AI technique could lead to development of new materials

Scientists from Russia, Singapore and the US have used AI to predict changes to material properties under strain, which could lead to the engineering of new tailored materials.

Strain engineering has wide implications for technology in general. It has previously been demonstrated that it has the potential to improve the performance of silicon chips by as much as 50 per cent, as well as manipulate nanoneedles made from diamond.

In the new study, published in in the Proceedings of the National Academy of Sciences, the researchers describe how machine learning was used to identify the most energy-efficient strain pathways that could transform diamond into more effective semiconductors. Strain can be applied in any of six different and independent ways (in three different dimensions, each one of which can produce strain in-and-out or sideways), and with nearly infinite gradations of degree, so the number of possibilities is impractical to explore simply by trial and error.