A Comparison of Machine Learning Models in Predicting Competition Between High-Speed Rail (HSR) and Air Transport: The Tehran-Mashhad Case Study

Document Type : Original Article

Authors

1 Department of Civil Engineering, SR.C., Islamic Azad University, Tehran, Iran

2 Department of Civil and Environmental Engineering, Tarbiat Modares University, Tehran, Iran

Abstract

Mode choice modeling represents a fundamental domain within transportation engineering and urban-regional planning. The competition between high-speed rail (HSR) and air travel holds particular significance for demand forecasting, revenue optimization, environmental policy, and infrastructure development. Traditional discrete choice models have long served as the cornerstone of mode choice analysis. These models offer interpretability, compatibility with stated and revealed preference data, and the capacity to compute policy-relevant elasticities. However, they suffer from critical limitations, such as the independence of irrelevant alternatives (IIA) assumption and inability to accommodate large, noisy datasets. Conversely, Machine Learning (ML) methodologies have gained prominence for their capacity to handle complex, nonlinear, and high-dimensional data. By applying Artificial Neural Network (ANN), Random Forest (RF), Decision Tree (DT), and K-Nearest Neighbor (KNN), this study addresses two critical research gaps: (1) the scarcity of ML applications in developing countries with limited HSR infrastructure, and (2) the limited incorporation of psychological factors alongside socio-economic variables. Using stated preference data from 100 Iranian respondents across 18 travel scenarios, this research develops ML-based models, examining variables such as travel time, cost, income, service frequency, previous travel experiences, and psychological factors including fear of flying. The findings reveal that ANN emerged as the top performer with an overall accuracy of 84.67%. The RF model followed with 82.44% accuracy, showing robust predictive capability with relatively balanced class-wise performance, though slightly favoring the majority class. Also, class-specific analysis across all models consistently demonstrated higher precision for airplane predictions.

