AI just designed concrete that could reverse climate damage

Concrete is everywhere – holding up highways, homes, office towers, and schools. It’s tough, fire-resistant, and essential to modern infrastructure.

But it’s also a major problem. Concrete production is responsible for about 8 percent of global carbon dioxide emissions. On top of that, most modern concrete starts to crack and crumble after about 100 years.

Now imagine this: concrete that can trap CO₂, make itself stronger, and possibly last thousands of years.

That’s the idea behind a new AI-powered model created by scientists at the USC Viterbi School of Engineering. This tool simulates billions of atoms at once, offering a new way to design cleaner, longer-lasting materials – starting with concrete.

Tackling climate challenges with precision

The climate crisis isn’t slowing down. Droughts, heat waves, and wildfires continue to get worse.

After the January wildfires in Los Angeles, a group of USC researchers started thinking differently about concrete and carbon. What if the very material used to rebuild fire-damaged buildings could also help pull carbon out of the air?

That’s when their 20-year collaboration turned into a new project: Allegro-FM.

“You can just put the CO₂ inside the concrete, and then that makes a carbon-neutral concrete,” said Aiichiro Nakano, a USC Viterbi professor of computer science, physics and astronomy, and quantitative and computational biology.

Their research focuses on “CO₂ sequestration,” the process of capturing carbon dioxide and storing it – ideally within the concrete itself. This isn’t easy, but that’s where the AI model comes in.

Supercomputer tests cleaner concrete

Normally, testing new materials means expensive, time-consuming lab work. Allegro-FM changes that. It runs digital experiments with billions of atoms, all simulated in virtual environments.

This allows researchers to test different chemical recipes for concrete – searching for mixes that don’t just reduce carbon emissions but absorb CO₂ during production.

Better yet, the model runs fast and big. On the Aurora supercomputer at Argonne National Laboratory, Allegro-FM simulated over four billion atoms at 97.5 percent efficiency.

That’s about 1,000 times larger than older models could handle.

Designing concrete for climate and fire

It’s also flexible. Allegro-FM covers 89 different chemical elements and can be used for everything from cement chemistry to long-term carbon storage.

“Concrete is also a very complex material. It consists of many elements and different phases and interfaces,” said Ken-Ichi Nomura, a USC Viterbi professor of chemical engineering and materials science practice.

“Traditionally, we didn’t have a way to simulate phenomena involving concrete material. But now we can use this Allegro-FM to simulate mechanical properties [and] structural properties.”

In a fire-prone city like Los Angeles, where cutting emissions is just as urgent as fire resistance, that combination matters. Simulations show that Allegro-FM can model concrete that does both – stand up to extreme heat and offset its own carbon impact.

Smarter, longer-lasting concrete

Beyond the climate benefits, there’s another bonus to storing CO₂ in concrete – it may actually make it stronger.

“If you put in the CO₂, the so-called ‘carbonate layer,’ it becomes more robust,” Nakano said. That means concrete could potentially last far longer than the current 100-year standard.

In fact, the team is thinking about concrete that could rival the durability of ancient Roman structures, some of which have stood for over 2,000 years.

AI is changing how scientists think

Traditionally, simulating materials at the atomic level required heavy mathematics based on quantum mechanics. The process was slow and extremely technical. But machine learning is changing that.

“Now, because of this machine-learning AI breakthrough, instead of deriving all these quantum mechanics from scratch, researchers are taking [the] approach of generating a training set and then letting the machine learning model run,” Nomura said.

That shift lets the model handle more data and more complexity while using fewer resources. Allegro-FM can now predict how atoms interact with one another – a job that used to require countless hours of calculation.

The result? Faster simulations, broader material options, and huge efficiency gains. According to Nakano, the AI can achieve quantum mechanical accuracy with much, much smaller computing resources.

Next steps in the concrete revolution

“We will certainly continue this concrete study research, making more complex geometries and surfaces,” Nomura said.

The big picture is this: AI isn’t just helping us understand the world at the atomic level – it’s helping us rethink the materials we rely on every day.

And in this case, that could mean stronger buildings, cleaner air, and a future where concrete becomes part of the climate solution instead of the problem.

The full study was published in the journal The Journal of Physical Chemistry Letters.

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates. 

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–