Using neural network for predicting hourly origin-destination matrices from trip data and environmental information

Document Type : Article

Authors

Department of Civil Engineering, Sharif University of Technology, Tehran, Iran

Abstract

Predicting OD demand has always been a challenging problem in transportation. Conventional demand prediction methods mainly propose procedures for forecasting aggregated temporal Origin-Destination (OD) flows. In other words, they are primarily unable to predict short-term demands. Another limitation of these models is that they do not consider the impact of environmental conditions on trip patterns. Furthermore, OD demand prediction requires two individual steps of modeling: trip generation and trip distribution. This article presents a framework for predicting hourly OD flows using the Neural Network. The proposed method utilizes trip patterns and environmental conditions for predicting demands in single-step modeling. A case study on New York City Green Taxi 2018 trip data is done to evaluate the method, and the results demonstrate that the network has reasonably accurate OD flows predictions.

Keywords

Main Subjects

References

References:
1. Mathew, T.V. and Sharma, S. "Capacity expansion problem for large urban transportation networks", J. Transp. Eng., 135(7), pp. 406-415 (2009). DOI: 10.1061/(ASCE)0733-947X(2009)135:7(433).
2. Halvorsen, A., Koutsopoulos, H.N., Ma, Z., et al. "Demand management of congested public transport systems: a conceptual framework and application using smart card data", Transportation, 47(5), pp. 1881-1904 (2020). DOI: 10.1007/s11116-020-10060-7.
3. McNally, M.G. "The Four-Step Model", In Handbook of Transport Modelling, D.A. Hensher and K.J. Button, Eds., Emerald Group Publishing Limited, 1, pp. 35-53 (January 1 2007).DOI: 10.1108/9780857245670-003.
4. Bhat, C.R. "Random utility-based discrete choice models for travel demand analysis", Transp. Syst. Plan. Methods Appl., 10(1), pp. 1-30 (2003). DOI: 10.1201/9781420042283.ch10.
5. Manski, C.F. "The structure of random utility models", Theory Decis., 8(3), pp. 229-254 (1977). DOI: 10.1007/bf00133443.
6. Walker, J. and Ben-Akiva, M. "Generalized random utility model", Math. Soc. Sci., 43(3), pp. 303-343 (2002). DOI: 10.1016/S0165-4896(02)00023-2.
7. Liu, C., Susilo, Y.O., and Karlstrom, A. "Weather variability and travel behaviour-what we know and what we do not know", Transp. Rev., 37(6), pp. 715- 741 (2017). DOI: 10.1080/01441647.2017.1293182.
8. Rudloff, C., Leodolter, M., Bauer, D., et al. "Influence of weather on transport demand: case study from the Vienna, Austria, region", Transp. Res. Rec., 2482(1), pp. 110-116 (2015). DOI: 10.3141/2482-13.
9. Tsapakis, I., Cheng, T., and Bolbol, A. "Impact of weather conditions on macroscopic urban travel times", J. Transp. Geogr., 28, pp. 204-211 (2013). DOI: 10.1016/j.jtrangeo.2013.01.008.
10. Litman, T. "Landuse impact on transport: how land use factors affect travel behaviour", Victoria Transport Policy Institute, (2012). 
11. McNally, M.G. "The four-step model", Emerald Group Publishing Limited (2007). DOI: 10.1108/s0195- 6310(2009)0000026019.
12. Bouchard, R.J. and Pyers, C.E. "Use of gravity model for describing urban travel", Highw. Res. Rec., 88 (1965).
13. Long, G.D. "An evaluation of the gravity model trip distribution", Texas Transportation Institute (1968). 
14. McFadden, D.L. "Conditional logit analysis of qualitative choice behavior", Front. Econom (1974). 
15. Louviere, J., Street, D., Carson, R., et al. "Dissecting the random component of utility", Mark. Lett., 13(3), pp. 177-193 (2002). DOI: 10.1023/a:1020258402210.
16. Ranganathan, P., Pramesh, C.S., and Aggarwal, R. "Common pitfalls in statistical analysis: intentionto-treat versus per-protocol analysis", Perspect. Clin. Res., 7(3), pp. 144-146 (2016). DOI: 10.4103/2229- 3485.184820.
17. Cramer, J.S. "The origins of logistic regression", SSRN Electron J. (2005). DOI: 10.2139/ssrn.360300.
