Artificial intelligence to help reduce train delays caused by 'leaves on the line'

Featured story
The Rail Safety and Standards Board is collaborating with the University of Sheffield to develop a tool using artificial intelligence to help predict low adhesion track conditions.

The new research project is investigating how more detailed information on local conditions can be used to tackle the seasonal challenge associated with ‘leaves on the line’.

Low adhesion track conditions are a serious safety and operational issue for the rail industry, costing around £350million each year. It not only causes delays affecting train performance but can also result in station overruns and signals being passed at danger. 

Temperature, humidity and the presence of leaf layers or other contaminants all have an impact on the level of adhesion between the train wheel and the rail. The project will use artificial intelligence to analyse data, and high-resolution video footage to deliver more accurate predictions about friction at the wheel-rail interface.

One of the project outputs will be an online tool, for users to enter data that will generate friction predictions for anywhere on the network, in time for Autumn 2023.

While people may think of leaves on the line as a joke, or just an excuse used when a train is delayed, the reality is that it's a very serious issue for the rail industry. Low adhesion causes significant safety risks and operational problems, costing millions of pounds to manage.

Our new research project will use artificial intelligence and data analysis to predict and identify where and when low adhesion is going to occur on the rail network. This will allow targeted action at these specific locations, to help manage the safety risks and reduce delays.

Paul Gray 11
Paul Gray, Professional Lead Engineering, RSSB

It is very exciting for the team at Sheffield and RSSB that our fundamental analysis of the causes of low adhesion as well as our extensive collection of data from track is now coming together to enable the development of the AI friction prediction tool that will help the railway industry with performance and safety issues around Autumn.

Roger Lewis, Professor of Mechanical Engineering, University of Sheffield

Notes to Editors

  1. The Rail Safety and Standards Board is the independent safety, standards and research body for Great Britain’s rail network. We help to make an evolving railway safer, more efficient and more sustainable.
  2. We work collaboratively with an evolving industry to ensure that innovative and sustainable technology is operated safely, efficiently and cost-effectively. We codify and share best practice, both in Britain and abroad. We are proudly impartial, and home to some of rail’s leading experts on technical matters. Guided by facts and analysis, we help to bridge knowledge gaps, optimise use of the latest technology and disseminate and systemise industry best practice.
  3. This project is part of ADHERE, the cross-industry adhesion research programme. The programme sets out to deliver research to achieve ‘adhesion conditions that are unaffected by and independent of the weather and climate’. The work will address industry’s gaps in knowledge with new insight that helps improve how we manage low adhesion. Further information can be found at: