Traffic in Istanbul, Turkey. Credit: Omar Ramadan via Pexels.
In welcome news for commuters, researchers have developed a forecasting algorithm which could help city planners improve traffic congestion.
The new ‘data-driven macroscopic mobility model’ (D3M), presented in Chaos: An Interdisciplinary Journal of Nonlinear Science, has faster simulation speeds and easier data requirements than existing models.
“Imagine a system that doesn’t just react to traffic locally, but simulates how congestion can spread in complex, often unexpected ways across an entire city,” says co-author Deniz Eroğlu from Kadir Has University (KHAS), Turkey.
“A jam in one part of the network might trigger bottlenecks kilometres away – not because of local crowding, but due to the ripple effects of shifting flows.
“Our model captures these dynamics, offering system-level foresight instead of piecemeal reaction.”
Existing traffic flow algorithms often require detailed trip information and determine how vehicles move through intersections using inflexible rules.
“Rather than using fixed equations for flow dynamics, we calibrate the model parameters directly from real-world traffic data,” says co-author Toprak Firat also from KHAS.
D3M instead relies on data which are routinely collected by city planners, such as level of road congestion.
“This allows D3M to adapt its behaviour to the observed conditions in each city, making it more flexible and realistic than models with hard-coded assumptions,” says Firat.
They found D3M performed more accurately, and up to 3 times faster, than a conventional model in synthetic benchmark tests.
It could also accurately represent the diverse traffic conditions of Istanbul, London, UK and New York City, USA in tests using real-world data.
“The key breakthrough is that cities can now run sophisticated traffic simulations without needing expensive data collection,” says Eroğlu.
“Urban planners could test ‘what-if’ scenarios – like temporary closures due to accidents or maintenance – and see the predicted traffic impact before spending millions on construction.”
The researchers now plan to test the model in the real world, with the goal of bringing it to real cities soon.