Keywords

Main Subjects

References

  1. Banyong, C., Hantanong, N., Wisutwattanasak, P., Champahom, T., Theerathitichaipa, K., Seefong, M., Ratanavaraha, V., Jomnonkwao, S. A machine learning comparison of transportation mode changes from high-speed railway promotion in Thailand. Results in Engineering, 2024; 24: 103110. doi:10.1016/j.rineng.2024.103110.
  2. Cao, W., Chen, Z., Shi, F., Xu, J. Analysis of travel mode choice behavior between high-speed rail and air transport utilizing large-scale ticketing data. Transportation Research Record: Journal of the Transportation Research Board, 2024; 2679: 1344–1358. doi:10.1177/03611981241270169.
  3. Li, X., Wang, Y., Wu, Y., Chen, J., Zhou, J. Modeling Intercity Travel Mode Choice with Data Balance Changes: A Comparative Analysis of Bayesian Logit Model and Artificial Neural Networks. Journal of Advanced Transportation, 2021; 2021: 9219176. doi:10.1155/2021/9219176.
  4. Banyong, C., Hantanong, N., Nanthawong, S., Se, C., Wisutwattanasak, P., Champahom, T., Ratanavaraha, V., Jomnonkwao, S. Machine learning-based analysis of travel mode preferences: Neural and boosting model comparison using stated preference data from Thailand’s emerging high-speed rail network. Big Data and Cognitive Computing, 2025; 9: 155. doi:10.3390/bdcc9060155.
  5. Zhao, X., Yan, X., Yu, A., Van Hentenryck, P. Prediction and behavioral analysis of travel mode choice: A comparison of machine learning and logit models. Travel Behaviour and Society, 2020; 20: 22–35. doi:10.1016/j.tbs.2020.02.003.
  6. Ali, M. Discrete Choice Models and Artificial Intelligence Techniques for Predicting the Determinants of Transport Mode Choice—A Systematic Review. Computers, Materials and Continua, 2024; 81: 2161–2194. doi:10.32604/cmc.2024.058888.
  7. Fale, M., Wang, Y., Rupnik, B., Kramberger, T., Vizinger, T. Systematic review of transportation choice modeling. Applied Sciences, 2025; 15: 9235. doi:10.3390/app15179235.
  8. Forsythe, C. R., Arteaga, C., Helveston, J. P. The Mixed Aggregate Preference Logit Model: A Machine Learning Approach to Modeling Unobserved Heterogeneity in Discrete Choice Analysis. arXiv preprint arXiv:2402.00184, 2024; doi:10.48550/arXiv.2402.00184.
  9. Givoni, M., Dobruszkes, F. A review of ex-post evidence for mode substitution and induced demand following the introduction of high-speed rail. Transport Reviews, 2013; 33: 720–742. doi:10.1080/01441647.2013.853707.
  10. Fu, X., Oum, T. H., Yan, J. An analysis of travel demand in Japan's intercity market empirical estimation and policy simulation. Journal of Transport Economics and Policy (JTEP), 2014; 48: 97–113. doi:10.3828/jtep.2014.48.1.97.
  11. Raturi, V., Verma, A. A game-theoretic approach to analyse inter-modal competition between high-speed rail and airlines in the Indian context. Transportation Planning and Technology, 2020; 43: 20–47. doi:10.1080/03081060.2020.1701666.
  12. Xia, W., Wang, K., Zhang, A. Air transport and high-speed rail interactions in China: review on impacts of low-cost carriers, rail speed, and modal integration. Advances in Airline Economics, 2018; 7: 103–122. doi:10.1108/S2212-160920180000007007.
  13. Xia, W., Zhang, A. Air and high-speed rail transport integration on profits and welfare: Effects of air-rail connecting time. Journal of Air Transport Management, 2017; 65: 181–190. doi:10.1016/j.jairtraman.2017.06.008.
  14. Park, Y., Ha, H.-K. Analysis of the impact of high-speed railroad service on air transport demand. Transportation Research Part E: Logistics and Transportation Review, 2006; 42: 95–104. doi:10.1016/j.tre.2005.09.003.
  15. Román, C., Martín, J. Potential demand for new high speed rail services in high dense air transport corridors. International Journal of Sustainable Development and Planning, 2010; 5: 114–129. doi:10.2495/SDP-V5-N2-114-129.
  16. Raturi, V., Verma, A. Analyzing competition between High Speed Rail and Bus mode using market entry game analysis. Transportation Research Procedia, 2017; 25: 2373–2384. doi:10.1016/j.trpro.2017.05.264.
  17. Raturi, V., Verma, A. Competition between High Speed Rail and Conventional Transport Modes: Market Entry Game Analysis on Indian Corridors. Networks and Spatial Economics, 2019; 19: 763–790. doi:10.1007/s11067-018-9421-2.
  18. D’Alfonso, T., Jiang, C., Bracaglia, V. Would competition between air transport and high-speed rail benefit environment and social welfare? Transportation Research Part B: Methodological, 2015; 74: 118–137. doi:10.1016/j.trb.2015.01.007.
  19. D’Alfonso, T., Jiang, C., Bracaglia, V. Air transport and high-speed rail competition: Environmental implications and mitigation strategies. Transportation Research Part A: Policy and Practice, 2016; 92: 261–276. doi:10.1016/j.tra.2016.06.009.
  20. Wang, J., Jiao, J., Du, C., Hu, H. Competition of spatial service hinterlands between high-speed rail and air transport in China: Present and future trends. Journal of Geographical Sciences, 2015; 25: 1137–1152. doi:10.1007/s11442-015-1224-5.
  21. Edrissi, A., Javanbakht, N., Ganjipour, H. Modeling the behavior of disordered taxi drivers of Tehran for choosing passenger and destination. International Journal of Human Capital in Urban Management, 2019; 4: 69–76. doi:10.22034/IJHCUM.2019.01.08.
  22. Pagliara, F., Vassallo, J. M., Román, C. High-speed rail versus air transportation: Case study of Madrid–Barcelona, Spain. Transportation Research Record: Journal of the Transportation Research Board, 2012; 2289: 10–17. doi:10.3141/2289-02.
  23. Javanbakht, N., Mirbaha, B. Evaluating Drivers’ Response to Road Hazard: A Simulation Study. Advances in Civil Engineering, 2024; 2024: 6788857. doi:10.1155/2024/6788857.
