A Google AI has discovered 2.2m materials unknown to science
Zillions of possible crystals exist. AI can help catalogue them
Crystals can do all sorts of things, some more useful than others. They can separate the gullible from their money in New Age healing shops. But they can also serve as the light-harvesting layer in a solar panel, catalyse industrial reactions to make things like ammonia and nitric acid, and form the silicon used in microchips. That diversity arises from the fact that “crystal” refers to a huge family of compounds, united only by having an atomic structure made of repeating units—the 3D equivalent of tessellating tiles.
Just how huge is highlighted by a paper published in Nature by Google DeepMind, an artificial-intelligence company. Scientists know of about 48,000 different crystals, each with a different chemical recipe. DeepMind has created a machine-learning tool called GNoME (Graph Networks for Materials Exploration) that can use existing libraries of chemical structures to predict new ones. It came up with 2.2m crystal structures, each new to science.
Explore more
This article appeared in the Science & technology section of the print edition under the headline "Crystal ball"
More from Science and technology
A Russia-linked network uses AI to rewrite real news stories
CopyCop churned out 19,000 deceptive posts in a month
To stay fit, future Moon-dwellers will need special workouts
Running around the inside of a barrel might help
Wind turbines keep getting bigger
That poses a giant transport problem