Multi-Time-Scale Modeling for Day-Ahead Forecasting of Passenger Travel-Time and Destinations Distribution

Yiren Liu; Lishuai Li; Yang Zhao; Yining Dong; S. Joe Qin

doi:10.1109/JAS.2026.126170

Volume 13 Issue 7

Jul. 2026

IEEE/CAA Journal of Automatica Sinica

JCR Impact Factor: 18.3, Top 1 (SCI Q1)

CiteScore: 28.2, Top 1% (Q1)
Google Scholar h5-index: 95， TOP 5

Turn off MathJax

Article Contents

Article Navigation > IEEE/CAA Journal of Automatica Sinica > 2026 > 13(7): 1610-1625

Y. Liu, L. Li, Y. Zhao, Y. Dong, and S. J. Qin, “Multi-time-scale modeling for day-ahead forecasting of passenger travel-time and destinations distribution,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 7, pp. 1610–1625, Jul. 2026. doi: 10.1109/JAS.2026.126170

Citation:

Y. Liu, L. Li, Y. Zhao, Y. Dong, and S. J. Qin, “Multi-time-scale modeling for day-ahead forecasting of passenger travel-time and destinations distribution,” IEEE/CAA J. Autom. Sinica, vol. 13, no. 7, pp. 1610–1625, Jul. 2026. doi: 10.1109/JAS.2026.126170

Citation:

PDF( 9082 KB)

Multi-Time-Scale Modeling for Day-Ahead Forecasting of Passenger Travel-Time and Destinations Distribution

doi: 10.1109/JAS.2026.126170

Funds: This work was supported in part by a Shenzhen-Hong Kong-Macau Science and Technology Project Category C (9240086), a grant from ITF - Guangdong-Hong Kong Technology Cooperation Funding Scheme (GHP/145/20), and a Collaborative Research Fund by RGC of Hong Kong (C1143-20G)

More Information

Author Bio:
Yiren Liu is currently a Postdoctoral Researcher at School of Data Science, Lingnan University, Hong Kong, China. He earned a Bachelor’s degree in software engineering from Shandong University, a Master’s degree in financial engineering from the University of Southern California, Los Angeles, California, USA, and a Ph.D. from the School of Data Science at the City University of Hong Kong, Hong Kong, China. His research interests encompass intelligent traffic systems, high-dimensional time series modeling, and sparse statistical learning

Lishuai Li is a Professor in the Department of Data Science and Department of Mechanical Engineering (by courtesy) at the City University of Hong Kong, Hong Kong, China. Her research is in the interdisciplinary field of intelligent transportation systems and data science. Prof. Li is a Fellow of the Royal Aeronautical Society and a senior member of IEEE. Prof. Li received her Ph.D. and M.Sc. from the Department of Aeronautics and Astronautics at Massachusetts Institute of Technology (MIT), Cambridge, Massachusetts, USA, and her B.Eng. in aircraft design and engineering from Fudan University

Yang Zhao is currently an Associate Professor at the School of Public Health (Shenzhen) of Sun Yat-sen University. Prior to joining Sun Yat-sen University, she worked as Scientific Officer at Centre for Systems Informatics Engineering of the City University of Hong Kong, Hong Kong, China, where she obtained her Ph.D. degree in 2015. She is specialized in applied statistics and machine learning, particularly their applications to facilitate system health monitoring, improve integrated decision support system, and enhance healthcare management

Yining Dong is currently an Assistant Professor in the Department of Data Science at City University of Hong Kong (CityU), Hong Kong, China. She received her Ph.D. degree in electrical engineering from University of Southern California, Los Angeles, California, USA, in 2016, and her B.Eng. degree in electronic engineering from Tsinghua University in 2011. Before joining CityU, she was a Post-doc in electrical engineering at Stanford University, Stanford, California, USA. Her research interests are process data analytics, high-dimensional time series modeling, statistical machine learning and smart manufacturing

S. Joe Qin (Fellow, IEEE) obtained his B.S. and M.S. degrees in automatic control from Tsinghua University and his Ph.D. degree in chemical engineering from University of Maryland at College Park, USA. He is currently Wai Kee Kau Chair Professor of data science and President of Lingnan University in Hong Kong, China. His research interests include data science and analytics, process monitoring, model predictive control, system identification, and smart cities. Dr. Qin is a member of the European Academy of Sciences and Arts, a Fellow of the U.S. National Academy of Inventors, IFAC, AIChE, and IEEE. He is the recipient of 2022 IEEE Control Systems Society Transition to Practice Award, the 2022 CAST Computing Award by AIChE, the U.S. NSF CAREER Award, and NSF-China Outstanding Young Investigator Award. His h-indices for Web of Science, SCOPUS, and Google Scholar are 72, 77, and 91, respectively, with over 45 000 Google Scholar citations. Dr. Qin’s research interests include data science and analytics, machine learning, process monitoring, model predictive control, system identification, smart manufacturing, smart cities, and predictive maintenance
Corresponding author: S. Joe Qin, e-mail: joeqin@LN.edu.hk
Received Date: 2024-09-03
Revised Date: 2026-04-22
Accepted Date: 2026-04-29