  24. Javanbakht, N., Mirbaha, B. From Traits to Speed Control: Engineering Insights from a Driving-Simulator Hazard Scenario. Contributions of Science and Technology for Engineering, 2026; 3: 10–19. doi:10.22080/cste.2025.29839.1075.
  25. Pan, J. High-Speed Rail in the US—Mode Choice Decision and Impact of COVID-19. Sustainability, 2024; 16: 4041. doi:10.3390/su16104041.
  26. Hillel, T., Bierlaire, M., Elshafie, M. Z. E. B., Jin, Y. A systematic review of machine learning classification methodologies for modelling passenger mode choice. Journal of Choice Modelling, 2021; 38: 100221. doi:10.1016/j.jocm.2020.100221.
  27. Chmielewski, J., Wójcik, M. The Use of Deep Neural Networks (DNN) in Travel Demand Modelling. Applied Sciences, 2025; 15: 11290. doi:10.3390/app152011290.
  28. Buijs, R., Koch, T., Dugundji, E. Using neural nets to predict transportation mode choice: Amsterdam network change analysis. Journal of Ambient Intelligence and Humanized Computing, 2021; 12: 121–135. doi:10.1007/s12652-020-02855-6.
  29. Tang, L., Tang, C., Fu, Q., Ma, C. Predicting travel mode choice with a robust neural network and Shapley additive explanations analysis. IET Intelligent Transport Systems, 2024; 18: 1339–1354. doi:10.1049/itr2.12514.
  30. Amoei Khorshidi, N., Zargari, S., Mirzahossein, H., Heidari, H., Waller, S. Predicting travel-time reliability in road networks: a Fitrnet-based approach–a case study of England. Scientific Journal of Silesian University of Technology. Series Transport, 2025; 126: 79–95. doi:10.20858/sjsutst.2025.126.5.
  31. Bhosle, N., Jagtap, J., Svitek, M. Machine Learning-Based Travel Mode Prediction: A Comparative Methodological Approach. In: 2025 Smart City Symposium Prague (SCSP); 2025; Prague. p. 1–5. doi:10.1109/SCSP65598.2025.11037720.
  32. Zhang, W., Luo, Z. Research on intercity travel mode recognition and network structure characteristics based on complex network and random forest classification. Scientific Reports, 2025; 15: 35339. doi:10.1038/s41598-025-19392-x.
  33. Naseri, H., Waygood, E. O. D., Patterson, Z., Alousi-Jones, M., Wang, B. Travel mode choice prediction: developing new techniques to prioritize variables and interpret black-box machine learning techniques. Transportation Planning and Technology, 2025; 48: 582–605. doi:10.1080/03081060.2024.2411611.
  34. Afandizadeh Zargari, S., Amoei Khorshidi, N., Mirzahossein, H., Heidari, H. Analyzing the effects of congestion on planning time index–Grey models vs. random forest regression. International Journal of Transportation Science and Technology, 2023; 12: 578–593. doi:10.1016/j.ijtst.2022.05.008.
  35. Kalantari, H., Sabouri, S., Brewer, S., Ewing, R., Tian, G. Machine learning in mode choice prediction as part of mpos’ regional travel demand models: Is it time for change? Sustainability, 2025; 17: 3580. doi:10.3390/su17083580.
  36. Uddin, M., Anowar, S., Eluru, N. Modeling freight mode choice using machine learning classifiers: a comparative study using Commodity Flow Survey (CFS) data. Transportation Planning and Technology, 2021; 44: 543–559. doi:10.1080/03081060.2021.1927306.
  37. Ghosh, T., Nagaraj, N. Evaluating the determinants of mode choice using statistical and machine learning techniques in the Indian megacity of Bengaluru. arXiv preprint arXiv:2401.13977, 2024; doi:10.48550/arXiv.2401.13977.
  38. Dahmen, V., Weikl, S., Bogenberger, K. Interpretable machine learning for mode choice modeling on tracking-based revealed preference data. Transportation Research Record: Journal of the Transportation Research Board, 2024; 2678: 2075–2091. doi:10.1177/03611981241246973.
  39. Afandizadeh, S., Amoei Khorshidi, N., Mirzahossein, H., Shakoori, S. Predicting the fluctuation of travel time reliability as a result of congestion variations by bagging-based regressors. Civil Engineering Infrastructures Journal, 2024; 57: 85–101. doi:10.22059/ceij.2023.349853.1878.
  40. Jang, J. Travel-time prediction using K-nearest neighbor method with distance metric of correlation coefficient. The Open Transportation Journal, 2019; 13: 141–150. doi:10.2174/1874447801913010141.
  41. Lagos, F., Moreno, S., Yushimito, W. F., Brstilo, T. Urban Origin–Destination Travel Time Estimation Using K-Nearest-Neighbor-Based Methods. Mathematics, 2024; 12: 1255. doi:10.3390/math12081255.
  42. Afandizadeh Zargari, S., Amoei Khorshidi, N., Mirzahossein, H., Kalantari, N. Comparative approach for predicting travel time reliability (a case study of Virginia interstate). Innovative Infrastructure Solutions, 2021; 6: 229. doi:10.1007/s41062-021-00597-8.
  43. Khorshidi, N., Rezashoar, S., Amini, P., Zargari, S. A., Mirzahossein, H. Metaheuristic-optimized neural networks for travel time index prediction: a comparative study of wild horse and coot optimization algorithms. Transportation Engineering, 2025; 22: 100395. doi:10.1016/j.treng.2025.100395.
  44. Khorshidi, N., Zargari, S. A., Rezashoar, S., Mirzahossein, H. Optimizing Travel Time Reliability with XAI: A Virginia Interstate Network Case Using Machine Learning and Meta-Heuristics. Machine Learning with Applications, 2025; 21: 100709. doi:10.1016/j.mlwa.2025.100709.
  45. Zargari, S. A., Khorshidi, N. A., Mirzahossein, H., Shakoori, S., Jin, X. Travel time reliability prediction by genetic algorithm and machine learning models. Proceedings of the Institution of Civil Engineers - Transport, 2022; 177: 214–223. doi:10.1680/jtran.22.00065.
Civil Engineering and Applied Solutions
Volume 3, Issue 1
Issue in Progress
January 2027
Pages 146-160

Files

History

  • Receive Date: 26 March 2026
  • Revise Date: 23 April 2026
  • Accept Date: 18 May 2026
  • First Publish Date: 24 May 2026

Share

How to cite

Statistics