Abstract
The dynamic urban link travel speed estimation (DU-LSE) problem has been studied extensively with approaches ranging from model to data driven since it benefits multiple applications in transport mobility, especially in dense cities. However, with drawbacks such as heavy assumption in model-driven and not being capable for big city network in data-driven, there has not been a consensus on the most effective method. This study aims to develop a Sequential Three Step framework to solve the DU-LSE problem using only the passively collected taxi trip data. The framework makes use of two deep learning models namely Traffic Graph Convolution (TGCN) and its recurrent variant TGCNlstm to capture both spatial and temporal correlation between road segments. The proposed framework has three advantages over similar approaches: (1) it uses only the affordable taxi data and overcomes the data’s incompleteness both in spatial (full GPS trajectory is not available) and temporal (incomplete historic time-series) domain, (2) it is specifically designed to preserve the directionality nature of traffic flow, and (3) it is capable for large networks. The model results and validations suggest the framework can achieve high enough accuracy and will provide valuable mobility data for cities especially those without traffic sensing infrastructure already in place.
Similar content being viewed by others
Data Availability
The data used in this study are publicly available. The New York Road Network dataset is provided by OpenStreetMap via the following link: https://www.openstreetmap.org/relation/175905. The New York Taxi dataset is made available by the New York City Taxi and Limousine Commission at https://www.nyc.gov/site/tlc/about/tlc-trip-record-data.page. The exact algorithm for the framework can be provided upon request at hhngo@memphis.edu.
References
Biem A, Bouillet E, Feng H (2010) IBM infosphere streams for scalable, real-time, intelligent transportation services. Proc 2010 ACM SIGMOD Int Conf Manag Data [WWW Document]. https://doi.org/10.1145/1807167.1807291. (Accessed 20 Jul 2020)
Chondrogiannis T, Bouros P, Gamper J, Leser U, Blumenthal DB (2020) Finding k-shortest paths with limited overlap. VLDB J 29:1023–1047. https://doi.org/10.1007/s00778-020-00604-x
City of New York (2019) Taxi Trips Record from the New York City Taxi & Limousine Commission [WWW Document]. https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page. (Accessed 20 Jul 2020)
Cui Z, Henrickson K, Ke R, Wang Y (2019) Traffic graph convolutional recurrent neural network: A deep learning framework for network-scale traffic learning and forecasting. IEEE Trans Intell Transp Syst 21(11):4883–4894
Diao Z, Wang X, Zhang D, Liu Y, Xie K, He S (2019) Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting. Proc AAAI Confer Artif Intel 33:890–897. https://doi.org/10.1609/aaai.v33i01.3301890
DOT (2019) Intelligent Transportation Systems - Benefits of Intelligent Transportation Systems Fact Sheet [WWW Document]. https://www.its.dot.gov/factsheets/benefits_factsheet.htm. (Accessed 20 Jul 2020)
Duan Y, Lv Y, Liu Y-L, Wang F-Y (2016) An efficient realization of deep learning for traffic data imputation. Transport Res C: Emerg Technol 72:168–181. https://doi.org/10.1016/j.trc.2016.09.015
Ermagun A, Levinson D (2018) Spatiotemporal traffic forecasting: review and proposed directions. Transp Rev 38:786–814. https://doi.org/10.1080/01441647.2018.1442887
