A Freight Mode Choice to Transport Oil Products Using an Artificial Neural Network Model
DOI:
https://doi.org/10.31272/jeasd.2137Keywords:
Complete separation in data, Doura refinery, Freight transportation, Geographical positioning system, Iraqi trains, Iraqi trucksAbstract
Transporting oil products by truck has many issues, including increased accident risk, adverse environmental effects, and increased congestion in traffic. This study aims to compare trucks and trains for transporting fuel oil between intercity locations and to develop freight mode-choice models using an artificial neural network and statistical software. Freight trips collected in this study are (277) collected by a tracking device, questionnaires, and personal interviews. The data included the delivery time, average speed, quantity transported per trip, and transportation cost. According to the findings, the average speed of trucks and trains is (48.79) km/h and (24.13) km/h, respectively. This indicates that the average speed of a truck is nearly twice that of a train. Trucks and trains have average delivery times of (12.40) h and (25.92) h, respectively. This indicates that the average delivery time for a truck is half that of a train. The quantity transported each trip is (993.16) tons/trip for trains and (30.47) tons/trip for trucks. Train transportation is approximately 33 times as costly per trip as truck transportation. Transportation by train is a cheaper option than transportation by truck. Establishing an effective schedule can reduce delays at freight train intersections and during railway maintenance, potentially reducing delivery time by approximately 20 hours.
References
R. Soesilo, "Supply chain performance improvement strategy in the packaging industry," Int. J. Bus. Appl. Econ., vol. 2, no. 2, pp. 245–256, 2023. https://doi.org/10.55927/ijbae.v2i2.2710.
B. Jourquin, "Mode choice in strategic freight transportation models: A constrained Box–Cox meta-heuristic for multivariate utility functions," Transportmetrica A: Transp. Sci., vol. 18, no. 3, pp. 1325–1345, 2022. https://doi.org/10.1080/23249935.2021.1937375.
V. Pajić, M. Andrejić, and M. Kilibarda, "Sustainable transportation mode selection from the freight forwarder's perspective in trading with Western EU countries," Sustain. Futures, vol. 4, p. 100090, 2022. https://doi.org/10.1016/j.sftr.2022.100090.
L. Kalahasthi, J. Holguín-Veras, and W. F. Yushimito, "A freight origin-destination synthesis model with mode choice," Transp. Res. Part E: Logist. Transp. Rev., vol. 157, p. 102595, 2022. https://doi.org/10.1016/j.tre.2021.102595.
W. Abdelwahab and T. Sayed, "Freight mode choice models using artificial neural networks," Civ. Eng. Syst., vol. 16, no. 4, pp. 267–286, 1999. https://doi.org/10.1080/02630259908970267.
G. Shen and J. Wang, "A freight mode choice analysis using a binary logit model and GIS: The case of cereal grains transportation in the United States," J. Transp. Technol., vol. 2, no. 2, pp. 175–188, 2012. https://doi.org/10.4236/jtts.2012.22019.
Y. Wang, C. Ding, C. Liu, and B. Xie, "An analysis of Interstate freight mode choice between truck and rail: A case study of Maryland, United States," Procedia - Soc. Behav. Sci., vol. 96, pp. 1239–1249, 2013. https://doi.org/10.1016/j.sbspro.2013.08.141.
A. F. Jensen et al., "A disaggregate freight transport chain choice model for Europe," Transp. Res. Part E: Logist. Transp. Rev., vol. 121, pp. 43–62, 2019. https://doi.org/10.1016/j.tre.2018.10.004.
D. Islam, "Barriers to and enablers for European rail freight transport for integrated door-to-door logistics service. Part 2: Enablers for multimodal rail freight transport," Transp. Probl., vol. 9, no. 4, pp. 5–13, 2014.
N. Keya, S. Anowar, and N. Eluru, "Joint model of freight mode choice and shipment size: A copula-based random regret minimization framework," Transp. Res. Part E: Logist. Transp. Rev., vol. 125, pp. 97–115, 2019. https://doi.org/10.1016/j.tre.2019.03.007.
Midland Refineries Company, 2023. https://mrc.oil.gov.iq/
U.S. Energy Information Administration, 2023. https://www.eia.gov/
BP Energy Outlook, Statistical Review of World Energy, 2021, vol. 70, p. 16.
Nations Online Project, "Map of Iraq and surrounding countries with international borders, the national capital Baghdad, governorate capitals, major cities, main roads, railroads, and major airports," 2023.
L. McMillan and L. Varga, "A review of the use of artificial intelligence methods in infrastructure systems," Eng. Appl. Artif. Intell., vol. 116, p. 105472, 2022. https://doi.org/10.1016/j.engappai.2022.105472.
P. D. Allison, "Convergence failures in logistic regression," in SAS Global Forum, 2008, vol. 360, no. 1, pp. 1–11.
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. London, UK: MIT Press, vol. 19, 2016. https://doi.org/10.1007/s10710-017-9314-z.
A. Pijoan, O. Kamara-Esteban, A. Alonso-Vicario, and C. E. Borges, "Transport choice modeling for the evaluation of new transport policies," Sustainability, vol. 10, no. 4, p. 1230, 2018. https://doi.org/10.3390/su10041230.
A. Saxena and P. Pandya, "Assessment of human capacity based on conjugate gradient technique using artificial neural network," in Proc. Int. Conf. Artif. Intell. Comput. Sci. ICT (AICS 2013), Langkawi, Malaysia, 2013.
V. Aryadoust and C. C. Goh, "Predicting listening item difficulty with language complexity measures: A comparative data mining study," CaMLA Working Papers, 2014.
Downloads
Key Dates
Received
Revised
Accepted
Published Online First
Published
Issue
Section
License
Copyright (c) 2026 Hussein M. Noor, Noor M. Asmael (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
