Back to Search
Start Over
Quantum chemical accuracy from density functional approximations via machine learning.
- Source :
-
Nature communications [Nat Commun] 2020 Oct 16; Vol. 11 (1), pp. 5223. Date of Electronic Publication: 2020 Oct 16. - Publication Year :
- 2020
-
Abstract
- Kohn-Sham density functional theory (DFT) is a standard tool in most branches of chemistry, but accuracies for many molecules are limited to 2-3 kcal ⋅ mol <superscript>-1</superscript> with presently-available functionals. Ab initio methods, such as coupled-cluster, routinely produce much higher accuracy, but computational costs limit their application to small molecules. In this paper, we leverage machine learning to calculate coupled-cluster energies from DFT densities, reaching quantum chemical accuracy (errors below 1 kcal ⋅ mol <superscript>-1</superscript> ) on test data. Moreover, density-based Δ-learning (learning only the correction to a standard DFT calculation, termed Δ-DFT ) significantly reduces the amount of training data required, particularly when molecular symmetries are included. The robustness of Δ-DFT  is highlighted by correcting "on the fly" DFT-based molecular dynamics (MD) simulations of resorcinol (C <subscript>6</subscript> H <subscript>4</subscript> (OH) <subscript>2</subscript> ) to obtain MD trajectories with coupled-cluster accuracy. We conclude, therefore, that Δ-DFT  facilitates running gas-phase MD simulations with quantum chemical accuracy, even for strained geometries and conformer changes where standard DFT fails.
Details
- Language :
- English
- ISSN :
- 2041-1723
- Volume :
- 11
- Issue :
- 1
- Database :
- MEDLINE
- Journal :
- Nature communications
- Publication Type :
- Academic Journal
- Accession number :
- 33067479
- Full Text :
- https://doi.org/10.1038/s41467-020-19093-1