Spatio-temporal information enhance graph convolutional networks: A deep learning framework for ride-hailing demand prediction

Zhenglong Tang; Chao Chen; Zhenglong Tang; Chao Chen

doi:10.3934/mbe.2024112

Mathematical Biosciences and Engineering

2024, Volume 21, Issue 2: 2542-2567. doi: 10.3934/mbe.2024112

Previous Article Next Article

Survey Special Issues

Spatio-temporal information enhance graph convolutional networks: A deep learning framework for ride-hailing demand prediction

Zhenglong Tang ¹,
Chao Chen ^{1,2
,
,}

1.
College of Computer Science and Engineering, Sichuan University of Science and Engineering, Zigong 643000, China
2.
Sichuan Key Provincial Research Base of Intelligent Tourism, Zigong 643000, China

Academic Editor: Yang Kuang

Received: 19 October 2023 Revised: 19 December 2023 Accepted: 09 January 2024 Published: 18 January 2024

Ride-hailing demand prediction is essential in fundamental research areas such as optimizing vehicle scheduling, improving service quality, and reducing urban traffic pressure. Therefore, achieving accurate and timely demand prediction is crucial. To solve the problems of inaccurate prediction results and difficulty in capturing the influence of external spatiotemporal factors in demand prediction of previous methods, this paper proposes a demand prediction model named as the spatiotemporal information enhance graph convolution network. Through correlation analysis, the model extracts the primary correlation information between external spatiotemporal factors and demand and encodes them to form feature units of the area. We utilize gated recurrent units and graph convolutional networks to capture the spatiotemporal dependencies between demand and external factors, respectively, thereby enhancing the model's perceptiveness to external spatiotemporal factors. To verify the model's validity, we conducted comparative and portability experiments on a relevant dataset of Chengdu City. The experimental results show that the model's prediction is better than the baseline model when incorporating external factors, and the errors are very close under different experimental areas. This result highlights the importance of external spatiotemporal factors for model performance enhancement. Also, it demonstrates the robustness of the model in different environments, providing excellent performance and broad application potential for ride-hailing prediction studies.
- demand prediction,
- external spatiotemporal factors,
- spatiotemporal graph convolutional networks,
- spatiotemporal dependence
Citation: Zhenglong Tang, Chao Chen. Spatio-temporal information enhance graph convolutional networks: A deep learning framework for ride-hailing demand prediction[J]. Mathematical Biosciences and Engineering, 2024, 21(2): 2542-2567. doi: 10.3934/mbe.2024112

Related Papers:

Abstract

Ride-hailing demand prediction is essential in fundamental research areas such as optimizing vehicle scheduling, improving service quality, and reducing urban traffic pressure. Therefore, achieving accurate and timely demand prediction is crucial. To solve the problems of inaccurate prediction results and difficulty in capturing the influence of external spatiotemporal factors in demand prediction of previous methods, this paper proposes a demand prediction model named as the spatiotemporal information enhance graph convolution network. Through correlation analysis, the model extracts the primary correlation information between external spatiotemporal factors and demand and encodes them to form feature units of the area. We utilize gated recurrent units and graph convolutional networks to capture the spatiotemporal dependencies between demand and external factors, respectively, thereby enhancing the model's perceptiveness to external spatiotemporal factors. To verify the model's validity, we conducted comparative and portability experiments on a relevant dataset of Chengdu City. The experimental results show that the model's prediction is better than the baseline model when incorporating external factors, and the errors are very close under different experimental areas. This result highlights the importance of external spatiotemporal factors for model performance enhancement. Also, it demonstrates the robustness of the model in different environments, providing excellent performance and broad application potential for ride-hailing prediction studies.

