Skip to main content
Oak Ridge National Laboratory researchers used an invertible neural network, a type of artificial intelligence that mimics the human brain, to select the most suitable materials for desired properties, such as flexibility or heat resistance, with high chemical accuracy. The study could lead to more customizable materials design for industry.

A study led by researchers at ORNL could help make materials design as customizable as point-and-click.

Using quantum Monte Carlo methods, the researchers simulated bulk VO2. Yellow and turquoise represent changes in electron density between the excited and ground states of a compound composed of oxygen, in red, and vanadium, in blue, which allowed them to evaluate how an oxygen vacancy, in white, can alter the compound’s properties. Credit: Panchapakesan Ganesh/ORNL, U.S. Dept. of Energy

Neuromorphic devices — which emulate the decision-making processes of the human brain — show great promise for solving pressing scientific problems, but building physical systems to realize this potential presents researchers with a significant

The illustrations show how the correlation between lattice distortion and proton binding energy in a material affects proton conduction in different environments. Mitigating this interaction could help researchers improve the ionic conductivity of solid materials.

Ionic conduction involves the movement of ions from one location to another inside a material. The ions travel through point defects, which are irregularities in the otherwise consistent arrangement of atoms known as the crystal lattice. This sometimes sluggish process can limit the performance and efficiency of fuel cells, batteries, and other energy storage technologies.