AI helps size up potholes and road durability

Researchers at the University of Mississippi have developed AI algorithms to predict the durability of road surfaces and likelihood of potholes developing.

State and local governments spent more than $206bn on maintaining the USA's roads in 2021
State and local governments spent more than $206bn on maintaining the USA's roads in 2021 - AdobeStock

The study, published in the International Journal of Pavement Engineering, tested different algorithms’ abilities to predict how well asphalt pavements with reclaimed materials could withstand moisture. When water seeps into asphalt, it can break the bonds that hold the materials together. In its weakened state, the asphalt is more likely to crack or otherwise fail, according to the researchers.    

MORE ON AI

“We focused on moisture damage, which is one of the most critical issues in asphalt pavements, particularly for wet and cold regions, because it results in a variety of distresses like stripping, potholes and cracking,” said Afshin Abolfazl Afshin, a Mississippi doctoral student in civil engineering. “We evaluated the effectiveness of four different artificial intelligence algorithms in predicting moisture damage in asphalt mixtures containing (reclaimed asphalt pavement) materials. 

“What we found was that these algorithms are able to effectively predict moisture damage in asphalt mixtures with high accuracy. Based on these results, we can optimize material selection and predict failure probability in the pavement’s life cycle.”  

State and local governments spent more than $206bn on maintaining the nation’s roads in 2021, and the Department of Transportation in 2023 reported nearly $1tn in backlog repairs and maintenance needed for roads and bridges. Optimising asphalt mixtures could reduce maintenance costs and extend the lifespan of these roads. 

Determining the best mixture of reclaimed asphalt pavement and other materials that could withstand wet and cold weather conditions without artificial intelligence would be an incredibly time-consuming and cost-intensive process, said Ali Behnood, an assistant professor of civil engineering at the University of Mississippi.

“The goal of our team in the NextGen Infrastructure Lab is to move towards the next generation of sustainable and resilient infrastructure,” said Behnood, who has dedicated more than 10 years to this field of study.

“We’re trying to optimise the use of recycled materials, industrial by-products, renewable resources, and alternative sustainable materials in construction while reducing not only physical cost, but labour costs, energy costs, environmental impact costs, and lifecycle maintenance expense as well.”