Data-driven models; delays forecasting; freight transport; gradient boosting; rail operation delays; Biological system modeling; Data-driven model; Delay; Delay forecasting; Freight transport; Gradient boosting; Predictive models; Rail operation delay; Rail operations; Rail transportation; Computer Science (all); Materials Science (all); Engineering (all); Delays; Data models; Analytical models; Freight handling; INDEX TERMS; General Engineering; General Materials Science; General Computer Science; Electrical and Electronic Engineering
Résumé :
[en] Despite rail's growing popularity as a mode of freight transportation due to its role in intermodal transportation and numerous economic and environmental benefits, optimizing all aspects of rail infrastructure use remains a significant challenge. To address this issue, various methods for developing train disruption prediction models have been used. However, these models continue to struggle with accurately predicting short-term arrival delay times, as well as identifying the causes of delays and the expected impact on operations. The lack of information available to operators makes it difficult for them to effectively mitigate the effects of disruptions. The goal of this study is to investigate a set of data-driven models for the short-term prediction of arrival delay time using data from the National Railway Company of Luxembourg of freight rail operations between Bettembourg (Luxembourg) and other nine terminal stations across the EU, and then investigate the effects of the features associated with the arrival delay time. For our dataset, the lightGBM model outperformed other models in predicting the arrival delay time in freight rail operations, with departure delay time, trip distance, and train composition appearing to be the most influential features in predicting the arrival delay time in the short-term. The National Railway Company of Luxembourg can use the short-term prediction model developed in this study as a decision-support system. For example, knowing a train's arrival delay time allows you to estimate future operational time, providing more support to reduce disruptions and subsequent operational delays via a simple web service.
Disciplines :
Ingénierie, informatique & technologie: Multidisciplinaire, généralités & autres
Auteur, co-auteur :
Pineda-Jaramillo, Juan ; University of Luxembourg, Department of Engineering, Esch-sur-Alzette, Luxembourg
BIGI, Federico ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
Bosi, Tommaso ; Roma Tre University, Department of Civil, Computer Science and Aeronautical Technologies Engineering, Rome, Italy
VITI, Francesco ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Engineering (DoE)
D'ariano, Andrea ; Roma Tre University, Department of Civil, Computer Science and Aeronautical Technologies Engineering, Rome, Italy
Co-auteurs externes :
yes
Langue du document :
Anglais
Titre :
Short-Term Arrival Delay Time Prediction in Freight Rail Operations Using Data-Driven Models
Date de publication/diffusion :
2023
Titre du périodique :
IEEE Access
ISSN :
2169-3536
Maison d'édition :
Institute of Electrical and Electronics Engineers Inc.
V. Cacchiani, A. Caprara, and P. Toth, "Scheduling extra freight trains on railway networks," Transp. Res. B, Methodol., vol. 44, no. 2, pp. 215-231, Feb. 2010, doi: 10.1016/j.trb.2009.07.007.
P. Mcmahon, T. Zhang, and R. Dwight, "Requirements for big data adoption for railway asset management," IEEE Access, vol. 8, pp. 15543-15564, 2020, doi: 10.1109/ACCESS.2020.2967436.
Q. Li, J.-C. Sibel, M. Berbineau, I. Dayoub, F. Gallee, and H. Bonneville, "Physical layer enhancement for next-generation railway communication systems," IEEE Access, vol. 10, pp. 83152-83175, 2022, doi: 10.1109/ACCESS.2022.3192971.
N. Zhao, C. Roberts, S. Hillmansen, and G. Nicholson, "A multiple train trajectory optimization to minimize energy consumption and delay," IEEE Trans. Intell. Transp. Syst., vol. 16, no. 5, pp. 2363-2372, Oct. 2015, doi: 10.1109/TITS.2014.2388356.
M. S. Artan and I. Sahin, "Exploring patterns of train delay evolution and timetable robustness," IEEE Trans. Intell. Transp. Syst., vol. 23, no. 8, pp. 11205-11214, Aug. 2022, doi: 10.1109/TITS.2021.3101530.