Available Online: 2026-07-22

Abstract

Abstract

It is crucial to forecast passenger flows for optimizing subway operations and improving travel experience for passengers. While traditional methods usually estimate the average travel time of passengers, this study delves into the modeling and prediction travel time distributions from all origin stations to all destinations. We construct a matrix that includes the travel time and destination for passengers originating from each station at a time slot. We propose a travel-time and destinations distribution modeling approach for one-day ahead predictions for each origin station. By quantifying the multi-time-scale similarities of week-to-week, day-to-day, and time-to-time, we unveil the underlying mechanisms of passengers’ travel patterns, revealing predictable and repetitive mobility behaviors. We validate the proposed model using real subway passenger data sets and demonstrate its superior performance in predicting the passenger flows and the associated travel time.
- Flow patterns,
- passenger flow modeling,
- short-term forecasting,
- subway data analytics,
- travel time distribution

FullText(HTML)

References(45)

References

[1]	S. Dasgupta, S. Lall, and D. Wheeler, “Subways and CO₂ emissions: A global analysis with satellite data,” Sci. Total Environ., vol. 883, Art. no. 163691, Jul. 2023. doi: 10.1016/j.scitotenv.2023.163691
[2]	Metrobits. org. (2023). World Metro Database.[Online]. Available: https://mic-ro.com/metro/table.
[3]	R. Li, Y. Huang, and J. Wang, “Long-term traffic volume prediction based on K-means Gaussian interval type-2 fuzzy sets,” IEEE/CAA J. Autom. Sinica, vol. 6, no. 6, pp. 1344–1351, Nov. 2019. doi: 10.1109/jas.2019.1911723
[4]	G. Xiong, F. Zhu, X. Liu, X. Dong, W. Huang, S. Chen, and K. Zhao, “Cyber-physical-social system in intelligent transportation,” IEEE/CAA J. Autom. Sinica, vol. 2, no. 3, pp. 320–333, Jul. 2015.
[5]	L. Zhu, F. R. Yu, Y. Wang, B. Ning, and T. Tang, “Big data analytics in intelligent transportation systems: A survey,” IEEE Trans. Intell. Transp. Syst., vol. 20, no. 1, pp. 383–398, Jan. 2019. doi: 10.1109/TITS.2018.2815678
[6]	M. Alam, J. Ferreira, and J. Fonseca, “Introduction to intelligent transportation systems,” in Intelligent Transportation Systems: Dependable Vehicular Communications for Improved Road Safety, M. Alam, J. Ferreira, and J. Fonseca, Ed. Cham: Springer, 2016, pp. 1−17.
[7]	Y. Sun, B. Leng, and W. Guan, “A novel wavelet-SVM short-time passenger flow prediction in Beijing subway system,” Neurocomputing, vol. 166, pp. 109–121, Oct. 2015. doi: 10.1016/j.neucom.2015.03.085
[8]	L. Liu, Y. Zhu, G. Li, Z. Wu, L. Bai, and L. Lin, “Online metro origin-destination prediction via heterogeneous information aggregation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 3, pp. 3574–3589, Mar. 2023. doi: 10.1109/tpami.2022.3178184
[9]	E. Hussain, A. Bhaskar, and E. Chung, “Transit OD matrix estimation using smartcard data: Recent developments and future research challenges,” Transp. Res. Part C: Emerg. Technol., vol. 125, Art. no. 103044, Apr. 2021. doi: 10.1016/j.trc.2021.103044
[10]	J. Zhang, H. Che, F. Chen, W. Ma, and Z. He, “Short-term origin-destination demand prediction in urban rail transit systems: A channel-wise attentive split-convolutional neural network method,” Transp. Res. Part C: Emerg. Technol., vol. 124, Art. no. 102928, Mar. 2021. doi: 10.1016/j.trc.2020.102928
[11]	Z. Cheng, M. Trépanier, and L. Sun, “Real-time forecasting of metro origin-destination matrices with high-order weighted dynamic mode decomposition,” Transp. Sci., vol. 56, no. 4, pp. 904–918, Feb. 2022. doi: 10.1287/trsc.2022.1128
