Bypassing the Kohn-Sham equations with machine learning
Machine learning allows electronic structure calculations to access larger system sizes and, in dynamical simulations, longer time scales. Here, the authors perform such a simulation using a machine-learned density functional that avoids direct solution of the Kohn-Sham equations.
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2017-10-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-017-00839-3 |
| _version_ | 1818843320437178368 |
|---|---|
| author | Felix Brockherde Leslie Vogt Li Li Mark E. Tuckerman Kieron Burke Klaus-Robert Müller |
| author_facet | Felix Brockherde Leslie Vogt Li Li Mark E. Tuckerman Kieron Burke Klaus-Robert Müller |
| author_sort | Felix Brockherde |
| collection | DOAJ |
| description | Machine learning allows electronic structure calculations to access larger system sizes and, in dynamical simulations, longer time scales. Here, the authors perform such a simulation using a machine-learned density functional that avoids direct solution of the Kohn-Sham equations. |
| first_indexed | 2024-12-19T04:56:00Z |
| format | Article |
| id | doaj.art-5eb66063f9824f3e9aa4606612d626ee |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-12-19T04:56:00Z |
| publishDate | 2017-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-5eb66063f9824f3e9aa4606612d626ee2022-12-21T20:35:14ZengNature PortfolioNature Communications2041-17232017-10-018111010.1038/s41467-017-00839-3Bypassing the Kohn-Sham equations with machine learningFelix Brockherde0Leslie Vogt1Li Li2Mark E. Tuckerman3Kieron Burke4Klaus-Robert Müller5Machine Learning Group, Technische Universität BerlinDepartment of Chemistry, New York UniversityDepartment of Physics and Astronomy, University of CaliforniaDepartment of Chemistry, New York UniversityDepartment of Physics and Astronomy, University of CaliforniaMachine Learning Group, Technische Universität BerlinMachine learning allows electronic structure calculations to access larger system sizes and, in dynamical simulations, longer time scales. Here, the authors perform such a simulation using a machine-learned density functional that avoids direct solution of the Kohn-Sham equations.https://doi.org/10.1038/s41467-017-00839-3 |
| spellingShingle | Felix Brockherde Leslie Vogt Li Li Mark E. Tuckerman Kieron Burke Klaus-Robert Müller Bypassing the Kohn-Sham equations with machine learning Nature Communications |
| title | Bypassing the Kohn-Sham equations with machine learning |
| title_full | Bypassing the Kohn-Sham equations with machine learning |
| title_fullStr | Bypassing the Kohn-Sham equations with machine learning |
| title_full_unstemmed | Bypassing the Kohn-Sham equations with machine learning |
| title_short | Bypassing the Kohn-Sham equations with machine learning |
| title_sort | bypassing the kohn sham equations with machine learning |
| url | https://doi.org/10.1038/s41467-017-00839-3 |
| work_keys_str_mv | AT felixbrockherde bypassingthekohnshamequationswithmachinelearning AT leslievogt bypassingthekohnshamequationswithmachinelearning AT lili bypassingthekohnshamequationswithmachinelearning AT marketuckerman bypassingthekohnshamequationswithmachinelearning AT kieronburke bypassingthekohnshamequationswithmachinelearning AT klausrobertmuller bypassingthekohnshamequationswithmachinelearning |