F. Bigi, T. Bosi, J. Pineda-Jaramillo, F. Viti, and A. D'Ariano. (2023). Addressing the Impact of Maintenance in Shunting Operations Through Shunt-In Policies for Freight Trains Operations. [Online]. Available: http://hdl.handle.net/10993/53485
N. Bešinovic, R. M. P. Goverde, E. Quaglietta, and R. Roberti, "An integrated micro-macro approach to robust railway timetabling," Transp. Res. B, Methodol., vol. 87, pp. 14-32, May 2016, doi: 10.1016/j.trb.2016.02.004.
F. Corman and L. Meng, "A review of online dynamic models and algorithms for railway traffic management," IEEE Trans. Intell. Transp. Syst., vol. 16, no. 3, pp. 1274-1284, Jun. 2015, doi: 10.1109/TITS.2014.2358392.
P. Bhavsar, I. Safro, N. Bouaynaya, R. Polikar, and D. Dera, "Machine learning in transportation data analytics," in Data Analytics for Intelligent Transportation Systems, M. Chowdhury, A. Apon, and K. Dey, Eds. Amsterdam, The Netherlands: Elsevier, 2017, pp. 283-307, doi: 10.1016/B978-0-12-809715-1.00012-2.
J. D. Pineda-Jaramillo, R. Insa, and P. Martínez, "Modeling the energy consumption of trains by applying neural networks," Proc. Inst. Mech. Engineers, F, J. Rail Rapid Transit, vol. 232, no. 3, pp. 816-823, Mar. 2018, doi: 10.1177/0954409717694522.
S. Milinkovic, M. Markovic, S. Veskovic, M. Ivic, and N. Pavlovic, "A fuzzy Petri net model to estimate train delays," Simul. Model. Pract. Theory, vol. 33, pp. 144-157, Apr. 2013, doi: 10.1016/j.simpat.2012.12.005.
V. De Martinis and F. Corman, "Data-driven perspectives for energy efficient operations in railway systems: Current practices and future opportunities," Transp. Res. C, Emerg. Technol., vol. 95, pp. 679-697, Oct. 2018, doi: 10.1016/j.trc.2018.08.008.
J. Pineda-Jaramillo, P. Martínez-Fernández, I. Villalba-Sanchis, P. Salvador-Zuriaga, and R. Insa-Franco, "Predicting the traction power of metropolitan railway lines using different machine learning models," Int. J. Rail Transp., vol. 9, no. 5, pp. 461-478, Sep. 2021, doi: 10.1080/23248378.2020.1829513.
H. Alawad, S. Kaewunruen, and M. An, "A deep learning approach towards railway safety risk assessment," IEEE Access, vol. 8, pp. 102811-102832, 2020, doi: 10.1109/ACCESS.2020.2997946.
P. Kecman and R. M. P. Goverde, "Predictive modelling of running and dwell times in railway traffic," Public Transp., vol. 7, no. 3, pp. 295-319, Dec. 2015, doi: 10.1007/s12469-015-0106-7.
D. Li, W. Daamen, and R. M. P. Goverde, "Estimation of train dwell time at short stops based on track occupation event data: A study at a Dutch railway station," J. Adv. Transp., vol. 50, no. 5, pp. 877-896, Aug. 2016, doi: 10.1002/atr.1380.
P. Huang, C. Wen, Q. Peng, C. Jiang, Y. Yang, and Z. Fu, "Modeling the influence of disturbances in high-speed railway systems," J. Adv. Transp., vol. 2019, pp. 1-13, Mar. 2019, doi: 10.1155/2019/8639589.
C. Wen, Z. Li, J. Lessan, L. Fu, P. Huang, and C. Jiang, "Statistical investigation on train primary delay based on real records: Evidence from Wuhan-Guangzhou HSR," Int. J. Rail Transp., vol. 5, no. 3, pp. 170-189, Jul. 2017, doi: 10.1080/23248378.2017.1307144.
