ROSEMOUNT, MINN. – Even concrete is adapting its ways and mixes to complement AI.
Amrize and Meta have partnered to develop a first-of-its-kind, AI-optimized concrete mix for Meta’s data center in Rosemount, Minn.
This customized solution was designed to deliver high strength, maintain set-time and reduce carbon load, states a release.
It also leverages Amrize’s material engineering expertise and Meta-developed open-sourced AI models, working in partnership with The Grainger College of Engineering at the University of Illinois Urbana-Champaign to create the data for the AI model.
With data showing the mix meets the strength and other performance parameters required for the slab-on-grade application for Meta’s infrastructure, it can now be used in additional areas of the project. The use of the ECOPact mix in the data center currently under construction is estimated to reduce the total carbon footprint of the concrete by 35 per cent.
“Using AI, we can optimize our specialized concrete formulations for data center requirements, from performance needs like strength and durability to thermal regulation and energy-efficiency. We look forward to continuing this exciting work with Meta to scale up the adoption of advanced tailored concrete mixes,” said Jaime Hill, president of Amrize Building Materials, in a statement.
“AI-driven mix design lets us optimize concrete for performance, cost and carbon in one step,” added Illinois Grainger Engineering professor Nishant Garg, who led the data-generation effort in his lab. “As mixes become more complex—with innovative raw materials and product formulation — AI can also forecast critical properties like strength gain over time.”
