US government agency National Science Foundation (NSF) has awarded a federal grant of $446,000 for a new collaborative engineering project undertaken by the Pennsylvania State University (Penn State) on traffic congestion.

The new study, dealing with ‘Statistical Learning for Dynamic Traffic Assignments (DTA)’, aims to enable NSF to regulate travelling in heavily congested major metropolitan areas, as well as allow the drivers to make more informed travel decisions.

Penn State Harold and Inge Marcus Department of Industrial and Manufacturing Engineering Chaired professor Terry Friesz will be the principal investigator of the two-year study.

Friesz explained: “This research grant aims to make the numerical computation of departure rates and route choice substantially faster than what has been possible in the past by exploiting the notion of machine learning to develop statistical models of a spectrum of traffic models.

“This research grant aims to make the numerical computation of departure rates and route choice substantially faster than what has been possible in the past.”

“This idea of making a model of a model, also known as metamodelling, has been used successfully in other disciplines, and has the potential to make possible rapid and accurate computation of traffic flows a few seconds, minutes or hours ahead of time, allowing rerouting or diversion to complete other tasks that would not otherwise be attempted.”

The models are also expected to help in rapidly modifying urban supply chains of possible traffic congestion.

According to a Texas Transportation Institute report published in 2015, an average urban commuter in the US spends nearly 42 hours annually stuck in traffic jams.

It also estimated that highway congestion in the country costs $160bn a year, resulting in lost productivity, fuel wastage and additional wear and tear on vehicles.