Accelerated discovery of CO 2 electrocatalysts using active machine learning | Nature

Accelerated discovery of CO 2 electrocatalysts using active machine learning | Nature

AI powers search for new materials

Researchers on the hunt for new materials are increasingly turning to artificial intelligence (AI) and machine learning. Algorithms can predict the physical characteristics of selected crystal structures from first principles, and neural networks can use that information to make guesses about much larger gamuts of possible materials. In future, automated labs might help to make the materials more quickly. But even a robotic lab will need human overseers: synthesis still involves “a fair amount of artisanship,” says electrical engineer Ted Sargent.

Wired | 6 min readSource: Nature paper