They may not be able to shout "Eureka!" like their human colleagues but AI/ML system have shown immense potential in the field of compound discovery -- whether that's sifting through reams of data to find new therapeutic compounds or imagining new recipes using the ingredients' flavor profiles. Now a team from Meta AI, working with researchers at the University of Illinois, Urbana-Champaign, have created an AI that can devise and refine formulas for increasingly high-strength, low-carbon concrete. Traditional methods for creating concrete, of which we produce billions of tons every year, are far from ecologically friendly. In fact, they generate an estimated 8 percent of the annual global carbon dioxide emission total. Advances have been made in recent years to reduce the concrete industry's carbon footprint (as well as in make the material more rugged, more resilient and even capable of charging EVs) but overall its production remains among the most carbon intensive in modern construction.

Concrete is the most widely used engineered material in the world with more than 10 billion tons produced annually. Unfortunately, with that scale comes a significant burden in terms of energy, water, and release of greenhouse gases and other pollutants. As such, there is interest in creating concrete formulas that minimize this environmental burden, while satisfying engineering performance requirements. Recent advances in artificial intelligence have enabled machines to generate highly plausible artifacts, such as images of realistic looking faces. Semi-supervised generative models allow generation of artifacts with specific, desired characteristics. In this work, we use Conditional Variational Autoencoders (CVAE), a type of semi-supervised generative model, to discover concrete formulas with desired properties. Our model is trained using open data from the UCI Machine Learning Repository joined with environmental impact data computed using a web-based tool. We demonstrate CVAEs can design concrete formulas with lower emissions and natural resource usage while meeting design requirements. To ensure fair comparison between extant and generated formulas, we also train regression models to predict the environmental impacts and strength of discovered formulas. With these results, a construction engineer may create a formula that meets structural needs and best addresses local environmental concerns.