Abstract
Accurate prediction of short-term passengers’ origin and destination (OD) demands is key to efficient operation and management of urban rail transit (URT), especially in the case of congestion or an incident. However, short-term OD demand forecasting is more challenging than passenger flow forecasting, due to its uncertainty and high dimensions. So far, most OD prediction models capture the spatio-temporal dependencies of OD flow by means of training models on historical data, but what characteristics and laws influence the performance of OD prediction are still unknown. In this paper, we propose temporal Pearson correlation coefficients and approximate entropy, as well as spatial correlations, as indicators to reflect the inherent time–space correlations and complexity of the OD flow. Then, by analyzing automatic fare collection data of the Beijing and Shanghai URT system, this paper deeply discusses the relationships between the spatio-temporal correlations and complexity of the OD flow and the predictive performances of different models with regard to different intervals. Finally, this paper proposes the predictable problem of travel demands and points out that the spatial correlations of the OD matrix are more important than the temporal correlations and complexity in the short-term prediction of travel demands. In particular, the number of principal components of the OD flow can be a key indicator to measure the forecasting performance of a model. A reasonable interval is very important for short-term OD forecasting, and in the Beijing URT system, 30 min is a preferable choice for workdays and 50 min for weekends. All these findings are beneficial to guide users to build a suitable model or improve the existing model to obtain better prediction performances.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Boukerche, A., Tao, Y., Sun, P.: Artificial intelligence-based vehicular traffic flow prediction methods for supporting intelligent transportation systems. Comput. Netw. 182, 107484 (2020). https://doi.org/10.1016/j.comnet.2020.107484
Castroneto, M., Jeong, Y.S., KeeJeong, M., Han, L.D.: Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions. Expert Syst. Appl. 36(3), 6164–6173 (2009). https://doi.org/10.1016/j.eswa.2008.07.069
Cui, Z.Y., Ke, R.M., Pu, Z.Y., Wang, Y.H.: Stacked bidirectional and unidirectional LSTM recurrent neural network for forecasting network-wide traffic state with missing values. Transp Res. C: Emerg. Technol. 118, 10674 (2020). https://doi.org/10.1016/j.trc.2020.102674
Cunningham, J.P., Ghahramani, Z.: Linear dimensionality reduction: survey, insights, and generalizations. J. Mach. Learn. Res. 16(1), 2859–2900 (2015)
Djukic, T., Flötteröd, G., Lint, H.V., Hoogendoorn, S.: Efficient real time OD matrix estimation based on principal component analysis. 2012 15th International IEEE Conference on Intelligent Transportation Systems 115–121(2012). https://doi.org/10.1109/ITSC.2012.6338720
Feng, J., Lin, Z.Q., Xia, T., Sun, F.: A sequential convolution network for population flow prediction with explicitly correlation modelling. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence. (2020).
Fu, R., Zhang, Z., Li, L. (2016) Using LSTM and GRU neural network methods for traffic flow prediction. In: 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC) 324–328 (2016). https://doi.org/10.1109/YAC.2016.7804912.
