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.
Similar content being viewed by others
Data availability
The datasets analyzed in this paper are available at https://pems.dot.ca.gov/.
References
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
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
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
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
Ojeda LL, Kibangou AY, Wit C (2013) Adaptive Kalman filtering for multi-step ahead traffic flow prediction. In: American control conference (ACC), 2013
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
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
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
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
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
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
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
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
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
Ye Q, Wong SC, Szeto WY (2010) Short-term traffic speed forecasting based on data recorded at irregular intervals. Transp Urban Sustain 601–601
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
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
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
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. arXiv:160902907 [cs, stat]
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
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
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
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
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
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
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
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
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
Shi X, Chen Z, Wang H, et al (2015) Convolutional LSTM network: a machine learning approach for precipitation nowcasting
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
Brian P, Mandar K (2014) Adaptive traffic speed estimation. Procedia Comp Sci 32:356–363
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
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
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
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
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
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
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
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
Azad R, Asadi-Aghbolaghi M, Fathy M, Escalera S (2019) Bi-directional ConvLSTM U-Net with densley connected convolutions
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
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
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
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
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
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
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
Zhu J, Tao C, Deng H, et al (2020) AST-GCN: attribute-augmented spatiotemporal graph convolutional network for traffic forecasting. arXiv:201111004 [cs]
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
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
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
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
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
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.
About this article
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
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-023-05383-0