P. Huang, T. Spanninger, and F. Corman, "Enhancing the understanding of train delays with delay evolution pattern discovery: A clustering and Bayesian network approach," IEEE Trans. Intell. Transp. Syst., vol. 23, no. 9, pp. 15367-15381, Sep. 2022, doi: 10.1109/TITS.2022. 3140386.
J. Barta, A. E. Rizzoli, M. Salani, and L. M. Gambardella, "Statistical modelling of delays in a rail freight transportation network," in Proc. Title, Winter Simul. Conf. (WSC), Dec. 2012, pp. 1-12, doi: 10.1109/WSC.2012.6465188.
F. Corman, A. D'Ariano, and I. A. Hansen, "Evaluating disturbance robustness of railway schedules," J. Intell. Transp. Syst., vol. 18, no. 1, pp. 106-120, Jan. 2014, doi: 10.1080/15472450.2013. 801714.
F. Corman and P. Kecman, "Stochastic prediction of train delays in realtime using Bayesian networks," Transp. Res. C, Emerg. Technol., vol. 95, pp. 599-615, Oct. 2018, doi: 10.1016/j.trc.2018.08.003.
A. Balster, O. Hansen, H. Friedrich, and A. Ludwig, "An ETA prediction model for intermodal transport networks based on machine learning," Bus. Inf. Syst. Eng., vol. 62, no. 5, pp. 403-416, Oct. 2020, doi: 10.1007/s12599-020-00653-0.
I. A. Hansen, R. M. P. Goverde, and D. J. van der Meer, "Online train delay recognition and running time prediction," in Proc. 13th Int. IEEE Conf. Intell. Transp. Syst. Lisbon, Portugal: IEEE, Sep. 2010, pp. 1783-1788, doi: 10.1109/ITSC.2010.5625081.
J. Luo, Q. Peng, C. Wen, W. Wen, and P. Huang, "Data-driven decision support for rail traffic control: A predictive approach," Exp. Syst. Appl., vol. 207, Nov. 2022, Art. no. 118050, doi: 10.1016/j.eswa.2022.118050.
J. Peters, B. Emig, M. Jung, and S. Schmidt, "Prediction of delays in public transportation using neural networks," in Proc. Int. Conf. Comput. Intell. Model., Control Autom. Int. Conf. Intell. Agents, Web Technol. Internet Commerce (CIMCA-IAWTIC), 2005, pp. 92-97, doi: 10.1109/CIMCA.2005.1631451.
S. Pongnumkul, T. Pechprasarn, N.Kunaseth, and K. Chaipah, "Improving arrival time prediction of Thailand's passenger trains using historical travel times," in Proc. 11th Int. Joint Conf. Comput. Sci. Softw. Eng. (JCSSE), May 2014, pp. 307-312, doi: 10.1109/JCSSE.2014.6841886.
L. Oneto, E. Fumeo, G. Clerico, R. Canepa, F. Papa, C. Dambra, N. Mazzino, and D. Anguita, "Dynamic delay predictions for large-scale railway networks: Deep and shallow extreme learning machines tuned via thresholdout," IEEE Trans. Syst., Man, Cybern. Syst., vol. 47, no. 10, pp. 2754-2767, Oct. 2017, doi: 10.1109/TSMC.2017.2693209.
W. Barbour, J. C. M. Mori, S.Kuppa, and D. B.Work, "Prediction of arrival times of freight traffic on US railroads using support vector regression," Transp. Res. C, Emerg. Technol., vol. 93, pp. 211-227, Aug. 2018, doi: 10.1016/j.trc.2018.05.019.
N. Minbashi, H. Sipilä, C.-W. Palmqvist, M. Bohlin, and B. Kordnejad, "Machine learning-Assisted macro simulation for yard arrival prediction," J. Rail Transp. Planning Manage., vol. 25, Mar. 2023, Art. no. 100368, doi: 10.1016/j.jrtpm.2022.100368.