References

[1]	Ministry of Transport of the People's Republic of China, Online Taxi-Hailing Regulatory Information Interactive System Releases Basic Online Taxi-Hailing Industry Operations for July 2023, 2003. Available from: https://www.mot.gov.cn/jiaotongyaowen/202308/t20230823_3896922.html.
[2]	China Internet Network Information Center, The 52nd statistical report on internet development in china released, 2023. Available from: https://www.cnnic.net.cn/n4/2023/0828/c199-10830.html.
[3]	Ministry of Transport of the People's Republic of China, Xiamen has highest compliance rate for Online Taxi-Hailing orders in July, 2022. Available from: https://www.mot.gov.cn/jiaotongyaowen/202208/t20220817_3666534.html.
[4]	Y. Liu, C. Lyu, A. Khadka, W. Zhang, Z. Liu, Spatio-temporal ensemble method for car-hailing demand prediction. IEEE Trans. Intell. Transp. Syst., 21 (2020), 5328–5333. https://doi.org/10.1109/TITS.2019.2948790 doi: 10.1109/TITS.2019.2948790
[5]	L. Bai, L. Yao, S. S. Kanhere, X. Wang, Q. Sheng, Stg2seq: Spatial-temporal graph to sequence model for multi-step passenger demand forecasting, in 28th International Joint Conference on Artificial Intelligence, (2019), 1981–1987.
[6]	A. Nejadettehad, H. Mahini, B. Bahrak, Short-term demand forecasting for online car-hailing services using recurrent neural networks. Appl. Artif. Intell., 34 (2020), 674–689. https://doi.org/10.1080/08839514.2020.1771522 doi: 10.1080/08839514.2020.1771522
[7]	T. Yang, X. Tang, R. Liu, Dual temporal gated multi-graph convolution network for taxi demand prediction, Neural Comput. Appl., 35 (2023), 13119–13134. https://doi.org/10.1007/s00521-021-06092-6 doi: 10.1007/s00521-021-06092-6
[8]	J. Ke, H. Zheng, H. Yang, X. Chen, Short-term forecasting of passenger demand under on-demand ride services: A spatio-temporal deep learning approach, Transp. Res. Part C: Emerging Technol., 85 (2017), 591–608. https://doi.org/10.1016/j.trc.2017.10.016 doi: 10.1016/j.trc.2017.10.016
[9]	Y. Guo, Y. Zhang, Y. Boulaksil, N. Tian, Multi-dimensional spatiotemporal demand forecasting and service vehicle dispatching for online car-hailing platforms, Int. J. Prod. Res., 60 (2022), 1832–1853. https://doi.org/10.1080/00207543.2021.1871675 doi: 10.1080/00207543.2021.1871675
[10]	H. Yang, Y. W. Lau, S. C. Wong, H. K. Lo, A macroscopic taxi model for passenger demand, taxi utilization and level of services, Transportation, 27 (2000), 317–340. https://doi.org/10.1023/A:1005289504549 doi: 10.1023/A:1005289504549
[11]	G. W. Douglas, Price regulation and optimal service standards: The taxicab industry, J. Transp. Econ. Policy, 6 (1972), 116–127.
[12]	A. Bazzani, B. Giorgini, S. Rambaldi, R. Gallotti, L. Giovannini, Statistical Laws in Urban Mobility from microscopic GPS data in the area of Florence, J. Stat. Mech., 5 (2010), P05001. https://doi.org/10.1088/1742-5468/2010/05/P05001 doi: 10.1088/1742-5468/2010/05/P05001
[13]	R. Asmundsdottir, Y. Chen, H. J. V. Zuylen, Dynamic origin–destination matrix estimation using probe vehicle data as a priori information, in Traffic Data Collection and its Standardization, (2010), 89–108. https://doi.org/10.1007/978-1-4419-6070-2_7
