Analysis and Prediction of Dockless Shared Bike Demand Evolving Around Urban Rail Transit Stations: Case Study in Shenzhen, China

Abstract

The emergence of dockless shared bikes (DSB) has led to their use as an important transfer mode to urban rail transit (URT) stations. However, in highly populated areas such as subway stations in peak hours, there is increasing concern about the imbalance between the demand and supply of shared bikes. To promote smoother subway transfer trips using shared bikes, it is very important to estimate the DSB demand, especially the disparity in the volume of bike pick-up and drop-off demand around subway stations. This research first utilizes the Shenzhen metro usage data and DSB usage data, analyzes data regarding subway and shared bike usage, discusses their potential transfer uses, and finds great disparity in DSB demand between different subway stations. The catchment area method is used to estimate bike usage as a potential transfer mode to the subway, where the catchment area is defined as a radius of 150 m from the subway station center. The DSB trip demand is categorized into two types: pick-up and drop-off. The most recent deep learning method, adaptive graph convolutional recurrent network (AGCRN), is used to predict the DSB demand more accurately because of its ability in enabling the modeling of relationships between entities in a self-adapted graph, and the prediction is compared with long short-term memory (LSTM), spatiotemporal neural network (STNN), diffusion convolutional recurrent neural network (DCRNN), and Graph WaveNet. Results show that methods with graphs (STNN, DCRNN, Graph WaveNet, and AGCRN) perform better than LSTM, and methods with adaptive graphs (Graph WaveNet and AGCRN) outperform methods with static graphs in terms of mean absolute error (MAE), root-mean-square error (RMSE), and mean absolute percentage error (MAPE). DSB prediction results show that AGCRN performs the best in this study. More data, particularly land use data and URT station volume data, are expected to improve the predictive accuracy of the method due to potentially improved graph representation of station characteristics and subway station volume correlations. And with more accurate prediction results, it will be possible to achieve a better balancing strategy for bike operation optimization for better bike usage, and thus for a higher transfer rate of DSB to subway.

Keywords

Urban rail transit / First-/last-mile transfer trips / Dockless shared bikes / Demand prediction / Deep learning / Adaptive graph convolutional recurrent network

References

[1] SUTPC Shenzhen household travel survey report 2017

[2] Daily SSZ Line density ranks the national first, 500km at the end of this year for Shenzhen metro 2017

[3] Channel C China bike Sharing report: March 2017

[4] iiMedia (2022) China Shared bikes user survey

[5] Du M, Cheng L. Better understanding the characteristics and influential factors of different travel patterns in free-floating bike sharing: evidence from Nanjing China. Sustainability, 2018, 10(4): 1244

[6] Kashyap AA, Raviraj S, Devarakonda A, Nayak KSR, Santhosh KV, Bhat SJ. Traffic flow prediction models–A review of deep learning techniques. Cogent Eng, 2022, 9(1): 2010510

[7] Chung J, Kastner K, Dinh L, Goel K, Courville AC, Bengio Y (2015) A recurrent latent variable model for sequential data. In: Advances in neural information processing systems, pp 2980–2988

[8] Luo Y, Cai X, Zhang Y, Xu J et al. (2018) Multivariate time series imputation with generative adversarial networks. In: Advances in neural information processing systems, pp 1596–1607

[9] Cao W, Wang D, Li J, Zhou H, Li L, Li Y (2018) Brits: bidirectional recurrent imputation for time series. In: Advances in neural information processing systems, pp 6775–6785

[10] Lai G, Chang WC, Yang Y, Liu H (2018) Modeling long-and short-term temporal patterns with deep neural networks. In: The 41st international ACM SIGIR conference on research & development in information retrieval, pp 95–104

[11] Borovykh A, Bohte S, Oosterlee CW (2017) Conditional time series forecasting with convolutional neural networks. arXiv preprint arXiv:1703.04691

[12] Bai S, Kolter JZ, Koltun V (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271

[13] Sen R, Yu HF, Dhillon IS (2019) Think globally, act locally: a deep neural network approach to high-dimensional time series forecasting. In: Advances in neural information processing systems, pp 4838–4847

[14] Bai L, Yao L, Kanhere SS, Wang X, Liu W, Yang Z (2019) Spatio-temporal graph convolutional and recurrent networks for citywide passenger demand prediction. In: Proceedings of the 28th ACM international conference on information and knowledge management, pp 2293–2296

[15] Ye J, Zhao J, Ye K, Xu C (2020) How to build a graph-based deep learning architecture in traffic domain: a survey. arXiv preprint arXiv:2005.11691

[16] Yin X, Wu G, Wei J, Shen Y, Qi H, Yin B (2020) A comprehensive survey on traffic prediction. arXiv preprint arXiv:2004.08555

[17] Ji Y, Cao Y, Liu Y, Ma X. Analysis of temporal and spatial usage patterns of dockless bike sharing system around rail transit station area. J Southeast Univ (Engl Ed)., 2019, 35: 228-235.

[18] Xu C, Ji J, Liu P. The station-free sharing bike demand forecasting with a deep learning approach and large-scale datasets. Transport Res Part C: Emerg Technol, 2018, 95: 47-60

[19] Faghih-Imani A, Eluru N. Incorporating the impact of spatio-temporal interactions on bicycle sharing system demand: a case study of New York CitiBike system. J Transp Geogr, 2016, 54: 218-227

[20] Wang K, Akar G, Chen Y-J. Bike sharing differences among millennials, Gen Xers, and baby boomers: lessons learnt from New York City’s bike share. Transport Res Part A: Policy Pract, 2018, 116: 1-14.

