AI and automation are accelerating science and chemistry by helping scientists choose which experiments to conduct and discover promising new materials.
Why it matters: These areas are under pressure to produce new materials faster and cheaper to support and power technologies that could transform industries and economies.
The big picture: New materials and molecules are needed for the batteries, drugs and semiconductors proposed to underpin green grids, precision medicine, and the next generation of computing and communications.
What’s happening: It can take decades to bring a new material to market in a process that involves “craft science,” Isayev says.
Zoom in: In a new study, researchers combined machine learning, theories and calculations of physical properties and experiments to identify new alloys.
How it works: The team fed data about various alloys – some more than 100 years old – into an AI model that determines correlations between alloy properties and the elements in them and generates hundreds of thousands of candidate materials. A neural network narrows that down to about 1,000 more candidates.
What they found: The researchers identified two new alloys in six times through the loop.
Yes, but: There is one obstacle to finding a material or chemical. Actually do it differently.
What they’re saying: “Despite the rate of progress in this area, the breakthrough potential of these approaches has yet to be realized,” says a description of a conference on the topic taking place this month.
Things to watch: Another AI model — large language learning models that can write text — may be coming to materials science.