[12]	J. Ye, J. Zhao, F. Zheng, and C. Xu, “Completion and augmentation-based spatiotemporal deep learning approach for short-term metro origin-destination matrix prediction under limited observable data,” Neural Comput. Appl., vol. 35, no. 4, pp. 3325–3341, Feb. 2023. doi: 10.1007/s00521-022-07866-2
[13]	B. M. Williams and L. A. Hoel, “Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: Theoretical basis and empirical results,” J. Transp. Eng., vol. 129, no. 6, pp. 664–672, Oct. 2003. doi: 10.1061/(ASCE)0733-947X(2003)129:6(664)
[14]	S. V. Kumar and L. Vanajakshi, “Short-term traffic flow prediction using seasonal ARIMA model with limited input data,” Eur. Transp. Res. Rev., vol. 7, no. 3, Art. no. 21, 2015. doi: 10.1007/s12544-015-0170-8
[15]	D. Li, C. Zhang, and J. Cao, “Short-term passenger flow prediction of a passageway in a subway station using time space correlations between multi sites,” IEEE Access, vol. 8, pp. 72471–72484, 2020. doi: 10.1109/ACCESS.2020.2988030
[16]	E. Chen, Z. Ye, C. Wang, and M. Xu, “Subway passenger flow prediction for special events using smart card data,” IEEE Trans. Intell. Transp. Syst., vol. 21, no. 3, pp. 1109–1120, Mar. 2020. doi: 10.1109/TITS.2019.2902405
[17]	F. Zheng, J. Zhao, J. Ye, X. Gao, K. Ye, and C. Xu, “Metro OD matrix prediction based on multi-view passenger flow evolution trend modeling,” IEEE Trans. Big Data, vol. 9, no. 3, pp. 991–1003, Jun. 2023. doi: 10.1109/TBDATA.2022.3229836
[18]	F. C. Pereira, F. Rodrigues, and M. Ben-Akiva, “Using data from the web to predict public transport arrivals under special events scenarios,” J. Intell. Transp. Syst., vol. 19, no. 3, pp. 273–288, Jul. 2015. doi: 10.1080/15472450.2013.868284
[19]	P. J. Brockwell and R. A. Davis, Introduction to Time Series and Forecasting. 2nd ed. New York, NY, USA: Springer, 2002.
[20]	B. Ghosh, B. Basu, and M. O’Mahony, “Multivariate short-term traffic flow forecasting using time-series analysis,” IEEE Trans. Intell. Transp. Syst., vol. 10, no. 2, pp. 246–254, Jun. 2009. doi: 10.1109/TITS.2009.2021448
[21]	G. Yu and C. Zhang, “Switching ARIMA model based forecasting for traffic flow,” in Proc. IEEE Int. Conf. Acoustics, Speech, and Signal Processing, Montreal, Canada, 2004, Art. no. ii–429.
[22]	L. Tang, Y. Zhao, J. Cabrera, J. Ma, and K. L. Tsui, “Forecasting short-term passenger flow: An empirical study on Shenzhen Metro,” IEEE Trans. Intell. Transp. Syst., vol. 20, no. 10, pp. 3613–3622, Oct. 2019. doi: 10.1109/TITS.2018.2879497
[23]	D. Yan, J. Zhou, Y. Zhao, and B. Wu, “Short-term subway passenger flow prediction based on ARIMA,” in Proc. 5th Int. Conf. Geo-Spatial Knowledge and Intelligence, Chiang Mai, Thailand, 2017, pp. 464−479.
[24]	B. M. Williams, “Multivariate vehicular traffic flow prediction: Evaluation of ARIMAX modeling,” Transport. Res. Record: J. Transport. Res. Board, vol. 1776, no. 1, pp. 194–200, Jan. 2001. doi: 10.3141/1776-25
[25]	L. Li, Y. Wang, G. Zhong, J. Zhang, and B. Ran, “Short-to-medium term passenger flow forecasting for metro stations using a hybrid model,” KSCE J. Civil Eng., vol. 22, no. 5, pp. 1937–1945, May 2018. doi: 10.1007/s12205-017-1016-9
[26]	C. Ding, J. Duan, Y. Zhang, X. Wu, and G. Yu, “Using an ARIMA-GARCH modeling approach to improve subway short-term ridership forecasting accounting for dynamic volatility,” IEEE Trans. Intell. Transp. Syst., vol. 19, no. 4, pp. 1054–1064, Apr. 2018. doi: 10.1109/TITS.2017.2711046
[27]	B. Leng, J. Zeng, Z. Xiong, W. Lv, and Y. Wan, “Probability tree based passenger flow prediction and its application to the Beijing subway system,” Front. Comput. Sci., vol. 7, no. 2, pp. 195–203, Apr. 2013. doi: 10.1007/s11704-013-2057-y
