Home / Blog / Using AI to “invent” new materials

Using AI to “invent” new materials

The University of Liverpool’s Materials Innovation Factory. Credit: The University of Liverpool

At the end of 2020 I included in the Megatrends for this decade the use of artificial intelligence to design new alloys. There is a potential huge space for mixing atoms of different elements (plus using additive manufacturing we could create specific atomic structures!) and because of that we can dream the possibility to create an alloy with the characteristics we need. The problem is looking for a needle in a haystack.

Now I stumbled onto a news that is reinforcing that Megatrend: researchers at the University of Liverpool, UK, have developed an AI based tool aiming at reducing the time to “invent” new materials. Interestingly, their approach is based on a collaboration between material designers and AI.

They are reporting in an article published on Sept. 21st on the successful discovery of four new materials. Among these they found a solid state materials that could be applied in lithium-ion batteries to increase their performance.

The AI system is learning from existing materials (several hundred thousands) correlating their characteristic with their atomic structure and use this knowledge to explore potential new combinations that can be promising, ranking the probability. This allows material designers to focus on the most promising solutions.
I like this news because it shows a trend towards combining human with artificial intelligence in a collaborative way. Notice that here we do not have a screwdriver that is helping a human worker in a specific activity, rather we have a tool that in addition to providing help is “learning” on the way, like a team of humans where we learn from each other making the teamwork better and better. This is the crucial difference in applying AI in teamwork from applying standard tools.

About Roberto Saracco

Roberto Saracco fell in love with technology and its implications long time ago. His background is in math and computer science. Until April 2017 he led the EIT Digital Italian Node and then was head of the Industrial Doctoral School of EIT Digital up to September 2018. Previously, up to December 2011 he was the Director of the Telecom Italia Future Centre in Venice, looking at the interplay of technology evolution, economics and society. At the turn of the century he led a World Bank-Infodev project to stimulate entrepreneurship in Latin America. He is a senior member of IEEE where he leads the New Initiative Committee and co-chairs the Digital Reality Initiative. He is a member of the IEEE in 2050 Ad Hoc Committee. He teaches a Master course on Technology Forecasting and Market impact at the University of Trento. He has published over 100 papers in journals and magazines and 14 books.