One of my favorite stories in that package comes from my colleague David Rotman, who took a close look at AI for materials research. AI could transform the process of discovering new materials – innovations that could be especially useful in the world of climate tech, which requires new batteries, semiconductors, magnets and more.
But the field still needs to prove that it can create materials that are truly innovative and useful. Can AI really supercharge materials research? What might that look like?
For researchers hoping to find new ways to power the world (or cure disease or achieve many other big, important goals), a new material could change everything.
The problem is that inventing content is hard and slow. Just look at plastics – the first fully synthetic plastic was invented in 1907, but it took until about the 1950s for companies to produce the wide range we are familiar with today. (And yes, although it’s incredibly useful, plastic also creates no shortage of complications for society.)
In recent decades, materials science has slowed down a bit – David has been covering the field for nearly 40 years, and as he says, there have been only a few major commercial breakthroughs in that time. (Lithium-ion batteries are one.)
Can AI change everything? The possibility is intriguing and companies are rushing to test it.
Leela Sciences, based in Cambridge, Massachusetts, is working on using AI models to uncover new materials. The company can not only train an AI model on all the latest scientific literature, but also plug it into an automated laboratory so it can learn from experimental data. The goal is to speed up the iterative process of inventing and testing new materials and to see research in ways that humans might miss.
At an MIT Technology Review event earlier this year, I got to hear David interview Rafael Gomez-Bombarelli, one of Leela’s co-founders. As he explained what the company is working on, Gomez-Bombarelli admitted that no major breakthroughs have been seen yet in the search for AI materials. As yet.