Guo, G., Zhang, T.Q.: A residual spatio-temporal architecture for travel demand forecasting. Transp. Res. C: Emerg. Technol. 115, 102639 (2020). https://doi.org/10.1016/j.trc.2020.102639
Hauke, J., Kossowski, T.: Comparison of values of Pearson’s and Spearman’s correlation coefficients on the same sets of data. Quaest. Geogr. 30(2), 87–93 (2011). https://doi.org/10.2478/v10117-011-0021-1
Kachroo, P., Ozbay, B., Narayanan, A.: Investigating the use of Kalman filtering approaches for dynamic origin-destination trip table estimation. in Proceedings IEEE Southeastcon '97. 'Engineering the New Century. (2002). https://doi.org/10.1109/SECON.1997.598628
Li, B.: Bayesian inference for origin-destination matrices of transport networks using the EM algorithm. Technometrics 47(4), 399–408 (2005). https://doi.org/10.1198/004017005000000283
Li, S.W., Chen, T., Wang, L., Ming, C.H.: Effective tourist volume forecasting supported by PCA and improved BPNN using Baidu index. Tour. Manag. 68, 116–126 (2018). https://doi.org/10.1016/j.tourman.2018.03.006
Li, C., Huang, J.L., Wang, B., Zhou, Y.Y., Bai, Y.Y., Chen, Y.Y.: Spatial-temporal correlation prediction modeling of origin-destination passenger flow under urban rail transit emergency conditions. IEEE Access 7, 162353–162365 (2019). https://doi.org/10.1061/(ASCE)0733-947X(1997)123:4(261)
Liu, L.B., Chen, J.W., Wu, H.F., Zhen, J.J., Li, G.B., Lin, L.: Physical-virtual collaboration modeling for intra-and inter-station metro ridership prediction. IEEE Transactions on Intelligent Transportation Systems, in press. (2020) https://doi.org/10.1109/TITS.2020.3036057
Liu, L.B., Qiu, Z.L., Li, G.B., Wang, Q., Ouyang, W.L., Lin, L., Contextualized spatial-temporal network for taxi origin-destination demand prediction. IEEE Transactions on Intelligent Transportation Systems. (99), 1–13(2019). https://doi.org/10.1109/TITS.2019.2915525
Luo, X.L., Li, D.Y., Yang, Y., Zhang, S.R.: Spatiotemporal traffic flow prediction with KNN and LSTM. J. Adv. Transp. 2019, 1–10 (2019)
Manley, E., Cheng, T.: Exploring the role of spatial cognition in predicting urban traffic flow through agent-based modelling. Transp. Res. A: Policy Pract 109, 14–23 (2018). https://doi.org/10.1016/j.tra.2018.01.020
Perrakis, K., Karlis, D., Cools, M., Janssens, D., Vanhoof, K., Wets, K.: A Bayesian approach for modeling origin-destination matrices. Transp. Res. A-Policy Pract. 46(1), 200–212 (2012). https://doi.org/10.1016/j.tra.2011.06.005
Pincus, S.M.: Approximate entropy (ApEn) as a complexity measure. Chaos 5(1), 110–117 (1995). https://doi.org/10.1063/1.16609
Shi, H.Z., Yao, Q.M., Guo, Q., Li, Y.G., Zhang, L.Y., Ye, J.P., Li, Y., Liu, Y.: Predicting origin-destination flow via multi-perspective graph convolutional network. in 2020 IEEE 36th International Conference on Data Engineering (ICDE). (2020). https://doi.org/10.1109/ICDE48307.2020.00178
Smith, B.L., Demetsky, M.J.: Traffic flow forecasting comparison of modeling approches. J. Transp. Eng.-Asce. 123(4), 261–266 (1997)
Srinivasan, V., Eswaran, C., Sriraam, N.: Approximate entropy-based epileptic EEG detection using artificial neural networks. IEEE Trans. Inf. Technol. Biomed. 11(3), 288–295 (2007). https://doi.org/10.1109/TITB.2006.884369
Starczewski, J., Grzesica, D., Jirsa, V.: Modelling bicycle demand using autoregressive and moving average models. IOP Conference Series: Materials Science and Engineering. 471: 062038(2019)
Tedjopurnomo, D.A., Bao, Z.F., Zheng, B.H., Choudhury, F., Qin, A.K. (2020) A survey on modern deep neural network for traffic prediction: trends, methods and challenges. IEEE Transactions on Knowledge and Data Engineering. https://doi.org/10.1109/TKDE.2020.3001195
Toqué, F., Côme, E., El Mahrsi, M.K., Oukhellou, L.: Forecasting dynamic public transport origin-destination matrices with long-short term memory recurrent neural networks. In: International Conference on Intelligent Transportation Systems. (2016). https://doi.org/10.1109/ITSC.2016.7795689
Wang, Y.D., Yin, H.Z., Chen, H.X., Wo, T.Y, Xu, J., Zheng, K.: Origin-destination matrix prediction via graph convolution: a new perspective of passenger demand modeling. In: Knowledge Discovery and Data Mining. (2019).