J. Pineda-Jaramillo and F. Viti, "Identifying the rail operating features associated to intermodal freight rail operation delays," Transp. Res. C, Emerg. Technol., vol. 147, Feb. 2023, Art. no. 103993, doi: 10.1016/j.trc.2022.103993.
N. Minbashi, M. Bohlin, C.-W. Palmqvist, and B. Kordnejad, "The application of tree-based algorithms on classifying shunting yard departure status," J. Adv. Transp., vol. 2021, pp. 1-10, Sep. 2021, doi: 10.1155/2021/3538462.
P. Huang, J. Lessan, C.Wen, Q. Peng, L. Fu, L. Li, and X. Xu, "A Bayesian network model to predict the effects of interruptions on train operations," Transp. Res. C, Emerg. Technol., vol. 114, pp. 338-358, May 2020, doi: 10.1016/j.trc.2020.02.021.
P. Huang, C. Wen, L. Fu, Q. Peng, and Y. Tang, "A deep learning approach for multi-Attribute data: A study of train delay prediction in railway systems," Inf. Sci., vol. 516, pp. 234-253, Apr. 2020, doi: 10.1016/j.ins.2019.12.053.
Y. Yang, P. Huang, Q. Peng, J. Li, and C. Wen, "Statistical delay distribution analysis on high-speed railway trains," J. Modern Transp., vol. 27, no. 3, pp. 188-197, Sep. 2019, doi: 10.1007/s40534-019-0188-z.
J. Lessan, L. Fu, and C. Wen, "A hybrid Bayesian network model for predicting delays in train operations," Comput. Ind. Eng., vol. 127, pp. 1214-1222, Jan. 2019, doi: 10.1016/j.cie.2018.03.017.
M. A. Nabian, N. Alemazkoor, and H. Meidani, "Predicting near-Term train schedule performance and delay using bi-level random forests," Transp. Res. Record, J. Transp. Res. Board, vol. 2673, no. 5, pp. 564-573, May 2019, doi: 10.1177/0361198119840339.
R. Nair, T. L. Hoang, M. Laumanns, B. Chen, R. Cogill, J. Szabó, and T. Walter, "An ensemble prediction model for train delays," Transp. Res. C, Emerg. Technol., vol. 104, pp. 196-209, Jul. 2019, doi: 10.1016/j.trc.2019.04.026.
J. Lessan, L. Fu, C. Wen, P. Huang, and C. Jiang, "Stochastic model of train running time and arrival delay: A case study of Wuhan-Guangzhou high-speed rail," Transp. Res. Record, J. Transp. Res. Board, vol. 2672, no. 10, pp. 215-223, Dec. 2018, doi: 10.1177/0361198118780830.
W. Barbour, C. Samal, S. Kuppa, A. Dubey, and D. B. Work, "On the data-driven prediction of arrival times for freight trains on U.S. railroads," in Proc. 21st Int. Conf. Intell. Transp. Syst. (ITSC), Nov. 2018, pp. 2289-2296, doi: 10.1109/ITSC.2018.8569406.
L. Oneto, E. Fumeo, G. Clerico, R. Canepa, F. Papa, C. Dambra, N. Mazzino, and D. Anguita, "Train delay prediction systems: A big data analytics perspective," Big Data Res., vol. 11, pp. 54-64, Mar. 2018, doi: 10.1016/j.bdr.2017.05.002.
F. Cerreto, B. F. Nielsen, O. A. Nielsen, and S. S. Harrod, "Application of data clustering to railway delay pattern recognition," J. Adv. Transp., vol. 2018, pp. 1-18, Apr. 2018, doi: 10.1155/2018/6164534.
I. Sahin, "Markov chain model for delay distribution in train schedules: Assessing the effectiveness of time allowances," J. Rail Transp. Planning Manage., vol. 7, no. 3, pp. 101-113, Dec. 2017, doi: 10.1016/j.jrtpm.2017.08.006.
