Liverpool University creates a collaborative AI tool to advance material discoveries

To reduce the time and effort required to discover state-of-the-art materials, researchers from Liverpool University’s Department of Chemistry and Materials Innovation Factory, led by Professor Matt Rosseinsky, have created a collaborative AI tool, which has led to the discovery of four new materials already. These materials include a new family of solid-state materials that conduct lithium, which is key to developing solid-state batteries offering increased safety and a more extended range for electric vehicles. In addition, more hopeful materials are said to be in progress. The researcher’s findings were published in Nature Communications.

The cutting-edge technology combines human expertise with artificial intelligence to prioritise areas of uncharted chemical space where novel functional materials are most likely to be discovered.

The tool observes the relationships between known materials at a scale unattainable by humans. These relationships numerically rank and identify combinations of elements that are likely to create new materials. To make the experimental investigation more efficient, the rankings are used to explore the sizeable unfamiliar chemical space in a targeted way. The ultimate judgments are made by those scientists, who are aided by the AI’s unique insight.

Professor Rosseinsky stated: “To date, a common and powerful approach has been to design new materials by close analogy with existing ones, but this often leads to materials that are similar to ones we already have. We, therefore, need new tools that reduce the time and effort required to discover truly new materials, such as the one developed here that combines artificial intelligence and human intelligence to get the best of both. This collaborative approach combines the ability of computers to look at the relationships between several hundred thousand known materials, a scale unattainable for humans, and the expert knowledge and critical thinking of human researchers that leads to creative advances. This tool is an example of one of many collaborative artificial intelligence approaches likely to benefit scientists in the future.”