Nature Reviews Physics volume 3, 724 (2021)
An AI-toolkit to develop and share research into new materials
Probably the biggest challenge in materials science is the discovery or design of new materials that exhibit exceptional performance for a desired function, or uncovering new properties of known materials. AI methods can be used to identify patterns and trends from big data to these ends. In materials science, these big data are a complex, hierarchical structure of experimental measures and theoretical estimates. Since 2014, the Novel Materials Discovery (NOMAD) Laboratory has established a materials data infrastructure, based on a large repository of materials data, and provides AI tools and training for researchers to freely access this resource, in compliance with the FAIR principles — that data should be findable, accessible, interoperable and reusable (or recyclable).