F. Cerreto, O. A. Nielsen, S. Harrod, and B. F. Nielsen, "Causal analysis of railway running delays," in Proc. 11th World Congr. Railway Res. (WCRR), Milan, Italy, 2016. [Online]. Available: https://orbit.dtu.dk/en/publications/causal-Analysis-of-railway-running-delays
A. A. Zilko, D. Kurowicka, and R. M. P. Goverde, "Modeling railway disruption lengths with copula Bayesian networks," Transp. Res. C, Emerg. Technol., vol. 68, pp. 350-368, Jul. 2016, doi: 10.1016/j.trc.2016.04.018.
J. Pineda-Jaramillo, W. McDonald, W. Zheng, and F. Viti, "Identifying the major causes associated to rail intermodal operation disruptions using causal machine learning," in Proc. 101st Transp. Res. Board, Washington, DC, USA, 2022. [Online]. Available: http://hdl.handle.net/10993/53922
D. Bollegala, "Dynamic feature scaling for online learning of binary classifiers," Knowl.-Based Syst., vol. 129, pp. 97-105, Aug. 2017, doi: 10.1016/j.knosys.2017.05.010.
R. Kang, J. Wang, J. Chen, J. Zhou, Y. Pang, and J. Cheng, "Analysis of failure features of high-speed automatic train protection system," IEEE Access, vol. 9, pp. 128734-128746, 2021, doi: 10.1109/ACCESS.2021.3113381.
P. Gaur, K. McCreadie, R. B. Pachori, H. Wang, and G. Prasad, "An automatic subject specific channel selection method for enhancing motor imagery classification in EEG-BCI using correlation," Biomed. Signal Process. Control, vol. 68, Jul. 2021, Art. no. 102574, doi: 10.1016/j.bspc.2021.102574.
S. Dündar and I. Sahin, "Train re-scheduling with genetic algorithms and artificial neural networks for single-Track railways," Transp. Res. C, Emerg. Technol., vol. 27, pp. 1-15, Feb. 2013, doi: 10.1016/j.trc.2012.11.001.
C.Wen, W. Mou, P. Huang, and Z. Li, "A predictive model of train delays on a railway line," J. Forecasting, vol. 39, no. 3, pp. 470-488, Apr. 2020, doi: 10.1002/for.2639.
P. Huang, C. Wen, L. Fu, J. Lessan, C. Jiang, Q. Peng, and X. Xu, "Modeling train operation as sequences: A study of delay prediction with operation and weather data," Transp. Res. E, Logistics Transp. Rev., vol. 141, Sep. 2020, Art. no. 102022, doi: 10.1016/j.tre.2020. 102022.
N. Markovic, S. Milinkovic, K. S. Tikhonov, and P. Schonfeld, "Analyzing passenger train arrival delays with support vector regression," Transp. Res. C, Emerg. Technol., vol. 56, pp. 251-262, Jul. 2015, doi: 10.1016/j.trc.2015.04.004.
S. Suthaharan, Machine Learning Models and Algorithms for Big Data Classification, vol. 36. Boston, MA, USA: Springer, 2016, doi: 10.1007/978-1-4899-7641-3.
K. S. Kim, H. H. Choi, C. S. Moon, and C. W. Mun, "Comparison of Knearest neighbor, quadratic discriminant and linear discriminant analysis in classification of electromyogram signals based on the wrist-motion directions," Current Appl. Phys., vol. 11, no. 3, pp. 740-745, May 2011, doi: 10.1016/j.cap.2010.11.051.
G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T. Liu, "LightGBM: A highly efficient gradient boosting decision tree," in Proc. Adv. Neural Inf. Process. Syst., Dec. 2017, pp. 3147-3155.
I. K. Nti, A. F. Adekoya, and B. A.Weyori, "Acomprehensive evaluation of ensemble learning for stock-market prediction," J. Big Data, vol. 7, no. 1, p. 20, Dec. 2020, doi: 10.1186/s40537-020-00299-5.
M. Fayaz and D. Kim, "A prediction methodology of energy consumption based on deep extreme learning machine and comparative analysis in residential buildings," Electronics, vol. 7, no. 10, p. 222, Sep. 2018, doi: 10.3390/electronics7100222.