[14]	L. Sun, L. Jia, Z. Wei, J. Li, Demand forecasting of taxi travel based on GPS data, J. Transp. Inf. Saf., 39 (2021), 128–136. https://doi.org/10.3963/j.jssn.1674-4861.2021.05.016 doi: 10.3963/j.jssn.1674-4861.2021.05.016
[15]	X. Ma, Z. Tao, Y. Wang, H. Yu, Y. Wang, Long short-term memory neural network for traffic speed prediction using remote microwave sensor data, Transp. Res. Part C: Emerging Technol., 54 (2015), 187–197. https://doi.org/10.1016/j.trc.2015.03.014 doi: 10.1016/j.trc.2015.03.014
[16]	R. Fu, Z. Zhang, L. Li, Using LSTM and GRU neural network methods for traffic flow prediction, in 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC), (2016), 324–328. https://doi.org/10.1109/YAC.2016.7804912
[17]	L. Liao, B. Li, F. Zou, D. Huang, MFGCN: A multimodal fusion graph convolutional network for online car-hailing demand prediction, IEEE Intell. Syst., 38 (2023), 21–30. https://doi.org/10.1109/MIS.2023.3250600 doi: 10.1109/MIS.2023.3250600
[18]	T. N. Kipf, M. Welling, Semi-supervised classification with graph convolutional networks, preprint, arXiv: 1609.02907.
[19]	A. Luo, B. Shangguan, C. Yang, F. Gao, Z. Fang, D. Yu, Spatial-temporal diffusion convolutional network: A novel framework for taxi demand forecasting, ISPRS Int. J. Geo-Inf., 11 (2022), 193. https://doi.org/10.3390/ijgi11030193 doi: 10.3390/ijgi11030193
[20]	Q. Wang, Y. Wu, C. Zhu, Y. Wang, Short-term traffic flow prediction studies integrated with external properties, Appl. Res. Comput., 39 (2022), 2974–2978. https://doi.org/10.19734/j.issn.1001-3695.2022.04.0119 doi: 10.19734/j.issn.1001-3695.2022.04.0119
[21]	J. Zhu, Q. Wang, C. Tao, H. Deng, L. Zhao, H. Li, AST-GCN: Attribute-augmented spatiotemporal graph convolutional network for traffic forecasting, IEEE Access, 9 (2021), 35973–35983. https://doi.org/10.1109/ACCESS.2021.3062114 doi: 10.1109/ACCESS.2021.3062114
[22]	L. Lin, Z. He, S. Peeta, Predicting station-level hourly demand in a large-scale bike-sharing network: A graph convolutional neural network approach, Transp. Res. Part C: Emerging Technol., 97 (2018), 258–276. https://doi.org/10.1016/j.trc.2018.10.011 doi: 10.1016/j.trc.2018.10.011
[23]	Y. Liu, Z. Liu, C. Lyu, J. Ye, Attention-based deep ensemble net for large-scale online taxi-hailing demand prediction, IEEE Trans. Intell. Transp. Syst., 21 (2020), 4798–4807. https://doi.org/10.1109/TITS.2019.2947145 doi: 10.1109/TITS.2019.2947145
[24]	J. Zhang, Y. Zheng, D. Qi, Deep spatio-temporal residual networks for citywide crowd flows prediction, in Thirty-First AAAI Conference on Artificial Intelligence, 31 (2017), 1655—1661. https://doi.org/10.1609/aaai.v31i1.10735
[25]	C. Zhang, F. Zhu, Y. Lv, P. Ye, F. Wang, MLRNN: Taxi demand prediction based on multi-level deep learning and regional heterogeneity analysis, IEEE Trans. Intell. Transp. Syst., 23 (2022), 8412–8422. https://doi.org/10.1109/TITS.2021.3080511 doi: 10.1109/TITS.2021.3080511
[26]	J. Sun, J. Zhang, Q. Li, X. Yi, Y. Liang, Y. Zheng, Predicting citywide crowd flows in irregular regions using multi-view graph convolutional networks, IEEE Trans. Knowl. Data Eng., 34 (2022), 2348–2359. https://doi.org/10.1109/TKDE.2020.3008774 doi: 10.1109/TKDE.2020.3008774
[27]	N. Davis, G. Raina, K. Jagannathan, Taxi Demand Forecasting: A HEDGE-based tessellation strategy for improved accuracy, IEEE Trans. Intell. Transp. Syst., 19 (2018), 3686–3697. https://doi.org/10.1109/TITS.2018.2860925 doi: 10.1109/TITS.2018.2860925