Wong, K., Yu, S.A.: Estimation of origin–destination matrices for mass event: a case of Macau Grand Prix. J. King Saud Univ.-Sci. 23(3), 281–292 (2011). https://doi.org/10.1016/j.jksus.2010.12.008
Woo, S., Tak, S., Yeo, H.: Data-driven prediction methodology of origin-destination demand in large network for real-time service. Transp. Res. Rec. J. Transp. Res. Board. 2567, 47–56 (2016)
Xi, X., Kaan, O., Li, J., Chen, F.: Dynamic prediction of origin-destination flows using fusion line graph convolutional networks. Learning (2019). https://doi.org/10.48550/arXiv.1905.00406
Xie, P., Li, T.R., Liu, J., Du, S.D., Yang, X., Zhang, J.B.: Urban flow prediction from spatiotemporal data using machine learning: a survey. Inf. Fusion. 59, 1–12 (2020). https://doi.org/10.1016/j.inffus.2020.01.002
Xu, S.J., Chan, H.K., Zhang, T.T.: Forecasting the demand of the aviation industry using hybrid time series SARIMA-SVR approach. Transp. Res. E 122, 169–180 (2019a). https://doi.org/10.1016/j.tre.2018.12.005
Xu, G., Li, Y.G., Wang, L.Y., Zhang, L.Y.: Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting. Natl. Conf. Artif. Intell. (2019b). https://doi.org/10.1609/aaai.v33i01.33013656
Yao, X.M., Zhao, P., Yu, D.D.: Dynamic origin-destination matrix estimation for urban rail transit based on averaging strategy. J. Jilin Univ. (2016). https://doi.org/10.13229/j.cnki.jdxbgxb201601014
Yu, B., Yin, B., Zhu, Z.: Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: Twenty-Seventh International Joint Conference on Artificial Intelligence IJCAI-18. (2018)
Yuan, H., Li, G.L.: A survey of traffic prediction: from spatio-temporal data to intelligent transportation. Data Sci. Eng. 6(1), 63–85 (2021)
Zhang, W.D., Chen, F., Wang, Z.J., Wang, B., Wang, T.: Similarity measurement of metro travel rules based on multrtime granularities. J. China Railw. Soc. 40(04), 9–17 (2018). https://doi.org/10.3969/j.issn.1001-8360.2018.04.002
Zhang, Y., Cheng, T., Ren, Y.B., Xie, K.: A novel residual graph convolution deep learning model for short-term network-based traffic forecasting. Int. J. Geogr. Inf. (2019a). https://doi.org/10.1080/13658816.2019b.1697879
Zhang, J.L., Feng, C., Wang, Z.J.: Short-term origin-destination forecasting in urban rail transit based on attraction degree. IEEE Access. 7133452–133462 (2019b)
Zhang, J.L., Che, H.S., Chen, F., Ma, W., He, Z.B.: Short-term origin-destination demand prediction in urban rail transit systems: a channel-wise attentive split-convolutional neural network method. Transp. Res. C: Emerg. Technol. (2021a). https://doi.org/10.1016/j.trc.2020.102928
Zhang, K., He, F., Zhang, Z.C., Lin, X., Li, M.: Graph attention temporal convolutional network for traffic speed forecasting on road networks. Transp. B-Transp. Dyn. 9(1), 153–171 (2021b). https://doi.org/10.1080/21680566.2020.1822765
Zhao, L., Song, Y.J., Zhang, C., Liu, Y., Wang, P., Lin, T., Deng, M., Li, H.F.: T-GCN: a temporal graph convolutional network for traffic prediction. IEEE Trans. Intell. Transp. Syst. 99, 1–11 (2019). https://doi.org/10.1109/TITS.2019.2935152
Acknowledgements
This research was supported in part by the National Natural Science Foundation of China (No. 71861017), and in part by the Innovation-Driven Project of Central South University (Grant number 2020CX013).
Author information
Authors and Affiliations
Contributions
FY Program implementation and revising papers. CS Contents design and paper writing. QQ Paper writing and algorithm verification. WW. Data analysis and processing. MH Design of algorithm. MH Idea and construction of paper. JL Writing and revising papers.
Corresponding author
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 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
Yang, F., Shuai, C., Qian, Q. et al. Predictability of short-term passengers’ origin and destination demands in urban rail transit. Transportation 50, 2375–2401 (2023). https://doi.org/10.1007/s11116-022-10313-9
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11116-022-10313-9