research laboratory to study “bad bubbles” that cause defects in metal alloys used to produce engine turbine blades and semiconductor crystals that are crucial components in electronic devices.

Machine-learning models can speed up the discovery of new materials by making predictions and suggesting experiments. But most models today only consider a few specific types of data or variables.

At Oak Ridge National Laboratory’s Center for Nanophase Materials Sciences, Yongtao Liu is building AI-driven “closed-loop” ...