[28]	H. Yang, Z. Pan, W. Bai, Review of time series prediction methods, Comput. Sci., 46 (2019), 21–28.
[29]	J. Liu, W. Guan, A summary of traffic flow forecasting methods, J. Highw. Transp. Res. Dev., 3 (2004), 82–85. https://doi.org/10.3969/j.issn.1002-0268.2004.03.022 doi: 10.3969/j.issn.1002-0268.2004.03.022
[30]	X. Li, G. Pan, Z. Wu, G. Qi, S. Li, D. Zhang, et al., Prediction of urban human mobility using large-scale taxi traces and its applications, Front. Comput. Sci., 6 (2012), 111–121. https://doi.org/10.1007/s11704-011-1192-6 doi: 10.1007/s11704-011-1192-6
[31]	B. M. Williams, P. K. Durvasula, D. E. Brown, Urban freeway traffic flow prediction: Application of seasonal autoregressive integrated moving average and exponential smoothing models, Transp. Res. Rec., 1644 (1998), 132–141. https://doi.org/10.3141/1644-14 doi: 10.3141/1644-14
[32]	L. Moreira-Matias, J. Gama, M. Ferreira, J. Mendes-Moreira, L. Damas, Predicting Taxi–Passenger Demand Using Streaming Data, IEEE Trans. Intell. Transp. Syst., 14 (2013), 1393–1402. https://doi.org/10.1109/TITS.2013.2262376 doi: 10.1109/TITS.2013.2262376
[33]	S. Singh, R. Kumar, U. P. Rao, Multi-objective adaptive manta-ray foraging optimization for workflow scheduling with selected virtual machines using time-series-based prediction, Int. J. Software Sci. Comput. Intell., 14 (2022), 1–25. https://doi.org/10.4018/IJSSCI.312559 doi: 10.4018/IJSSCI.312559
[34]	W. Wu, Y. Xia, W. Jin, Predicting bus passenger flow and prioritizing influential factors using multi-source data: Scaled stacking gradient boosting decision trees, IEEE Trans. Intell. Transp. Syst., 22 (2021), 2510–2523. https://doi.org/10.1109/TITS.2020.3035647 doi: 10.1109/TITS.2020.3035647
[35]	P. Cai, Y. Wang, G. Lu, P. Chen, C. Ding, J. Sun, A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting, Transp. Res. Part C: Emerging Technol., 62 (2016), 21–34. https://doi.org/10.1016/j.trc.2015.11.002 doi: 10.1016/j.trc.2015.11.002
[36]	E. Castillo, J. M. Menéndez, S. Sánchez-Cambronero, Predicting traffic flow using bayesian networks, Transp. Res. Part B: Methodol., 42 (2008), 482–509. https://doi.org/10.1016/j.trb.2007.10.003 doi: 10.1016/j.trb.2007.10.003
[37]	C. Yang, E. J. Gonzales, Modeling taxi trip demand by time of day in new york city, Transp. Res. Rec., 2429 (2014), 110–120. https://doi.org/10.3141/2429-12 doi: 10.3141/2429-12
[38]	S. Jiang, W. Chen, Z. Li, H. Yu, Short-term demand prediction method for online car-hailing services based on a least squares support vector machine, IEEE Access, 7 (2019), 11882–11891. https://doi.org/10.1109/ACCESS.2019.2891825 doi: 10.1109/ACCESS.2019.2891825
[39]	F. J. G. Peñalvo, T. Maan, S. K. Singh, S. Kumar, V. Arya, K. T. Chui, et al., Sustainable stock market prediction framework using machine learning models, Int. J. Software Sci. Comput. Intell., 14 (2022), 1–15. https://doi.org/10.4018/IJSSCI.313593 doi: 10.4018/IJSSCI.313593
[40]	M. Lippi, M. Bertini, P. Frasconi, Short-term traffic flow forecasting: An experimental comparison of time-series analysis and supervised learning, IEEE Trans. Intell. Transp. Syst., 14 (2013), 871–882. https://doi.org/10.1109/TITS.2013.2247040 doi: 10.1109/TITS.2013.2247040
