ČȵăşÚÁĎ

Skip to Content
View site list

Profile

Pre-Bid Projects

Pre-Bid Projects

Click here to see Canada's most comprehensive listing of projects in conceptual and planning stages

Technology

AI is changing concrete formulations for the better

John Bleasby
AI is changing concrete formulations for the better

The ongoing search for concrete mixes that cure faster and harder while reducing carbons is complex and has research teams faced with hundreds of variables to consider. Teams at the Massachusetts Institute of Technology (MIT) and at technology giant Meta have each been using AI to help reach some practical conclusions.

“There is so much data out there on potential materials — hundreds of thousands of pages of scientific literature,” postdoc civil and environmental engineering student Soroush Mahjoubi. “Sorting through them would have taken many lifetimes of work, by which time more materials would have been discovered. We realized that AI was the key to moving forward.”

The MIT team built a machine-learning framework based on Large Language Models that evaluated and ranked candidate materials based on their physical and chemical properties that might contribute to successful alternative cements.

Ancient Roman concrete has long been regarded as a Holy Grail of sorts. Mahjoubi and his team noted that ceramics used in those mixes contributed waterproofing characteristics that has contributed to the longevity of structures still standing today.

 

MIT postdoc civil and environmental engineering student Soroush Mahjoubi led the Institute’s research into AI-developed alternate concrete formulations.
MIT/ANDREW LAURENT — MIT postdoc civil and environmental engineering student Soroush Mahjoubi led the Institute’s research into AI-developed alternate concrete formulations.

 

They also investigated the possible “high reactivity” of today’s tiles, bricks and pottery, that being their chemical reactions within a concrete mix. These could enhance the properties of concrete. The potential of reusing such everyday materials, and even industrial materials like mine tailings, points to the development of concrete mixes than could contribute to a circular building economy.

Professor Elsa Olivetti, a senior author on the work and member of the MIT Department of Materials Science and Engineering, acknowledges that AI helped make the team’s detailed research possible. “AI tools have gotten this research far in a short time, and we are excited to see how the latest developments in Large Language Models enable the next steps.”

Meanwhile, tech giant Meta plans to build several new, high-powered data centres across the United States. Facilities such as these will require huge amounts of electricity to operate, initiating concerns surrounding the carbon emissions associated with their power consumption and the generation methods that might be used.

Addressing environmental questions surrounding their new data centers, Meta has made a public commitment to build their facilities in the most sustainable manner possible. A large part of this involves using carbon-reduced concrete.

“Modern constructions, including data centres, require concrete that is optimized for sustainability, curing speed, workability, and finishability as well,” Meta explains. “Compared to traditional concrete, current formulas for low carbon concrete face several challenges: slower curing speeds, issues with surface quality, and complications in supply chains when novel materials are involved.”

 

Meta’s AI-developed low carbon concrete is poured at its new data centre in Rosemount, MN.
META — Meta’s AI-developed low carbon concrete is poured at its new data centre in Rosemount, MN.

 

Innovation in concrete formulations is difficult and slow. Developing the correct mix of concrete that meets corporate sustainability goals is highly complex. Meta collaborated with Amrize, a North American spin-off of Holcim, and the Grainger College of Engineering at the University of Illinois Urbana-Champaign. Together, they developed leveraging to accelerate the discovery of new concrete mixtures that meet traditional requirements alongside newer sustainability needs.

Meta successfully deployed a concrete mix that was optimized with their AI tool for the construction of an $800 million, 715,000 square foot data centre in Rosemount, Minnesota. The numbers achieved are impressive.

The concrete mix will reportedly achieve a 35 per cent reduction in the data centre’s carbon footprint, while also demonstrating a 9.5 per cent reduction in shrinkage. It reached 4,000 PSI strength 43 per cent faster than the original slab mix.

Meta’s AI model is open-sourced, and now available for others to download from .

“With open source AI models, everybody leap-frogs to that level,” Grainger College assistant professor Nishant Garg. “If we want to improve concrete, it won’t help the overall industry if only one company has better concrete, and the remaining concrete producers lag behind. My aspiration would be 10 years from now, we have this happening at scale at all the ready-mix concrete plants in the world.”

“There’s a lot of opportunity for different parties to collaborate: the general contractors, the concrete and material suppliers, the building owners,” says Darryl Neopolitano, manager of major construction projects for Amrize. “We all have a stake in revolutionizing the most used material on our planet. If we work together, I think we can advance how our world builds the future.”

John Bleasby is a freelance writer. Send comments and Inside Innovation column ideas to editor@dailycommercialnews.com.

Print

Recent Comments

comments for this post are closed

You might also like