AI could shine a light on better materials for batteries and flexible solar panels

A new AI system could “seriously accelerate” the development of materials for technologies ranging from batteries to flexible solar panels, researchers have claimed.

Researchers at Aalto University in Finland and the Technical University of Denmark developed Artist (Artificial Intelligence for Spectroscopy) to speed up spectroscopy, a technique that will be vital for the creation of ‘designer materials’ for future technology.

Spectroscopy probes the internal properties of materials by observing their response to electromagnetic radiation such as light. It has led to the development of countless everyday technologies, but existing experimental and computational spectroscopy approaches can be incredibly costly, the researchers said.

“Normally, to find the best molecules for devices, we have to combine previous knowledge with some degree of chemical intuition,” said postdoctoral Aalto researcher Milica Todorovic. “Checking their individual spectra is then a trial-and-error process that can stretch weeks or months, depending on the number of molecules that might fit the job. Our AI gives you these properties instantly.”

The multidisciplinary team trained the AI over a few weeks with a dataset of more than 132,000 organic molecules. Artist can accurately predict how those molecules, and similar ones, will react to a stream of light. The team now hopes to expand its abilities by training Artist with even more data.

The system’s speed and accuracy could hasten the development of flexible electronics, including light-emitting diodes (LEDs), paper with screen-like abilities or solar panels, the team said. When combined with other research, they said Artist could “hold the key” to better batteries and catalysts.

The researchers aim to release Artist on an open science platform this year. It is available for use and training on request.

The work was published in Advanced Science.