Data-driven train delay prediction

In Sweden, extensive use and the inherent heterogeneity of train traffic have significantly increased the sensitivity of the train system so that the delay of one train can easily propagate to others. Repeated experiences with train delays can lead passengers to perceive that railway transportation is unreliable. Despite being considered a green mode of transport, this environmental benefit truly comes into effect when passenger volumes are sufficiently high. Therefore, minimising train delays becomes crucial to promote a modal shift from private vehicles to railways. The advent of advanced technologies facilitating the collection and storage of extensive train operation data has paved the way for addressing train delay issues from a data-driven perspective, thus leading to a predominant focus on train delay prediction research. To develop theoretical and practical knowledge for the continuous advancement of decision support tools, this thesis aims to explore and understand data-driven train delay prediction. The thesis is grounded in the findings of six papers.

• Record URL:
  • https://lup.lub.lu.se/record/913e4821-55bf-49c5-ba29-e2877df4fa1a
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9789180399715
• Authors:
  • Tiong, Kah Yong
• Publication Date: 2024

Language

• English

Media Info

• Pagination: 115p
• Serial:
  • Bulletin / Lund University
  • Issue Number: 333
  • Publisher: Lund University. Department of Technology and Society. Transport and Roads, Sweden
  • ISSN: 1653-1930

Subject/Index Terms

• TRT Terms: Calculation; Forecasting; Railroad traffic; Railroad trains; Regression analysis; Theses; Traffic delays
• ITRD Terms: 6464: Calculation; 9010: Delay; 132: Forecast; 771: Rail traffic; 6588: Regression analysis; 8597: Thesis; 1268: Train
• Subject Areas: Railroads; I71: Traffic Theory;

Filing Info

• Accession Number: 01942747
• Record Type: Publication
• Source Agency: Swedish National Road and Transport Research Institute (VTI)
• ISBN: 9789180399715
• Files: ITRD, VTI
• Created Date: Jan 17 2025 3:17PM