[28]	X. Dai, L. Sun, and Y. Xu, “Short-term origin-destination based metro flow prediction with probabilistic model selection approach,” J. Adv. Transport., vol. 2018, no. 1, Art. no. 5942763, Jun. 2018. doi: 10.1155/2018/5942763
[29]	S. Sha, J. Li, K. Zhang, Z. Yang, Z. Wei, X. Li, and X. Zhu, “RNN-based subway passenger flow rolling prediction,” IEEE Access, vol. 8, pp. 15232–15240, Jan. 2020. doi: 10.1109/ACCESS.2020.2964680
[30]	R. Fu, Z. Zhang, and L. Li, “Using LSTM and GRU neural network methods for traffic flow prediction,” in Proc. 31st Youth Academic Annual Conf. Chinese Association of Automation, Wuhan, China, 2016, pp. 324−328.
[31]	J. Wang, Y. Zhang, Y. Wei, Y. Hu, X. Piao, and B. Yin, “Metro passenger flow prediction via dynamic hypergraph convolution networks,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 12, pp. 7891–7903, Dec. 2021. doi: 10.1109/TITS.2021.3072743
[32]	G. Xue, S. Liu, L. Ren, Y. Ma, and D. Gong, “Forecasting the subway passenger flow under event occurrences with multivariate disturbances,” Expert Syst. Appl., vol. 188, Art. no. 116057, Feb. 2022. doi: 10.1016/j.eswa.2021.116057
[33]	Y. Li, X. Wang, S. Sun, X. Ma, and G. Lu, “Forecasting short-term subway passenger flow under special events scenarios using multiscale radial basis function networks,” Transp. Res. Part C: Emerg. Technol., vol. 77, pp. 306–328, Apr. 2017. doi: 10.1016/j.trc.2017.02.005
[34]	Y. He, L. Li, X. Zhu, and K. L. Tsui, “Multi-graph convolutional-recurrent neural network (MGC-RNN) for short-term forecasting of transit passenger flow,” IEEE Trans. Intell. Transp. Syst., vol. 23, no. 10, pp. 18155–18174, Oct. 2022. doi: 10.1109/TITS.2022.3150600
[35]	B. Yu, H. Yin, and Z. Zhu, “Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting,” in Proc. 27th Int. Joint Conf. Artificial Intelligence, Stockholm, Sweden, 2018, pp. 3634−3640.
[36]	P. Xie, M. Ma, T. Li, S. Ji, S. Du, Z. Yu, and J. Zhang, “Spatio-temporal dynamic graph relation learning for urban metro flow prediction,” IEEE Trans. Knowl. Data Eng., vol. 35, no. 10, pp. 9973−9984, Oct.2023. doi: 10.1109/TKDE.2023.3269771
[37]	S. P. Boyd and L. Vandenberghe, Convex Optimization. Cambridge, UK: Cambridge University Press, 2004.
[38]	A. Fu, B. Narasimhan, and S. Boyd, “CVXR: An R package for disciplined convex optimization,” arXiv preprint arXiv: 1711.07582, 2017.
[39]	G. E. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung, Time Series Analysis: Forecasting and Control. 5th ed. John Wiley & Sons, Hoboken, USA, 2015.
[40]	M. Ni, Q. He, and J. Gao, “Forecasting the subway passenger flow under event occurrences with social media,” IEEE Trans. Intell. Transp. Syst., vol. 18, no. 6, pp. 1623–1632, Jun. 2017. doi: 10.1109/tits.2016.2611644
[41]	I. Okutani and Y. J. Stephanedes, “Dynamic prediction of traffic volume through Kalman filtering theory,” Transport. Res. Part B: Methodol., vol. 18, no. 1, pp. 1–11, Feb. 1984. doi: 10.1016/0191-2615(84)90002-X
[42]	K. Cho, B. van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using RNN encoder-decoder for statistical machine translation,” in Proc. Conf. Empirical Methods in Natural Language Processing, Doha, Qatar, 2014, pp. 1724−1734.
[43]	G. Schwarz, “Estimating the dimension of a model,” Ann. Statist., vol. 6, no. 2, pp. 461–464, Mar. 1978. doi: 10.1214/aos/1176344136
[44]	D. Deng, C. Shahabi, U. Demiryurek, and L. Zhu, “Situation aware multi-task learning for traffic prediction,” in Proc. IEEE International Conference on Data Mining, New Orleans, LA, USA, 2017, pp. 81−90.
[45]	Y. Gong, Z. Li, J. Zhang, W. Liu, and Y. Zheng, “Online spatio-temporal crowd flow distribution prediction for complex metro system,” IEEE Trans. Knowl. Data Eng., vol. 34, no. 2, pp. 865–880, Feb. 2022. doi: 10.1109/TKDE.2020.2985952