[41]	M. Castro-Neto, Y. Jeong, M. Jeong, L. D. Han, Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions, Expert Syst. Appl., 36 (2009), 6164–6173. https://doi.org/10.1016/j.eswa.2008.07.069 doi: 10.1016/j.eswa.2008.07.069
[42]	K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2016), 770–778. https://doi.org/10.1109/CVPR.2016.90
[43]	A. Krizhevsky, I. Sutskever, G. E. Hinton, ImageNet classification with deep convolutional neural networks, Commun. ACM, 60 (2017), 84–90. https://doi.org/10.1145/3065386 doi: 10.1145/3065386
[44]	S. Alaparthi, M. Mishra, Bidirectional encoder representations from transformers (BERT): A sentiment analysis odyssey, preprint, arXiv: 2007.01127.
[45]	F. Sun, J. Liu, J. Wu, C. Pei, X. Lin, W. Ou, et al., BERT4rec: Sequential recommendation with bidirectional encoder representations from transformer, in 28th ACM International Conference on Information and Knowledge Management, (2019), 1441–1450. https://doi.org/10.1145/3357384.3357895
[46]	S. Guo, Y. Lin, N. Feng, C. Song, H. Wan, Attention based spatial-temporal graph convolutional networks for traffic flow forecasting, in AAAI Conference on Artificial Intelligence, 33 (2019), 922–929. https://doi.org/10.1609/aaai.v33i01.3301922
[47]	Y. Li, R. Yu, C. Shahabi, Y. Liu, Diffusion convolutional recurrent neural network: Data-driven traffic forecasting, preprint, arXiv: 1707.01926.
[48]	L. Yu, J. Zhao, Y. Gao, W. Lin, Short-term traffic flow prediction based on deep learning, in 2019 International Conference on Robots & Intelligent System (ICRIS), (2019), 466–469. https://doi.org/10.1109/ICRIS.2019.00122
[49]	S. Liao, L. Zhou, X. Di, B. Yuan, J. Xiong, Large-scale short-term urban taxi demand forecasting using deep learning, in 2018 23rd Asia and South Pacific Design Automation Conference (ASP-DAC), (2018), 428–433. https://doi.org/10.1109/ASPDAC.2018.8297361
[50]	Y. Gu, M. Li, X. Rui, W. Lu, S. Wang, Short-term forecasting of supply-demand gap under online car-hailing services based on deep learning, J. Transp. Syst. Eng. Inf. Technol., 19 (2019), 223–230. https://doi.org/10.16097/j.cnki.1009-6744.2019.02.032 doi: 10.16097/j.cnki.1009-6744.2019.02.032
[51]	E. Dogan, LSTM training set analysis and clustering model development for short-term traffic flow prediction, Neural Comput. Appl., 33 (2021), 11175–11188. https://doi.org/10.1007/s00521-020-05564-5 doi: 10.1007/s00521-020-05564-5
[52]	G. N. Kouziokas, Deep bidirectional and unidirectional LSTM neural networks in traffic flow forecasting from environmental factors, in Conference on Sustainable Urban Mobility, 1278 (2020), 171–180. https://doi.org/10.1007/978-3-030-61075-3_17
[53]	G. Dai, C. Ma, X. Xu, Short-term traffic flow prediction method for urban road sections based on space-time analysis and GRU, IEEE Access, 7 (2019), 143025–143035. https://doi.org/10.1109/ACCESS.2019.2941280 doi: 10.1109/ACCESS.2019.2941280
[54]	Z. Huang, G. Huang, Z. Chen, C. Wu, X. Ma, H. Wang, Multi-regional online car-hailing order quantity forecasting based on the convolutional neural network, Information, 10 (2019), 193. https://doi.org/10.3390/info10060193 doi: 10.3390/info10060193
