Machine learning-assisted macro simulation for yard arrival prediction
Minbashi, Niloofar ; Sipilä, Hans ; Palmqvist, Carl William LU
; Bohlin, Markus
and Kordnejad, Behzad
(2023)
In Journal of Rail Transport Planning and Management
25.
- Abstract
Increasing the modal share of the single wagonload transport in Europe requires improving the reliability and predictability of freight trains running between the yards. In this paper, we propose a novel machine learning-assisted macro simulation framework to increase the predictability of yard departures and arrivals. Machine learning is applied through a random forest algorithm to implement a yard departure prediction model. Our yard departure prediction approach is less complex compared to previous yard simulation approaches, and provides an accuracy level of 92% in predictions. Then, departure predictions assist a macro simulation network model (PROTON) to predict arrivals to the succeeding yards. We tested this framework using data... (More)
Increasing the modal share of the single wagonload transport in Europe requires improving the reliability and predictability of freight trains running between the yards. In this paper, we propose a novel machine learning-assisted macro simulation framework to increase the predictability of yard departures and arrivals. Machine learning is applied through a random forest algorithm to implement a yard departure prediction model. Our yard departure prediction approach is less complex compared to previous yard simulation approaches, and provides an accuracy level of 92% in predictions. Then, departure predictions assist a macro simulation network model (PROTON) to predict arrivals to the succeeding yards. We tested this framework using data from a stretch between two main yards in Sweden; our experiments show that the current framework performs better than the timetable and a basic machine learning arrival prediction model by R2 of 0.48 and a mean absolute error of 35 minutes. Our current results indicate that combination of approaches, including yard and network interactions, can yield competitive results for complex yard arrival time prediction tasks which can assist yard operators and infrastructure managers in yard re-planning processes and yard-network coordination respectively.
(Less)
- author
- Minbashi, Niloofar
; Sipilä, Hans
; Palmqvist, Carl William
LU
; Bohlin, Markus
and Kordnejad, Behzad
- organization
- publishing date
- 2023
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Delay prediction, Machine learning, Macroscopic simulation, Rail traffic, Yards
- in
- Journal of Rail Transport Planning and Management
- volume
- 25
- article number
- 100368
- publisher
- Elsevier
- external identifiers
-
- scopus:85145972631
- ISSN
- 2210-9706
- DOI
- 10.1016/j.jrtpm.2022.100368
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2022 The Authors
- id
- 56853470-fd57-4735-bf60-d2a840f1a522
- date added to LUP
- 2023-01-22 21:17:24
- date last changed
- 2023-11-17 18:06:38
@article{56853470-fd57-4735-bf60-d2a840f1a522,
abstract = {{<p>Increasing the modal share of the single wagonload transport in Europe requires improving the reliability and predictability of freight trains running between the yards. In this paper, we propose a novel machine learning-assisted macro simulation framework to increase the predictability of yard departures and arrivals. Machine learning is applied through a random forest algorithm to implement a yard departure prediction model. Our yard departure prediction approach is less complex compared to previous yard simulation approaches, and provides an accuracy level of 92% in predictions. Then, departure predictions assist a macro simulation network model (PROTON) to predict arrivals to the succeeding yards. We tested this framework using data from a stretch between two main yards in Sweden; our experiments show that the current framework performs better than the timetable and a basic machine learning arrival prediction model by R<sup>2</sup> of 0.48 and a mean absolute error of 35 minutes. Our current results indicate that combination of approaches, including yard and network interactions, can yield competitive results for complex yard arrival time prediction tasks which can assist yard operators and infrastructure managers in yard re-planning processes and yard-network coordination respectively.</p>}},
author = {{Minbashi, Niloofar and Sipilä, Hans and Palmqvist, Carl William and Bohlin, Markus and Kordnejad, Behzad}},
issn = {{2210-9706}},
keywords = {{Delay prediction; Machine learning; Macroscopic simulation; Rail traffic; Yards}},
language = {{eng}},
publisher = {{Elsevier}},
series = {{Journal of Rail Transport Planning and Management}},
title = {{Machine learning-assisted macro simulation for yard arrival prediction}},
url = {{http://dx.doi.org/10.1016/j.jrtpm.2022.100368}},
doi = {{10.1016/j.jrtpm.2022.100368}},
volume = {{25}},
year = {{2023}},
}