Bypassing the Kohn-Sham equations with machine learning

Felix Brockherde, Leslie Vogt, Li Li, Mark E. Tuckerman, Kieron Burke, Klaus Muller

Research output: Contribution to journalArticle

161 Citations (Scopus)

Abstract

Last year, at least 30,000 scientific papers used the Kohn-Sham scheme of density functional theory to solve electronic structure problems in a wide variety of scientific fields. Machine learning holds the promise of learning the energy functional via examples, bypassing the need to solve the Kohn-Sham equations. This should yield substantial savings in computer time, allowing larger systems and/or longer time-scales to be tackled, but attempts to machine-learn this functional have been limited by the need to find its derivative. The present work overcomes this difficulty by directly learning the density-potential and energy-density maps for test systems and various molecules. We perform the first molecular dynamics simulation with a machine-learned density functional on malonaldehyde and are able to capture the intramolecular proton transfer process. Learning density models now allows the construction of accurate density functionals for realistic molecular systems.

Original languageEnglish
Article number872
JournalNature Communications
Volume8
Issue number1
DOIs
Publication statusPublished - 2017 Dec 1

ASJC Scopus subject areas

  • Chemistry(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Physics and Astronomy(all)

Fingerprint Dive into the research topics of 'Bypassing the Kohn-Sham equations with machine learning'. Together they form a unique fingerprint.

  • Cite this

    Brockherde, F., Vogt, L., Li, L., Tuckerman, M. E., Burke, K., & Muller, K. (2017). Bypassing the Kohn-Sham equations with machine learning. Nature Communications, 8(1), [872]. https://doi.org/10.1038/s41467-017-00839-3