Fountoulakis M, Bekiaris-Liberis N, Roncoli C, Papamichail I, Papageorgiou M (2017) Highway traffic state estimation with mixed connected and conventional vehicles: Microscopic simulation-based testing. Transport Res C: Emerg Technol 78:13–33. https://doi.org/10.1016/j.trc.2017.02.015
Frank M (1981) The Braess paradox. Math Program 20:283–302. https://doi.org/10.1007/BF01589354
Geng X, Li Y, Wang L, Zhang L, Yang Q, Ye J, Liu Y (2019) Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting. Proc AAAI Confer Artif Intell 33:3656–3663. https://doi.org/10.1609/aaai.v33i01.33013656
Google (2020) TensorFlow [WWW Document]. TensorFlow. https://www.tensorflow.org/. (Accessed 23 Sept 2020)
Hochreiter S, Schmidhuber J (1997) LSTM can Solve Hard Long Time Lag Problems. In: Mozer MC, Jordan MI, Petsche T (eds) Advances in Neural Information Processing Systems 9. MIT Press, pp 473–479
Hoffman W, Pavley R (1959) A Method for the Solution of the Nth Best Path Problem. J ACM 6:506–514. https://doi.org/10.1145/320998.321004
Hu X, Chiu Y-C (2015) A Constrained Time-Dependent K Shortest Paths Algorithm Addressing Overlap and Travel Time Deviation. Int J Transport Sci Technol 4:371–394. https://doi.org/10.1016/S2046-0430(16)30169-1
Jenelius E, Koutsopoulos HN (2013) Travel time estimation for urban road networks using low frequency probe vehicle data. Transport Res B: Methodol 53:64–81. https://doi.org/10.1016/j.trb.2013.03.008
Kawasaki Y, Hara Y, Kuwahara M (2019) Traffic State Estimation on a Two-Dimensional Network by a State-Space Model. Transport Res Proc 38:299–319. https://doi.org/10.1016/j.trpro.2019.05.017
Ke J, Zheng H, Yang H, Chen X( (2017) Short-term forecasting of passenger demand under on-demand ride services: A spatio-temporal deep learning approach. Transport Res C: Emerg Technol 85:591–608. https://doi.org/10.1016/j.trc.2017.10.016
Khan SM, Dey KC, Chowdhury M (2017) Real-Time Traffic State Estimation With Connected Vehicles. IEEE Trans Intell Transp Syst 18:1687–1699. https://doi.org/10.1109/TITS.2017.2658664
Kipf TN, Welling M (2017) Semi-Supervised Classification with Graph Convolutional Networks. https://arxiv.org/abs/1609.02907
Kumar A, Haque K, Mishra S, Golias MM (2019) Multi-criteria based approach to identify critical links in a transportation network. Case Stud Transport Pol 7(3):519–530
Lin L, He Z, Peeta S (2018) Predicting station-level hourly demand in a large-scale bike-sharing network: A graph convolutional neural network approach. Transport Res C: Emerg Technol 97:258–276. https://doi.org/10.1016/j.trc.2018.10.011
Liu H, Jin C, Yang B, Zhou A (2018) Finding Top-k Shortest Paths with Diversity. IEEE Trans Knowl Data Eng 30:488–502. https://doi.org/10.1109/TKDE.2017.2773492
Liu Z, Liu Y, Meng Q, Cheng Q (2019) A tailored machine learning approach for urban transport network flow estimation. Transport Res C: Emerg Technol 108:130–150. https://doi.org/10.1016/j.trc.2019.09.006
Nantes A, Ngoduy D, Bhaskar A, Miska M, Chung E (2016) Real-time traffic state estimation in urban corridors from heterogeneous data. Transport Res C: Emerg Technol, Adv Network Traffic Manag: from Dynamic State Estimation Traffic Control 66:99–118. https://doi.org/10.1016/j.trc.2015.07.005
Papageorgiou M, Kiakaki C, Dinopoulou V, Kotsialos A, Wang Y (2003) Review of road traffic control strategies. Proc IEEE 91:2043–2067. https://doi.org/10.1109/JPROC.2003.819610
Polson NG, Sokolov VO (2017) Deep learning for short-term traffic flow prediction. Transport Res C: Emerg Technol 79:1–17. https://doi.org/10.1016/j.trc.2017.02.024
