A deep learning approach on short-term spatiotemporal distribution forecasting of dockless bike-sharing system

  • Yi Ai
  • Zongping Li
  • Mi Gan
  • Yunpeng Zhang
  • Daben Yu
  • Wei Chen
  • Yanni Ju
S.I.: Emerging Intelligent Algorithms for Edge-of-Things Computing


Dockless bike-sharing is becoming popular all over the world, and short-term spatiotemporal distribution forecasting on system state has been further enlarged due to its dynamic spatiotemporal characteristics. We employ a deep learning approach, named the convolutional long short-term memory network (conv-LSTM), to address the spatial dependences and temporal dependences. The spatiotemporal variables including number of bicycles in area, distribution uniformity, usage distribution, and time of day as a spatiotemporal sequence in which both the input and the prediction target are spatiotemporal 3D tensors within one end-to-end learning architecture. Experiments show that conv-LSTM outperforms LSTM on capturing spatiotemporal correlations.


Dockless bike-sharing system Short-term spatiotemporal distribution forecasting Deep learning Convolutional long short-term memory network (conv-LSTM) 


  1. 1.
  2. 2.
  3. 3.
    Pidd H, Lavelle D (2017) Chinese bike-share scheme launches in rainy Manchester. The Guardian. Retrieved 6 July 2017Google Scholar
  4. 4.
    Mobike bicycle-hire scheme to be launched in Greater Manchester. BBC. 13 June 2017. Retrieved 6 July 2017Google Scholar
  5. 5.
    Cox, C (2017) Everything you need to know about the new Mobike service coming to Manchester and Salford. Manchester Evening NewsGoogle Scholar
  6. 6.
    Mobike launches in Sapporo. Shanghai Daily. Shanghai Daily. 23 August 2017. Retrieved 24 August 2017Google Scholar
  7. 7.
  8. 8.
    Bai Y, Sun Z, Zeng B, Deng J, Li C (2017) A multi-pattern deep fusion model for short-term bus passenger flow forecasting. Appl Soft Comput 58:669–680CrossRefGoogle Scholar
  9. 9.
    Ma Z, Xing J, Mesbah M, Ferreira L (2014) Predicting short-term bus passenger demand using a pattern hybrid approach. Transp Res Part C 39(39):148–163CrossRefGoogle Scholar
  10. 10.
    Wei Y, Chen MC (2012) Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks. Transp Res Part C 21(1):148–162CrossRefGoogle Scholar
  11. 11.
    Yang H, Leung CW, Wong SC, Bell MG (2010) Equilibria of bilateral taxi–customer searching and meeting on networks. Transp Res Part B 44:1067–1083CrossRefGoogle Scholar
  12. 12.
    Yang H, Yang T (2011) Equilibrium properties of taxi markets with search frictions. Transp Res Part B 45:696–713CrossRefGoogle Scholar
  13. 13.
    Ke JT, Zheng HY, Yang H et al (2017) Short-term forecasting of passenger demand under on-demand ride services: a spatio-temporal deep learning approach. Transp Res C Emerg Technol 85:591–608CrossRefGoogle Scholar
  14. 14.
    Wu Y, Tan H (2016) Short-term traffic flow forecasting with spatial–temporal correlation in a hybrid deep learning framework. arXiv preprint arXiv:1612.01022Google Scholar
  15. 15.
    Zhang J, Zheng Y, Qi D (2016) Deep spatio-temporal residual networks for citywide crowd flows prediction. arXiv preprint arXiv:1610.00081
  16. 16.
    Shaheen S, Zhang H, Martin E, Guzman S (2011) China’s Hangzhou public bicycle: understanding early adoption and behavioral response to bikesharing. Transp Res Rec J Transp Res Board 2247:33–41CrossRefGoogle Scholar
  17. 17.
    Caggiani L, Ottomanelli M (2013) A dynamic simulation based model for optimal fleet repositioning in bike-sharing systems. Proc Soc Behav Sci 87:203–210CrossRefGoogle Scholar
  18. 18.
    Caggiani L, Ottomanelli M (2012) A modular soft computing based method for vehicles repositioning in bike-sharing systems. Proc Soc Behav Sci 54:675–684CrossRefGoogle Scholar
  19. 19.
    Zeng D, Xu J, Gu J, Liu L, Xu G (2008) Short term traffic flow prediction based on online learning SVR. In: Workshop on power electronics and intelligent transportation system, p 616–620Google Scholar
  20. 20.
    Smith B, Demetsky M (1997) Traffic flow forecasting: comparison of modeling approaches. J Transp Eng 123(4):261–266CrossRefGoogle Scholar
  21. 21.
    Sun Y, Leng B, Guan W (2015) A novel wavelet-SVM short-time passenger flow prediction in Beijing subway system. Neurocomputing 166:109–121CrossRefGoogle Scholar
  22. 22.
    Sapankevych N, Sankar R (2009) Time series prediction using support vector machines: a survey. IEEE Intell Syst 4(2):24–38Google Scholar
  23. 23.
    Yu H, Yang J, Han J, Li X (2005) Making SVMs scalable to large data sets using hierarchical cluster indexing. Data Min Knowl Disc 11(3):295–321CrossRefGoogle Scholar
  24. 24.
    Zhao K, Khryashchev D, Freire J, Silva C, Vo H (2016) Predicting taxi demand at high spatial resolution: approaching the limit of predictability. In: IEEE international conference on big dataGoogle Scholar
  25. 25.
    Lv Y, Duan Y, Kang W, Li Z, Wang F-Y (2015) Traffic flow prediction with big data: a deep learning approach. IEEE Trans Intell Transp Syst 16(2):865–873Google Scholar
  26. 26.
    Huang W, Song G, Hong H, Xie K (2014) Deep architecture for traffic flow prediction: deep belief networks with multitask learning. IEEE Trans Intell Transp Syst 15:2191–2201CrossRefGoogle Scholar
  27. 27.
    Graham B (2014) Spatially-sparse convolutional neural networks. Comput Sci 34(6):864–867Google Scholar
  28. 28.
    Ma X, Tao Z, Wang Y, Yu H, Wang Y (2015) Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transp Res Part C Emerg Technol 54:187–197CrossRefGoogle Scholar
  29. 29.
    Shi X, Chen Z, Wang H, Yeung DY, Wong WK, Woo WC (2015) Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Advances in neural information processing systems, p 802–810Google Scholar

Copyright information

© The Natural Computing Applications Forum 2018

Authors and Affiliations

  • Yi Ai
    • 1
    • 2
  • Zongping Li
    • 1
    • 2
  • Mi Gan
    • 1
  • Yunpeng Zhang
    • 3
  • Daben Yu
    • 1
    • 2
  • Wei Chen
    • 1
    • 2
  • Yanni Ju
    • 1
    • 2
  1. 1.School of Transportation and LogisticsSouthwest Jiaotong UniversityChengduChina
  2. 2.Comprehensive Transportation Key Laboratory of Sichuan ProvinceChengduChina
  3. 3.College of TechnologyUniversity of HoustonHoustonUSA

Personalised recommendations