New tool for building and repairing roads and bridges: artificial intelligence
In Pennsylvania, true 13 percent of bridges are classified as structurally deficient, engineers use artificial intelligence to create lighter concrete blocks for new construction. Another project uses AI to develop a highway wall that can absorb the noise of cars – and also some of the greenhouse gas emissions released by traffic.
At a time when federal allocation of billions of dollars to infrastructure projects would help with just a fraction of the cost needed to repair or replace the nation’s aging bridges, tunnels, buildings and roads, some engineers are looking to AI to become more resilient to help build projects for less money.
“These are structures, with the tools we have, that save materials, save costs, save everything,” said Amir Alavi, professor of engineering at the University of Pittsburgh and member of the consortium developing the two AI projects in collaboration with the Pennsylvania Department of Transportation and the Pennsylvania Turnpike Commission.
The potential is enormous. At least the production of cement alone makes up for that 8 percent of the world’s CO2 emissions, and 30 billion tons of concrete are used worldwide every year, so more efficient concrete production would have huge environmental consequences.
And AI – essentially machines that can synthesize information and find patterns and conclusions just as the human mind can – could have the ability to speed up and improve tasks like engineering challenges to an incalculable degree. It works by analyzing massive amounts of data and providing options that give people better information, models and alternatives for making decisions.
It has the potential to be both more cost-effective (one machine does the work of dozens of engineers) and more creative in coming up with new approaches to familiar tasks.
But experts warn against embracing the technology too quickly because it is largely unregulated and its results remain largely unproven. In particular, some are concerned about AI’s ability to design infrastructure in a process that involves multiple regulators and participants over a long period of time. Others worry that AI’s ability to instantly draw from the entire internet could lead to flawed data that produces unreliable results.
The challenges facing America’s infrastructure have become all the more apparent in recent years: Texas’ power grid failed during devastating ice storms in 2021 and continues to struggle with the state’s needs; communities across the country, from Flint, Mich., to Jackson, Miss., have struggled with failing water supplies; and more than 42,000 bridges are in poor condition nationwide.
A vast majority of the country’s roads and bridges were built decades ago, and as a result, “infrastructure problems are significant in many dimensions,” said Abdollah Shafieezadeh, a professor of civil, environmental and geodetic engineering at Ohio State University.
The collaborations in Pennsylvania reflect AI’s potential to address some of these problems.
In the bridge project, engineers use AI technology to develop new shapes for concrete blocks that use 20 percent less material while maintaining durability. The Pennsylvania Department of Transportation will use the blocks to build a bridge; there are more than 12,000 in the state that need repairs, This was reported by the American Road & Transportation Builders Association.
Engineers in Pittsburgh are also working with the Pennsylvania Turnpike Commission to design a more efficient sound-absorbing wall that will also capture some of the nitrous oxide emitted by vehicles. They plan to build it in an area disproportionately affected by highway noise. The designs save approximately 30 percent on material costs.
These new projects have not been field tested, but they have been successful in the laboratory setting, said Dr. Alavi.
In addition to AI’s speed in developing new designs, one of the greatest assets in civil engineering is its potential to prevent and detect damage.
Rather than investing large sums of money in repair projects, engineers and transportation agencies could identify problems early, experts say, such as a crack developing in a bridge before the structure itself collapsed.
This technology is capable of providing an analysis of what is happening in real time during incidents such as the bridge collapse on Interstate 95 in Philadelphia this summer or the fire that closed part of Interstate 10 in Los Angeles this month, and could be developed to implement automated emergency response measures, says Seyede Fatemeh Ghoreishi, professor of engineering and computer science at Northeastern University.
But as in many areas, there are increasing conversations – and concerns – about the relationship between AI, human work and physical safety.
While AI has proven useful in many applications, technology leaders have testified before Congress and pushed for regulations. And last month, President Biden issued a statement executive order for a range of AI standards, including security, privacy and employee support.
Experts are also concerned about the spread of disinformation from AI systems. AI works by integrating already available data, so if that data is incorrect or biased, the AI will draw incorrect conclusions.
“It’s a really great tool, but it’s really a tool that you should only use for an initial version at this point,” says Norma Jean Mattei, past president of the American Society of Civil Engineers.
Dr. Mattei, who has worked in engineering education and ethics throughout her career, added: “Once this develops, I’m confident we’ll get to a point where you’re less likely to encounter problems gets. We’re not there yet.”
Also worrying is the lack of standards for AI. For example, the Occupational Safety and Health Administration has no standards for the robotics industry. There is growing concern about car accidents involving autonomous vehicles, but for now automakers are not required to adhere to federal regulations for software safety testing.
Lola Ben-Alon, assistant professor of architectural technology at Columbia University, is also cautious about using AI. She emphasized the need to take the time to understand how to use it, but she said she “wasn’t condemning” it and that it had many great possibilities.
Few doubt that AI exists in infrastructure projects and elsewhere as a tool for people to use, not as a replacement.
“There is still a strong and important place for human existence and experience” in the field of engineering, said Dr. Ben-Alon.
The uncertainty surrounding AI could create more problems in financing projects like the one in Pittsburgh. But a spokesperson for the Pennsylvania Department of Transportation said the agency was excited to see how the concrete Dr. Alavi and his team design the field of bridge construction could expand.
Dr. Alavi said his work throughout his career had shown him how serious the potential risks of AI are.
But he is confident in the safety of the designs he and his team create, and he is excited about the future of the technology.
“After 10, 12 years, this is going to change our lives,” said Dr. Alavi.