Ralph J (2013) 2.5 quintillion bytes of data created every day. How does CPG & Retail manage it? [WWW Document]. IBM Consumer Products Industry Blog. https://www.ibm.com/blogs/insights-on-business/consumer-products/2-5-quintillion-bytes-of-data-created-every-day-how-does-cpg-retail-manage-it/. (Accessed 29 Dec 19)
Sekuła P, Marković N, Vander Laan Z, Sadabadi KF (2018) Estimating historical hourly traffic volumes via machine learning and vehicle probe data: A Maryland case study. Transport Res C: Emerg Technol 97:147–158. https://doi.org/10.1016/j.trc.2018.10.012
Seo T, Bayen AM, Kusakabe T, Asakura Y (2017) Traffic state estimation on highway: A comprehensive survey. Annu Rev Control 43:128–151. https://doi.org/10.1016/j.arcontrol.2017.03.005
Sheffi Y (1975) Urban Transportation Networks | Professor Yossi Sheffi [WWW Document]. https://sheffi.mit.edu/book/urban-transportation-networks. (Accessed 2 Mar 2020)
Tan H, Feng G, Feng J, Wang W, Zhang Y-J, Li F (2013) A tensor-based method for missing traffic data completion. Transport Res C: Emerg Technol 28:15–27. https://doi.org/10.1016/j.trc.2012.12.007
Thapa D, Paleti R, Mishra S (2022) Overcoming challenges in crash prediction modeling using discretized duration approach: An investigation of sampling approaches. Accident; Anal Prevent 169:106639
Wang Y, Zhang D, Liu Y, Dai B, Lee LH (2019) Enhancing transportation systems via deep learning: A survey. Transport Res C: Emerg Technol 99:144–163. https://doi.org/10.1016/j.trc.2018.12.004
World Bank (2019) Urban population (% of total population) | Data [WWW Document]. URL https://data.worldbank.org/indicator/SP.URB.TOTL.IN.ZS. (Accessed 20 Jul 2020)
Wu C, Thai J, Yadlowsky S, Pozdnoukhov A, Bayen A (2015) Cellpath: Fusion of cellular and traffic sensor data for route flow estimation via convex optimization. Transport Res C: Emerg Technol 59:111–128. https://doi.org/10.1016/j.trc.2015.05.004
Xu D, Wei C, Peng P, Xuan Q, Guo H (2020) GE-GAN: A novel deep learning framework for road traffic state estimation. Transportation Res C: Emerg Technol 117:102635. https://doi.org/10.1016/j.trc.2020.102635
Yang S, Ma W, Pi X, Qian S (2019) A deep learning approach to real-time parking occupancy prediction in transportation networks incorporating multiple spatio-temporal data sources. Transport Res C: Emerg Technol 107:248–265. https://doi.org/10.1016/j.trc.2019.08.010
Yao H, Wu F, Ke J, Tang X, Jia Y, Lu S, Gong P, Ye J Li Z (2018, April) Deep multi-view spatial-temporal network for taxi demand prediction. In Proceedings of the AAAI conference on artificial intelligence (Vol. 32, No. 1)
Yen JY (1971) Finding the K Shortest Loopless Paths in a Network. Manage Sci 17:712–716
Yeon J, Elefteriadou L, Lawphongpanich S (2008) Travel time estimation on a freeway using Discrete Time Markov Chains. Transport Res B: Methodol 42:325–338. https://doi.org/10.1016/j.trb.2007.08.005
Yu B, Li M, Zhang J, Zhu Z (2019) 3D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecasting. https://arxiv.org/abs/1903.00919
Yu H, Wu Z, Wang S, Wang Y, Ma X (2017) Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks. Sensors 17:1501. https://doi.org/10.3390/s17071501
Zhan X, Hasan S, Ukkusuri SV, Kamga C (2013) Urban link travel time estimation using large-scale taxi data with partial information. Transport Res C: Emerg Technol 33:37–49. https://doi.org/10.1016/j.trc.2013.04.001
Zheng F, Van Zuylen H (2013) Urban link travel time estimation based on sparse probe vehicle data. Transport Res C: Emerg Technol 31:145–157. https://doi.org/10.1016/j.trc.2012.04.007
Zhu L, Guo F, Polak JW, Krishnan R (2018) Urban link travel time estimation using traffic states-based data fusion. IET Intel Transport Syst 12:651–663. https://doi.org/10.1049/iet-its.2017.0116
