph neural network for traffic forecasting. Appl Intell 53, 23166–23178 (2023). https://doi.org/10.1007/s10489-023-04737-8

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-023-04737-8

Keywords

Search

Navigation