Delayed trains predicted by AI after analysis of railway data
An AI has been fed with British railway data, allowing it to accurately predict delays on the train network.
Over the past 20 years, the number of passengers travelling on British train networks has almost doubled to 1.7 billion, with delays having a significant impact on people’s travel plans.
A team from the University of Illinois applied a 'Spatial-Temporal Graph Convolutional Network' model to predict delays within a portion of the British rail network where Didcot Parkway and London Paddington serve as gateway stations.
“Compared with other statistical models, this one outperforms them for forecasting delays up to 60 minutes in the future,” said researcher Huy Tran. “One challenge was that this data only captures the full trip of a train from start to finish. It doesn’t tell us where it was delayed along the way”.
The team’s new formulation approximates on which leg of the trip a delay occurs - data which the AI then combines with real-world data to predict behaviours.
Britain’s train network is typically less efficient than those of its European neighbours. According to European Commission figures from 2014, British trains are on time (within a five or ten-minute window, depending on the type of service) 90 per cent of the time, compared to 91 per cent in France and 93 per cent in Germany.
More recent UK-only figures from the 2016-17 period show that the punctuality rate slipped to around 87.7 per cent.
“A lot of times with AI models, we don’t really understand why the model says what it does. We just try to predict what the delay will be, but we don’t have any insight into why it was delayed or where,” Tran said. “One of the things we’re interested in is getting more explainability into these models, so we can better understand why it’s making the suggestion or predictions that it does.
“We’d also like to, at some point, close the loop and say: given this information, here’s how you might want to react to that delay.”
The UK’s rail sector has suffered since the beginning of coronavirus lockdowns, which saw the number of journeys fall by more than 400 million between April and June this year.
Sign up to the E&T News e-mail to get great stories like this delivered to your inbox every day.