Quantum chemical accuracy from density functional approximations via machine learning
High-level ab initio quantum chemical methods carry a high computational burden, thus limiting their applicability. Here, the authors employ machine learning to generate coupled-cluster energies and forces at chemical accuracy for geometry optimization and molecular dynamics from DFT densities.
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2020-10-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-020-19093-1 |
| _version_ | 1818743676321398784 |
|---|---|
| author | Mihail Bogojeski Leslie Vogt-Maranto Mark E. Tuckerman Klaus-Robert Müller Kieron Burke |
| author_facet | Mihail Bogojeski Leslie Vogt-Maranto Mark E. Tuckerman Klaus-Robert Müller Kieron Burke |
| author_sort | Mihail Bogojeski |
| collection | DOAJ |
| description | High-level ab initio quantum chemical methods carry a high computational burden, thus limiting their applicability. Here, the authors employ machine learning to generate coupled-cluster energies and forces at chemical accuracy for geometry optimization and molecular dynamics from DFT densities. |
| first_indexed | 2024-12-18T02:32:12Z |
| format | Article |
| id | doaj.art-d4bccd11d88747148712df68cb7f00dc |
| institution | Directory Open Access Journal |
| issn | 2041-1723 |
| language | English |
| last_indexed | 2024-12-18T02:32:12Z |
| publishDate | 2020-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj.art-d4bccd11d88747148712df68cb7f00dc2022-12-21T21:23:52ZengNature PortfolioNature Communications2041-17232020-10-0111111110.1038/s41467-020-19093-1Quantum chemical accuracy from density functional approximations via machine learningMihail Bogojeski0Leslie Vogt-Maranto1Mark E. Tuckerman2Klaus-Robert Müller3Kieron Burke4Machine Learning Group, Technische Universität BerlinDepartment of Chemistry, New York UniversityDepartment of Chemistry, New York UniversityMachine Learning Group, Technische Universität BerlinDepartment of Physics and Astronomy, University of CaliforniaHigh-level ab initio quantum chemical methods carry a high computational burden, thus limiting their applicability. Here, the authors employ machine learning to generate coupled-cluster energies and forces at chemical accuracy for geometry optimization and molecular dynamics from DFT densities.https://doi.org/10.1038/s41467-020-19093-1 |
| spellingShingle | Mihail Bogojeski Leslie Vogt-Maranto Mark E. Tuckerman Klaus-Robert Müller Kieron Burke Quantum chemical accuracy from density functional approximations via machine learning Nature Communications |
| title | Quantum chemical accuracy from density functional approximations via machine learning |
| title_full | Quantum chemical accuracy from density functional approximations via machine learning |
| title_fullStr | Quantum chemical accuracy from density functional approximations via machine learning |
| title_full_unstemmed | Quantum chemical accuracy from density functional approximations via machine learning |
| title_short | Quantum chemical accuracy from density functional approximations via machine learning |
| title_sort | quantum chemical accuracy from density functional approximations via machine learning |
| url | https://doi.org/10.1038/s41467-020-19093-1 |
| work_keys_str_mv | AT mihailbogojeski quantumchemicalaccuracyfromdensityfunctionalapproximationsviamachinelearning AT leslievogtmaranto quantumchemicalaccuracyfromdensityfunctionalapproximationsviamachinelearning AT marketuckerman quantumchemicalaccuracyfromdensityfunctionalapproximationsviamachinelearning AT klausrobertmuller quantumchemicalaccuracyfromdensityfunctionalapproximationsviamachinelearning AT kieronburke quantumchemicalaccuracyfromdensityfunctionalapproximationsviamachinelearning |