Future Rail – how machine learning is improving your journeys

Machine learning is one of the many ways we’re using innovative technology to run the railway more efficiently – and ultimately give you better journeys.

Automated Intelligent Video Review (AIVR) – developed by Bristol-based tech company One Big Circle – gathers a wide range of data from high-definition video around the railway.

A phone-sized device mounted to the front of any train takes footage of our more than 20,000 miles of track across Britain.

Close-up of a computer screen showing the AIVR technology, featuring footage of a viaduct and a map.

This AIVR-Go continually captures video and makes it instantly accessible Via 4G so we can easily monitor the environment around the railway.

It also applies machine learning – computer algorithms to find patterns in data to predict future outcomes – to understand the context of the environment.

The information it captures includes location data, hazards on or near the line, vegetation that may need maintaining and even the condition of the track and bridges, tunnels and viaducts.

Gathering this information via video means we can capture lots of vital and useful knowledge about the state of our infrastructure, easily and smartly.

It means we can keep our workers safer, with fewer people needing to go out to safety-critical areas like track. And we can maintain, develop and repair the railway with more efficient use of time and taxpayers’ money.

Ultimately, it helps us look after your railway better so we can give you better journeys and a more enjoyable trip by preventing the issues that cause delays or cancellations.

One Big Circle says on its website: “Rather than having to trawl through old data which may no longer be relevant, machine learning allows you to dip into a current map of assets and conditions. Being able to access current data which gives a snapshot of an event in real-time is incredibly valuable in safety-critical industries like rail.

A Network Rail employee in PPE fitting an AIVR-Go camera to the front of a train at a railway station.

“In One Big Circle’s case, machine learning accelerates the capability of what you can do with video by showing you events, anomalies and inconsistencies you may not instantly spot with the naked eye or be able to interpret and understand at speed.”


The company says the use of machine learning in the rail industry is growing, with “massive potential”.

The tech is revolutionising the way the industry carries out projects, helping contractors and passengers, too.

Using data to spot patterns and predict forecasts helps projects to speed up and rail service reliability to improve. 

Still from a film showing a split screen of a man assembling an AIVR-Go camera, some data on graphs and a woman sitting at a desk.

And efficiencies like this mean a safer and more resilient railway with less disruption to your journeys.

One Big Circle says: “For example, let’s say you were facing the issue of detecting potential failures on third rail. By using a thermal sensor the machine learning can uncover where the electrical fault is, based on spikes in temperature, so that it can be dealt with before it escalates into full failure.

“It might be that the component is overheating but not failed, so being able to pinpoint this quickly means teams can be sent out to respond to the exact piece of track before it results in lines that are out of action.”

Safer communities

Meanwhile, deploying machine learning across CCTV helps railway station staff spot unusual behaviour and suspicious objects in zones like restricted areas.

It automatically alerts operators if it detects unusual behaviour in that area so operators can determine whether it’s a cause for concern.

One Big Circle says: “It essentially arms station staff with the knowledge about what they’re tending to so they can deal with a situation in the most appropriate and prepared manner.”


One Big Circle can securely mount AIVR-Go in a strong casing developed by us at Network Rail. This casing fits by hand onto any tail lamp bracket at any station or depot. One Big Circle has reached agreements with all train operating companies to mount the tech to their trains.

AIVR-Go automatically activates on motion, detecting GPS location and mapping it to engineer’s line references, which describes what part of our network any given mileage of track is on.

AIVR-Go transmits the video data, location and other telemetry via 4G. It temporarily stores the data when connectivity is poor.

Learn more about AIVR here.

Read more:

Nine ways tech is improving the railway

How cutting-edge track technology is reducing delays for passengers

Rail Week: five times tech has changed the railway

International Women’s Day: Q and A with Kathryn Bishop – virtual reality

Research, development and technology

Rail innovation and development centres

Reliability boost through multi-million-pound investment

Liverpool Lime Street: taking upgrades to new dimensions