18. Lindner, A., Pitombo, C.S., and Cunha, A.L. "Estimating motorized travel mode choice using classifiers: An application for high-dimensional multicollinear data", Travel Behav. Soc., 6, pp. 100-109 (2017). DOI: 10.1016/j.tbs.2017.01.004.
19. Duan, Z., Zhang, K., Chen, Z., et al. "Prediction of city-scale dynamic taxi origin-destination  flows using a hybrid deep neural network combined with travel time", IEEE Access, 7, pp. 127816-127832 (2019). DOI: 10.1109/ACCESS.2019.2937885.
20. Zhang, J., Che, H., Chen, F., et al. "Shortterm origin-destination demand prediction in urban rail transit systems: a channel-wise attentive splitconvolutional neural network method", Transp. Res. Part C Emerg. Technol., 124, p. 102928 (2021). DOI: 10.1016/j.trc.2020.102928.
21. Chu, K.F., Lam, A.Y.S., and Li, V.O.K. "Deep multiscale convolutional LSTM network for travel demand and origin-destination predictions", IEEE Trans. Intell. Transp. Syst., 21(8), pp. 3219-3232 (2020). DOI: 10.1109/TITS.2019.2939042.
22. Krishnakumari, P., van Lint, H., Djukic, T., et al. "A data driven method for OD matrix estimation", Transp. Res. Part C Emerg. Technol., 113, pp. 38-56 (2020). DOI: 10.1016/j.trc.2020.01.007.
23. Ke, J., Qin, X., Yang, H., et al. "Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multigraph convolutional network", Transp. Res. Part C Emerg. Technol., 122, p. 102858 (2021). DOI:10.1016/j.trc.2020.102858.
24. Lee, D., Derrible, S., and Pereira, F.C. "Comparison of four types of artificial neural network and a multinomial logit model for travel mode choice modeling", Transp. Res. Rec., 2672(49), pp. 101-112 (2018). DOI: 10.1177/0361198118783167.
25. Golshani, N., Shabanpour, R., Mahmoudifard, S.M., et al. "Modeling travel mode and timing decisions: comparison of artificial neural networks and copulabased joint model", Travel Behav. Soc., 10(1), pp. 21- 32 (2018). DOI: 10.1016/j.tbs.2018.02.001.
26. Brathwaite, T., Vij, A., and Walker, J.L. "Machine learning meets microeconomics: the case of decision trees and discrete choice", Travel Behaviour and Society, 9(1), pp. 41-54 (2017). DOI: 10.1016/j.tbs.2017.05.006.
27. Xiong, X., Ozbay, K., Jin, L., et al. "Dynamic origin-destination matrix prediction with line graph neural networks and Kalman filter", Transp. Res. Rec., 2674(8), pp. 491-503 (2020). DOI: 10.1177/0361198120933921.
28. Yaldi, G., Taylor, M.a.P., and Yue, W.L. "Using artificial neural network in passenger trip distribution modelling (a case study in Padang, Indonesia) ", Proc. East. Asia Soc. Transp. Stud., pp. 105-105 (2009). DOI: 10.11175/eastpro.2009.0.105.0.
29. Hyland, M., Frei, C., Frei, A., et al. "Riders on the storm: exploring weather and seasonality effects on commute mode choice in Chicago", Travel Behav. Soc., 13, pp. 44-60 (2018). DOI: 10.1016/j.tbs.2018.04.002.
30. Dong, X., Wang, L., and Hu, B. "Analysis of spatio-temporal distribution characteristics of passenger travel behaviour based on online ride-sharing trajectory data", J. Phys. Conf. Ser., 1187(5), p. 052055 (2019). DOI: 10.1088/1742-6596/1187/5/052055.
31. Regehr, J.D., Montufar, J., and Hernandez-Vega, H. "Traffic pattern groups based on hourly traffic variations in urban areas", J. Transp. Inst. Transp. Eng., 7(1), pp. 1-16 (2015).
32. Fujita, M., Yamada, S., and Murakami, S. "Time coefficient estimation for hourly origin-destination demand from observed link  flow based on semidynamic traffic assignment", J. Adv. Transp., 2017(1), pp. 1-14 (2017). DOI: 10.1155/2017/7453126.
33. Venkatanarayana, R., Smith, B.L., and Demetsky, M.J. "Quantum-frequency algorithm for automated identification of traffic patterns", Transp. Res. Rec., 2024(1), pp. 8-17 (2007). DOI: 10.3141/2024-02.
34. Yu, Q., Xie, Y., Li, W., et al. "GPS data in urban bicycle-sharing: dynamic electric fence planning with assessment of resource-saving and potential energy consumption increasement", Appl. Energy, 322, p. 119533 (2022). DOI: 10.1016/j.apenergy.2022.119533.
35. Shang, W.-L., Chen, J., Bi, H., et al. "Impacts of COVID-19 pandemic on user behaviors and environmental benefits of bike sharing: A big-data analysis", Appl. Energy, 285, p. 116429 (2021). DOI: 10.1016/j.apenergy.2020.116429.