[21] Wu Z, Pan S, Long G, et al. Graph wavenet for deep spatial-temporal graph modeling. Proceedings of the 28th International Joint Conference on Artificial Intelligence. 2019, pp.1907–1913

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

[23] Song C, Lin Y, Guo S. Spatial-temporal synchronous graph convolutional networks: A new framework for spatial-temporal network data forecasting. Proceedings of the AAAI Conference on Artificial Intelligence. 2020.

[24] Zheng C, Fan X, Wang C. et al. Gman: A graph multi-attention network for traffic prediction. arXiv preprint arXiv:1911.08415

[25] Obrien O, Cheshire J, Batty M. Mining bicycle sharing data for generating insights into sustainable transport systems. J Transport Geogr, 2014, 34: 262-273

[26] Fu X m, Zhi-cai J. Unraveling mobility pattern of dockless bike-sharing use in shanghai[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(3): 219.

[27] Lv X, Pan H. Sharing bicycle riding characteristics analysis in Shanghai based on mobike opening data. Shanghai Urban Plan Rev, 2018, 2: 46-51.

[28] Deng L, Xie Y, Huang D. Bicycle-sharing facility planning base on riding spatiotemporal data. Planners, 2017, 10: 82-88.

[29] Hui Y, Tang L, Xie Y, Liao J, Shi C (2021) Impact of built environment on bike sharing diurnal variation characteristics: A case study in Xiamen. Urban Trans of China 6

[30] Tran TD, Ovtracht N, d’Arcier BF. Modeling bike sharing system using built environment factors. Procedia Cirp, 2015, 30: 293-298

[31] Lu M, Hsu S-C, Chen P-C, Lee W-Y. Improving the sustainability of integrated transportation system with bike-sharing: a spatial agent-based approach. Sustain Cities Soc, 2018, 41: 44-51

[32] Leister EH, Vairo N, Sims D, Bopp M. Understanding bike share reach, use, access and function: an exploratory study. Sustain Cities Soc, 2018, 43: 191-196

[33] Zhang Y, Thomas T, Brussel M, Van Maarseveen M. Exploring the impact of built environment factors on the use of public bikes at bike stations: case study in Zhongshan China. J Trans Geogr, 2017, 58: 59-70

[34] Kim K. Investigation on the effects of weather and calendar events on bike-sharing according to the trip patterns of bike rentals of stations. J Transp Geogr, 2018, 1(66): 309-320

[35] Kim K. Discovering spatiotemporal usage patterns of a bike-sharing system by type of pass: a case study from Seoul. Transportation, 2023, 21: 1-35.

[36] Yang Z, Hu J, Shu Y, et al. Mobility modeling and prediction in bike-sharing systems. Proceedings of the 14th annual international conference on mobile systems, applications, and services. 2016, pp.165–178.

[37] Faghih-Imani A, Eluru N, El-Geneidy AM, Rabbat M, Haq U. How land-use and urban form impact bicycle flows: evidence from the bicycle-sharing system (BIXI) in Montreal. J Transport Geogr, 2014, 41: 306-314

[38] Ai Y, Li Z, Mi G, Zhang Y, Yu D, Chen W, Ju Y. A deep learning approach on short term spatio-temporal distribution forecasting of dockless bike-sharing system. Neur Comput Appl, 2019, 31(5): 1665-1677

[39] Wang D, Yang Y, Ning S (2018) Deepstcl: a deep spatio-temporal convlstm for travel demand prediction. In: 2018 International joint conference on neural networks (IJCNN). IEEE, pp 1–8.

[40] Jin K, Wang W, Li S, et al. Dockless shared-bike demand prediction with temporal convolutional networks. CICTP 2020. 2020, pp.2851–2863.

[41] Yang Y, Heppenstall A, Turner A, Comber A. Using graph structural information about flows to enhance short-term demand prediction in bike-sharing systems. Comput Environ Urban Syst, 2020, 1(83):

[42] Zhang J, Zheng Y, Qi D. Deep spatio-temporal residual networks for citywide crowd flowsprediction. Proceedings of the AAAI conference on artificial intelligence: volume 31. 2017

[43] Bai L, Yao L, Li C, Wang X, Wang C. Adaptive graph convolutional recurrent network for traffic forecasting. Adv Neural Inf Process Syst, 2020, 33: 17804-17815.

[44] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput, 1997, 9(8): 1735-1780

[45] Ziat A, Delasalles E, Denoyer L, Gallinari P (2017) Spatio-temporal neural networks for space-time series forecasting and relations discovery. In: 2017 IEEE International conference on data mining (ICDM), IEEE, 2017, pp. 705–714

[46] Li Y, Yu R, Shahabi C, Liu Y (2018) Diffusion convolutional recurrent neural network: data-driven traffic forecasting. In: International conference on learning representations

[47] Wang J, Jiang J, Jiang W, Li C, Zhao WX (2021) LibCity: an open library for traffic prediction. In: Proceedings of the 29th international conference on advances in geographic information systems, association for computing machinery, New York, NY, USA, 2021, SIGSPATIAL ’21, p. 145–148