Acknowledgements
This research is partly funded by the Center for Transportation Innovations in Education and Research (C-TIER) at the University of Memphis. The authors are grateful to associate editor and anonymous reviewers for their constructive feedback. Any opinions, findings, and recommendations expressed by the authors herein do not reflect the view of the agency funding and supporting this study.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
All authors declare that they have no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix A. Sets, Parameters, and Decision Variables used in the paper
1.1 Sets
- N :
-
Set of nodes
- A :
-
Set of links
- F :
-
Set of node features or directions
- K :
-
Set of layers
- I :
-
Set of taxi trips
- T :
-
Set of time periods
1.2 Parameters
- η:
-
Total number of trips selected for subset S in the TTS model of step 2
- L :
-
Total number of links included in subset S in the TTS model of step 2
- P i :
-
[\(\mathrm{A}\times 1\)] vector representing links comprising the travel path of taxi trip i
- β :
-
Hyperparameter in the TTS model of step 2
- length a :
-
Length of link \(a\)
- \(t_i^{pred}\) :
-
Predicted travel time for taxi trip i
- \(t_i^{obs}\) :
-
Observed travel time for taxi trip i
- Δ i :
-
Intersection delay of trip i
- \(\alpha_a^{link}\) :
-
North-bearing angle of link a
- A :
-
Modified directional adjacency matrix with dimension [\(N\times N\times F\)]
- a f :
-
Subset of \(A\) at \(f\) with dimension [\(N\times F\)]
- \(H_k^u\) :
-
Feature representation of a node u at kth hidden layer
- \(H_k^t\) :
-
\(\lbrack N\times F\rbrack\) matrix contains information of all nodes in the network at kth hidden layer and time period t
- for t :
-
Forget value for TGCNlstm at time period t
- inp t :
-
Input value for TGCNlstm at time period t
- Out t :
-
Output value for TGCNlstm at time period t
- act t :
-
Activation value for TGCNlstm at time period t
- s t :
-
Internal State value for TGCNlstm at time period t
- Loss :
-
Overall loss value for the deep learning model in step 3
1.3 Decision Variables
- xi={0,1}:
-
1 if trip \(i\) is selected for subset S in the TTS model of step 2, and 0 otherwise
- tt :
-
[A \(\times 1\)] vector representing link travel time from PLTT model
- W t :
-
[\(N\times N\)] weight matrix in TGCN for passing information between neighbors at time period t
- Wfor, Winp, Wact, Wout:
-
[\(N\times 2N\)] weight matrices for passing information and calculating internal state values in TGCNlstm cell
- Bfor, Binp, Bact, Bout:
-
[\(N\times F\)] Bias matrices in TGCNlstm cell
1.4 Models and Operations
- PCP:
-
Path Choice Prediction. The first step in the framework
- PLTT:
-
Partial Link Travel Time Prediction. The second step in the framework
- TTS:
-
Taxi Trip Subsetting. An inner preprocessing model within step 2
- TGCN:
-
Traffic Graph Convolution Network. An operation for passing message between host node and its neighbor, specifically design to capture directional traffic flow
- TGCNlstm:
-
Traffic Graph Convolution Network with Long-Short Term Memory. An operation for passing message between host node’s historical data as well as its neighbor’s
Appendix B
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) 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
Ngo, H., Mishra, S. Traffic Graph Convolutional Network for Dynamic Urban Travel Speed Estimation. Netw Spat Econ 23, 179–222 (2023). https://doi.org/10.1007/s11067-022-09582-9
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11067-022-09582-9