ASCE Civil Engineering Magazine Features Pioneering CEE Research on Scanning At-risk Bridges

Content

Simos Gerasimidis and Chengbo Ai

The 2021 Report Card for America’s Infrastructure, released by the American Society of Engineers (ASCE), found that more than 46,000 of the country’s 617,000 bridges are structurally deficient due to corrosion. Many of these structures are waiting for current state-of-the-art inspections, which are often time-consuming, imprecise, and inefficient, before being upgraded. In answer to this critical backlog of at-risk bridges, a team of researchers from the UMass Amherst Civil and Environmental Engineering (CEE) Department and four European institutions has been developing a game-changing, 3D-laser-scanning, bridge-inspection system that was featured prominently in a long article in ASCE’s Civil Engineering Magazine. See https://www.asce.org/publications-and-news/civil-engineering-source/article/2025/03/04/why-3d-scanning-could-be-wave-of-future-for-bridge-inspection.

CEE Associate Professor Simos Gerasimidis (Personal Academic Webpage), CEE Associate Professor Chengbo Ai (Personal Academic Website), and their Ph.D. student Aidan Provost have been working with an international team of researchers, including Georgios Tzortzinis from the Institute of Lightweight Engineering and Polymer Technology at Technische Universität Dresden in Germany, to develop an innovative framework that combines 3D-laser scanning and convolutional neural networks for precise evaluation of corroded steel bridges. 

Tzortzinis was the lead author of the team’s recent “Editor’s Choice” paper in Communications Engineering (Structural integrity of aging steel bridges by 3D laser scanning and convolutional neural networks | Communications Engineering).

Meanwhile, countless steel bridges are slowly deteriorating, due in large part to corrosion, which is insidiously at work weakening bridge load capacities over time. 

“Currently,” as the team’s Communications Engineering paper explained, “inspection practices rely heavily on subjective visual assessments and low-precision tools, resulting in labor-intensive processes that often lack consistency and accuracy. These traditional methods are further constrained by accessibility issues, time-intensive data collection, and an inability to provide detailed evaluations of corrosion patterns and their impacts on structural capacity.”

According to the Communications Engineering editorial staff, “The study integrates advanced point-cloud data from 3D-laser scanning with convolutional neural networks trained on over 1,400 corrosion scenarios, achieving remarkable classification and regression accuracy with errors as low as 2.0 percent and 3.3 percent, respectively...Validated on eight decommissioned girders and applied to an in-service bridge, the framework demonstrates transformative potential in bridge maintenance.” 

As the Communications Engineering paper’s seven authors concluded, “This framework promises significant advancements in assessing aging bridge infrastructure with higher accuracy and efficiency compared to analytical or semi-analytical approaches.”

Ai told ASCE Civil Engineering Magazine that he believes this innovative technology will become the norm for bridge inspection in the coming years. He added that, compared to ultrasound scanning and other state-of-the-art bridge-inspection methods, this groundbreaking 3D-laser-scanning technology documents the bridge inspection much more accurately and comprehensively for such features as corrosion patterns, detailed evaluations, and future references. 

As Gerasimidis said in the ASCE magazine article, 3D scanners are not intended to replace bridge inspectors or load-capacity engineers – only to provide relief to a backlog that he described as “massive.” Massachusetts alone has thousands of at-risk bridges. 

According to Gerasimidis in the ASCE magazine feature, “Whenever I talk about this, I encourage the person I’m talking to: ‘When you go home, try to look at the bridges that you go under. I bet half of these have corrosion. They’re everywhere.’” (April 2025)