Meta, formerly known as Facebook, claims that it has created a new artificial intelligence (AI) model that can effectively formulate sustainable concrete.
Meta AI researchers have collaborated with the University of Illinois, Urbana-Champaign, to develop this novel AI that can design and revise formulas for increasingly high-strength, low-carbon concrete.
Concrete, which accounts for 8% of global carbon emissions, is one of the highest contributing sources of carbon emissions in the world. As a result, lowering concrete emissions will have a far-reaching influence.
Researchers used the Concrete Compressive Strength data set, freely available from the UCI Machine Learning Repository, to train this AI model. The AI model generated multiple new concrete mixes using the input data on concrete formulas, along with their compressive strength and carbon footprint.
According to Meta, the database used to train the AI model contains 1,030 instances of concrete formulas and their validated attributes, which includes seven-day and 28-day compressive strength data.
“The embodied carbon footprint associated with the concrete formulas was derived using the Cement Sustainability Initiative’s Environmental Product Declaration (EPD) tool. EPDs are a standardized way of accounting for the environmental impacts of a product or material, including carbon emissions over its life cycle,” mentioned Meta in the blog.
Researchers had to spend only about a week on the refinement of the AI model. Post refinement, the concrete formula designed by the model met or surpassed all of the standards while replacing up to 70% of the cement with low carbon-emitting substitutes called fly ash and slag.
“We wanted to test the formulas in the field and selected our data center in DeKalb, Illinois, as an ideal location, given its proximity to the University of Illinois at Urbana-Champaign,” said Meta.