M. F. Gorman, "Statistical estimation of railroad congestion delay," Transp. Res. E, Logistics Transp. Rev., vol. 45, no. 3, pp. 446-456, May 2009, doi: 10.1016/j.tre.2008.08.004.
M. S. Devi, R. M. Mathew, and R. Suguna, "Regressor fitting of feature importance for customer segment prediction with ensembling schemes using machine learning," Int. J. Eng. Adv. Technol., vol. 8, no. 6, pp. 952-956, Aug. 2019, doi: 10.35940/ijeat.F8255. 088619.
J. Xu, A. Wang, N. Schmidt, M. Adams, and M. Hatzopoulou, "A gradient boost approach for predicting near-road ultrafine particle concentrations using detailed traffic characterization," Environ. Pollut., vol. 265, Oct. 2020, Art. no. 114777, doi: 10.1016/j.envpol.2020.114777.
I. Ivanoska, L. Pastorino, and M. Zanin, "Assessing identifiability in airport delay propagation roles through deep learning classification," IEEE Access, vol. 10, pp. 28520-28534, 2022, doi: 10.1109/ACCESS.2022.3158313.
T. Kuflik, E. Minkov, S. Nocera, S. Grant-Müller, A. Gal-Tzur, and I. Shoor, "Automating a framework to extract and analyse transport related social media content: The potential and the challenges," Transp. Res. C, Emerg. Technol., vol. 77, pp. 275-291, Apr. 2017, doi: 10.1016/j.trc.2017.02.003.
A. N. Richter and T. M. Khoshgoftaar, "Learning curve estimation with large imbalanced datasets," in Proc. 18th IEEE Int. Conf. Mach. Learn. Appl. (ICMLA), Dec. 2019, pp. 763-768, doi: 10.1109/ICMLA.2019.00135.
D. Husmeier, "Introduction to learning Bayesian networks from data," in Probabilistic Modeling in Bioinformatics and Medical Informatics, London, U.K.: Springer-Verlag, 2005, pp. 17-57, doi: 10.1007/1-84628-119-9-2.
S. Lundberg and S.-I. Lee, "A unified approach to interpreting model predictions," in Proc. 31st Int. Conf. Neural Inf. Process. Syst., Dec. 2017, pp. 4768-4777. [Online]. Available: https://papers.nips.cc/paper/7062-Aunified-Approach-To-interpreting-model-predictions
F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, A. Müller, J. Nothman, G. Louppe, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, "Scikit-learn: Machine learning in Python," J. Mach. Learn. Res., vol. 12, pp. 2825-2830, Oct. 2012.
M. Ali. (2020). PyCaret: An Open Source, Low-Code Machine Learning Library in Python. [Online]. Available: https://www.pycaret.org
C. Wen, P. Huang, Z. Li, J. Lessan, L. Fu, C. Jiang, and X. Xu, "Train dispatching management with data-driven approaches: A comprehensive reviewand appraisal," IEEE Access, vol. 7, pp. 114547-114571, 2019, doi: 10.1109/ACCESS.2019.2935106.
A. Okland and N. O. E. Olsson, "Punctuality development and delay explanation factors on Norwegian railways in the period 2005-2014," Public Transp., vol. 13, no. 1, pp. 127-161, Mar. 2021, doi: 10.1007/s12469-020-00236-y.
N. O. E. Olsson and H. Haugland, "Influencing factors on train punctuality-Results from some Norwegian studies," Transp. Policy, vol. 11, no. 4, pp. 387-397, Oct. 2004, doi: 10.1016/j.tranpol.2004.07.001.
R. B. K. van der Kooij, A. D. Landmark, A. A. Seim, and N. O. E. Olsson, "The effect of temporary speed restrictions, analyzed by using real train traffic data," Transp. Res. Proc., vol. 22, pp. 580-587, 2017, doi: 10.1016/j.trpro.2017.03.047.
