More Sustainable Concrete with Meta and AI
Concrete is the most popular building material in the world, and we use between 10 and 30 billion tons each year. But the price of that progress is a cost to the environment. Cement, an essential ingredient in concrete, is responsible for eight percent of global anthropogenic greenhouse gas emissions.
With its glue-like properties, cement has historically been combined with other ingredients, such as water, sand, and coarse aggregates, to make concrete. But the manufacture of cement causes enormous amounts of carbon emissions, in part because of the fuels needed to heat some of the ingredients to 1,400 degrees Celsius. Furthermore, one of the key ingredients is limestone, which also releases carbon dioxide during calcination in the manufacturing process.
Enter the power of artificial intelligence. Researchers at The Grainger College of Engineering, Meta, and the concrete supplier Ozinga partnered to develop better concrete formulas using AI. The Grainger Engineering team was led by Professors Nishant Garg of the Department of Civil & Environmental Engineering and Lav Varshney of the Department of Electrical & Computer Engineering and the Coordinated Science Lab. The work was supported by the Meta Sustainability Net Zero program, Meta, and the Illinois-IBM Center for Cognitive Computing Systems Research (C3SR).
The early-stage results found the AI-powered formulas reduce the carbon footprint of the concrete by 40 percent while maintaining strength and durability. Meta tested the formulas on multiple structures at the company’s DeKalb data center, including the floor slabs of the guardhouse and the construction management team’s temporary offices.