36. Shang, W.-L., Chen, Y., and Ochieng, W.Y. "Resilience analysis of transport networks by combining variable message signs with agent-based day-to-day dynamic learning", IEEE Access, 8, pp. 104458-104468 (2020). DOI: 10.1109/ACCESS.2020.2997657.
37. Shang, W., Han, K., Ochieng, W., and Angeloudis, P. "Agent-based day-to-day traffic network model with information percolation", Transp. Transp. Sci., 13(1), pp. 38-66 (2017). DOI: 10.1080/18128602.2017.1292829.
38. Deri, J.A., Franchetti, F., and Moura, J.M.F. "Big data computation of taxi movement in New York City", 2016 IEEE Int. Conf. Big Data Big Data, pp. 2616-2625 (2016). DOI: 10.1109/Big- Data.2016.7840933.
39. Freire, J., Bessa, A., Chirigati, F., et al. "Exploring what not to clean in urban data: a study using New York City taxi trips", IEEE Data Eng. Bull., 39(2), pp. 63-77 (2013). DOI: 10.1109/tvcg.2013.226.
40. Patel, U. "NYC taxi trip and fare data analytics using bigdata" (2015). DOI:10.13140/RG.2.1.3511.0485.
41. Martinez, L.M., Viegas, J.M., and Silva, E.A. "A traffic analysis zone definition: a new methodology and algorithm", Transportation, 36(5), pp. 581-599 (2009). DOI: 10.1007/s11116-009-9225-7.
42. Rousseeuw, P.J. and Hubert, M. "Robust statistics for outlier detection", WIREs Data Min. Knowl. Discov., 1(1), pp. 73-79 (2011). DOI: 10.1002/widm.2.
43. Shanker, M., Hu, M.Y., and Hung, M.S. "Effect of data standardization on neural network training", Omega, 24(4), pp. 385-397 (1996). DOI: 10.1016/0305- 0483(96)00010-2.
44. LeCun, Y., Bengio, Y., and Hinton, G. "Deep learning", Nature, 521(7553), pp. 436-444 (2015). DOI: 10.1038/nature14539.
45. Nwankpa, C., Ijomah, W., Gachagan, A., and Marshall, S. "Activation functions: comparison of trends in practice and research for deep learning", 2nd International Conference on Computational Sciences and Technology, pp. 124-133 (2021). DOI: 10.48550/arXiv.1811.03378.
46. Taxi, N.Y. and (TLC), L.C. "New York City Green Taxi Trip Data", Available: https://www.nyc. gov/site/tlc/about/tlc-trip-record-data.page (2018).
47. Department of City Planning's Neighborhood Tabulation Areas (NTAs), N.Y.C.D., "NYC Taxi Zones", https://catalog.data.gov/dataset/nyc-taxi-zones/resource/79e158e7-d158-4ace-b9d3-41ede473c76c (2019).
48. (NCDC), N.C.D.C. "NYC 2018 Hourly Surface Data", Available: https://www.ncei.noaa.gov/products/land-based-station/integrated-surface-database (2018).
49. Tang, J., Liu, F.,Wang, Y., andWang, H. "Uncovering urban human mobility from large scale taxi GPS data", Phys. Stat. Mech. Its Appl., 438, pp. 140-153 (2015).DOI: 10.1016/j.physa.2015.06.032.
50. Office of the New York State Comptroller, O."An Economic Snapshot of the East Harlem Neighborhood" (2018). https://www.osc.state.ny.us/files/reports/osdc/pdf/report-9-2018.pdf.
51. Office of City Planning, N.Y.C.D. "New York City's Zoning and Land Use Map", p. 5 (2020).https://zola.planning.nyc.gov/.
52. Chollet, F. "Keras" https://github.com/fchollet/keras (2015).
53. Wilson, A.G. "Advances and problems in distribution modelling", Transp. Res., 4(1), pp. 1-18 (1970). DOI: 10.1016/0041-1647(70)90071-7.
54. Duffus, L.N., Sule Alfa, A., and Soliman, A.H. "The reliability of using the gravity model for forecasting trip distribution", Transportation, 14(3), pp. 175-192 (1987). DOI: 10.1007/bf00837528.
55. Celik, H.M. "Sample size needed for calibrating trip distribution and behavior of the gravity model", J. Transp. Geogr., 18(1), pp. 183-190 (2010). DOI: 10.1016/j.jtrangeo.2009.04.004.
56. Willmott, C.J. "On the validation of models", Phys. Geogr., 2(2), pp. 184-194 (1981). DOI: 10.1080/02723646.1981.10642213.
57. Schemper, M., "Predictive accuracy and explained variation", Stat. Med., 22(14), pp. 2299-2308 (2003). DOI: 10.1002/sim.1522.
Scientia Iranica
Volume 31, Issue 19
Transactions on Civil Engineering (A)
November and December 2024
Pages 1711-1726

Files

History

  • Receive Date: 27 April 2021
  • Revise Date: 26 April 2023
  • Accept Date: 17 July 2023

Share

How to cite

Statistics