[55]	H. Luo, J. Cai, K. Zhang, R. Xie, L. Zheng, A multi-task deep learning model for short-term taxi demand forecasting considering spatiotemporal dependences, J. Traffic Transp. Eng., 8 (2021), 83–94. https://doi.org/10.1016/j.jtte.2019.07.002 doi: 10.1016/j.jtte.2019.07.002
[56]	X. Geng, Y. Li, L. Wang, L. Zhang, Q. Yang, J. Ye, et al., Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting, in AAAI Conference on Artificial Intelligence, 33 (2019), 3656–3663. https://doi.org/10.1609/aaai.v33i01.33013656
[57]	G. Jin, Y. Cui, L. Zeng, H. Tang, Y. Feng, J. Huang, Urban ride-hailing demand prediction with multiple spatio-temporal information fusion network, Transp. Res. Part C: Emerging Technol., 117 (2020), 102665. https://doi.org/10.1016/j.trc.2020.102665 doi: 10.1016/j.trc.2020.102665
[58]	G. Jin, Y. Liang, Y. Fang, Z. Shao, J. Huang, J. Zhang, et al., Spatio-temporal graph neural networks for predictive learning in urban computing: A survey, IEEE Trans. Knowl. Data Eng., (2023), 1–20. https://doi.org/10.1109/TKDE.2023.3333824
[59]	T. Tsai, C. Lee, C. Wei, Neural network based temporal feature models for short-term railway passenger demand forecasting, Expert Syst. Appl., 36 (2009), 3728–3736. https://doi.org/10.1016/j.eswa.2008.02.071 doi: 10.1016/j.eswa.2008.02.071
[60]	M. Li, Z. Zhu, Spatial-temporal fusion graph neural networks for traffic flow forecasting, in AAAI Conference on Artificial Intelligence, 35 (2021), 4189–4196. https://doi.org/10.1609/aaai.v35i5.16542
[61]	L. Zhao, Y. Song, C. Zhang, Y. Liu, P. Wang, T. Lin, et al., T-GCN: A temporal graph convolutional network for traffic prediction, IEEE Trans. Intell. Transp. Syst., 21 (2020), 3848–3858. https://doi.org/10.1109/TITS.2019.2935152 doi: 10.1109/TITS.2019.2935152
[62]	X. Lu, C. Ma, Y. Qiao, Short-term demand forecasting for online car-hailing using ConvLSTM networks, Phys. A: Stat. Mech. Appl., 570 (2021), 125838. https://doi.org/10.1016/j.physa.2021.125838 doi: 10.1016/j.physa.2021.125838
[63]	J. T. Connor, R. D. Martin, L. E. Atlas, Recurrent neural networks and robust time series prediction, IEEE Trans. Neural Networks, 5 (1994), 240–254. https://doi.org/10.1109/72.279188 doi: 10.1109/72.279188
[64]	S. Hochreiter, J. Schmidhuber, Long short-term memory, Neural Comput., 9 (1997), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735 doi: 10.1162/neco.1997.9.8.1735
[65]	K. Cho, B. V. Merrienboer, D. Bahdanau, Y. Bengio, On the properties of neural machine translation: Encoder-decoder approaches, preprint, arXiv: 1409.1259.
[66]	B. M. Williams, L. A. Hoel, Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: Theoretical basis and empirical results, J. Transp. Eng., 129 (2003), 664–672. https://doi.org/10.1061/(ASCE)0733-947X(2003)129:6(664) doi: 10.1061/(ASCE)0733-947X(2003)129:6(664)
[67]	D. Satrinia, G. A. P. Saptawati, Traffic speed prediction from GPS data of taxi trip using support vector regression, in 2017 International Conference on Data and Software Engineering (ICoDSE), (2017), 1–6. https://doi.org/10.1109/ICODSE.2017.8285869
[68]	J. Ye, L. Sun, B. Du, Y. Fu, H. Xiong, Coupled layer-wise graph convolution for transportation demand prediction, in AAAI Conference on Artificial Intelligence, 35 (2021), 4617–4625. https://doi.org/10.1609/aaai.v35i5.16591

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)