Published in

Royal Society of Chemistry, Digital Discovery, 4(2), p. 1112-1125, 2023

DOI: 10.1039/d2dd00133k

Links

Tools

Export citation

Search in Google Scholar

By how much can closed-loop frameworks accelerate computational materials discovery?

This paper is made freely available by the publisher.
This paper is made freely available by the publisher.

Full text: Download

Red circle
Preprint: archiving forbidden
Green circle
Postprint: archiving allowed
Green circle
Published version: archiving allowed
Data provided by SHERPA/RoMEO

Abstract

A combination of task automation, calculation runtime improvements, machine learning surrogatization, and sequential learning-guided candidate selection within a closed-loop computational workflow can accelerate materials discovery by up to 20×.