AI is now being used to predict traffic jams in Melbourne – and prevent them

A pioneering project using artificial intelligence (AI) to predict traffic congestion up to three hours before it’s going to happen, and could change the way authorities control traffic in real time, has launched in Melbourne. 

The University of Melbourne’s Australian Integrated Multimodal EcoSystem (AIMES) has partnered with PeakHour Urban Technologies, the Victorian Department of Transport, and Telstra to create a large-scale AI application that optimises city traffic flows.

While the initial use with focus on the state’s capital, the project has global potential.

AIMES director Professor Majid Sarvi said the application can also optimise traffic signals for on-road vehicles, freight, and public transport such as buses and trams.

“The application observes the nature of traffic and figures out complex traffic patterns across the network through machine learning built into the technology,” he said.

“If we can upscale the application to provide more accurate prediction with machine learning and real-time data, it will soon be possible to substantially reduce delays in hotspots across Melbourne and many locations across the globe.”

PeakHour Urban Technologies founding CEO Omid Ejtemai said pioneering AI in forecasting real-time traffic lies at the heart of this effort.

“We are using a multidisciplinary approach, combining deep knowledge of mobility with vast amounts of real-time data analytics to predict and optimise traffic in large cities,” he said.

The Victorian Department of Transport provided traffic data and insights to build the application. Victorian Minister for Transport Ben Carroll said managing a complex transport network presents many real-time challenges.

“Not only does this world first technology help Victorians navigate congestion by predicting traffic patterns hours in advance, but it paves the way to the future of connected and autonomous vehicles,” he said.