Similar success in atomic property prediction has been limited due to the challenges of training effective models across multiple chemical domains.
Computational catalysis is playing an increasingly significant role in the design of catalysts across a wide range of applications.
We address this issue by relaxing the catalyst discovery goal into a classification problem: "What is the set of catalysts that is worth testing experimentally?"
These uncertainty estimates are instrumental for determining which materials to screen next, but there is not yet a standard procedure for judging the quality of such uncertainty estimates objectively.
Materials Science Computational Physics