Nanodiamonds and Beyond: Argonne Designs Carbon Materials With Artificial Intelligence at Exascale

LEMONT, Ill.--(BUSINESS WIRE)--Carbon is everywhere. It forms the graphite in pencils, the diamonds in jewelry and the molecules that make up every living thing. Under extreme conditions — like the heat and pressure of intense explosions — carbon can transform into exotic nanometer-sized structures called nanocarbons. These materials are often stronger than steel, lighter than plastic and adaptable for uses in medicine, energy and national security.

Scientists at the U.S. Department of Energy’s (DOE) Argonne National Laboratory and partner universities are uncovering how carbon behaves in extreme environments, and researchers are learning to predict and control the ways that carbon atoms rearrange themselves under intense heat and pressure. Their discoveries open the door to designing materials before they are ever made in a laboratory.

Carbon reveals new structures under extreme conditions. Scientists can use physics-based modeling, AI and exascale computing to predict how carbon assembles at the nanoscale and design carbon materials for real-world applications.

The research team focused on nanodiamonds, tiny diamond crystals only a few millionths of a millimeter across. The particles form in explosive environments, where temperatures soar higher than the surface of the sun and pressures rise to millions of times that of Earth’s atmosphere.

What happens next — how the material cools and how the pressure drops — determines whether the nanodiamond stays a diamond or transforms into other carbon forms.

The team used Argonne’s Aurora supercomputer to simulate these transformations atom by atom. Aurora is the flagship computer of the Argonne Leadership Computing Facility, a DOE Office of Science user facility. They also used the Frontier supercomputer at DOE’s Oak Ridge National Laboratory and the Delta and DeltaAI systems at the National Center for Supercomputing Applications at the University of Illinois Urbana-Champaign.

The researchers’ simulations revealed that the ​“recipe” of cooling and pressure release strongly influences the final structure of the material. Rapid cooling tends to preserve the diamond form, while slower cooling allows carbon atoms to rearrange into layered shells and curved structures.

The scientists trained AI models on the massive simulation data they produced. The models learned to recognize patterns between temperature, pressure and the final shape of the carbon material. With this approach, the computer could predict what kind of nanocarbon will form from a given set of conditions. This means scientists can design new materials on a computer first, rather than relying on lengthy trial-and-error experiments in the lab, saving time and research funds.