Near-term train delay prediction in the Dutch railways network

Li, Zhongcan; Wen, Chao; Hu, Rui; Xu, Chuanlin; Huang, Ping; Xi, Jiang

doi:10.1080/23248378.2020.1843194

Cited by 33 publications

(15 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, some approaches use section-specific catch-up potential or buffer times, minimal headway times, planned connections or waiting time policies as an explicit source of information (e.g., Berger et al, 2011b;Gao et al, 2020;Goverde, 2010). A few approaches consider the schedules of rolling stock and crew as input data to predict train delays (e.g., Barbour et al, 2018;Li et al, 2020).…”

Section: Input Datamentioning

confidence: 99%

A review of train delay prediction approaches

Spanninger

Trivella

Büchel

et al. 2022

Journal of Rail Transport Planning & Management

View full text Add to dashboard Cite

Section: Input Datamentioning

confidence: 99%

A review of train delay prediction approaches

Spanninger

Trivella

Büchel

et al. 2022

Journal of Rail Transport Planning & Management

View full text Add to dashboard Cite

“…The visibility at Pearson International Airport, classified as poor (if less than 1 km) or good (otherwise). The initial delay, classified into ranges of [0, 5), [5,15), [15,30), and ½30; 'Þ minutes.…”

Section: Historical Incident Recommendationmentioning

confidence: 99%

“…Traditionally, studies investigating delay propagation in railway networks use methods such as maximum-likelihood estimation ( 3 ) or max-plus algebra ( 4 , 5 ). More recently, machine learning methods such as fuzzy Petri nets ( 6 ), support vector regression ( 7 , 8 ), Bayesian networks ( 9 – 11 ), neural networks ( 12 ), long short-term models ( 13 , 14 ), and random forests ( 15 ) have provided promising results, because of their ability to detect patterns across the many factors that may influence delays on the railway.…”

mentioning

confidence: 99%

“…Studies that focus specifically on incident delay prediction ( 11 , 12 , 15 , 16 ) are generally concerned with determining system response and recovery times, not supplementing existing expertise with context from historical data. Studies that focus on the propagation of delays throughout the network ( 5 , 10 , 17 ) tend to focus on determining weak points and the prioritization of potential improvements, whereas Zilko et al provided dispatchers with predictive information to support their response to an incident as it unfolds ( 11 ).…”

mentioning

confidence: 99%

See 1 more Smart Citation

Using Delay Logs and Machine Learning to Support Passenger Railway Operations

Klumpenhouwer

Shalaby

2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Passenger railways face reliability challenges resulting from shared track with other trains, limited infrastructure capacity, and rolling stock and trackway that is subject to major failures during service. Dispatchers may have limited contextual information when responding to an emerging delay, and often rely on their own experience to manage an incident. This study leverages various aspects of delay logs—a common set of data collected during railway operations—to arm dispatchers with an understanding of delays, provide contextual information about previous delays that are similar to an emerging event, and make predictions about the size of a delay based on emerging information. Using graph theory, short-text topic modeling, cosine similarity, and machine learning regression models, we demonstrate that agencies can leverage this single data source for insight and operational support. To showcase the potential insights gained by these methods, we apply them to delay log data from the GO Rail network in the Greater Golden Horseshoe area of Ontario, Canada. We find that elastic net and random forest regression models outperform naive models that may be tacitly used in practice today.

show abstract

“…However, the railway operations would inevitably encounter disturbances, and the punctuation of the railway system could be determined by various factors, including the severe weather conditions, unexpected mechanical failure, drivers' and travelers' behavior, and temporary speed restrictions (Z. Li et al, 2021;Nabian et al, 2019;Olsson and Haugland, 2004). As shown in (Harris et al, 2013), the delay variations in Norway by different railway lines are significant, with the best-performing route achieving 94.4% and the worst routes achieving only near 80%, against the target of 90%.…”

Section: Introductionmentioning

confidence: 99%

A Novel Markov Model for Near-Term Railway Delay Prediction

Xu¹,

Wang²,

Gao³

et al. 2022

Preprint

View full text Add to dashboard Cite

Predicting the near-future delay with accuracy for trains is momentous for railway operations and passengers' traveling experience. This work aims to design prediction models for train delays based on Netherlands Railway data. We first develop a chi-square test to show that the delay evolution over stations follows a first-order Markov chain. We then propose a delay prediction model based on non-homogeneous Markov chains. To deal with the sparsity of the transition matrices of the Markov chains, we propose a novel matrix recovery approach that relies on Gaussian kernel density estimation. Our numerical tests show that this recovery

show abstract

Near-term train delay prediction in the Dutch railways network

Cited by 33 publications

References 30 publications

A review of train delay prediction approaches

A review of train delay prediction approaches

Using Delay Logs and Machine Learning to Support Passenger Railway Operations

A Novel Markov Model for Near-Term Railway Delay Prediction

Contact Info

Product

Resources

About