TY - JOUR
T1 - Quantum chemical accuracy from density functional approximations via machine learning
AU - Bogojeski, Mihail
AU - Vogt-Maranto, Leslie
AU - Tuckerman, Mark E.
AU - Müller, Klaus Robert
AU - Burke, Kieron
N1 - Funding Information:
The authors thank Dr. Felix Brockherde and Joseph Cendagorta for helpful discussions, Dr. Li Li for the initial water dataset, and Dr. Huziel Sauceda and Dr. Stefan Chmiela for the optimized geometries of ethanol and for helpful discussions. Calculations were run on NYU IT High Performance Computing resources and at TUB. Work at NYU was supported by the U.S. Army Research Office under contract/grant number W911NF-13-1-0387 (L.V.-M. and M.E.T.). K.-R.M. was supported in part by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea Government (No. 2019-0-00079, Artificial Intelligence Graduate School Program, Korea University), and was partly supported by the German Ministry for Education and Research (BMBF) under Grants 01IS14013A-E, 01GQ1115, 01GQ0850, 01IS18025A, 031L0207D and 01IS18037A; the German Research Foundation (DFG) under Grant Math+, EXC 2046/1, Project ID 390685689. K.B. was supported by NSF grant CHE 1856165. This publication only reflects the authors views. Funding agencies are not liable for any use that may be made of the information contained herein.
Publisher Copyright:
© 2020, The Author(s).
PY - 2020/12/1
Y1 - 2020/12/1
N2 - 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−1 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−1) 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 (C6H4(OH)2) 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.
AB - 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−1 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−1) 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 (C6H4(OH)2) 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.
UR - http://www.scopus.com/inward/record.url?scp=85092626669&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85092626669&partnerID=8YFLogxK
U2 - 10.1038/s41467-020-19093-1
DO - 10.1038/s41467-020-19093-1
M3 - Article
C2 - 33067479
AN - SCOPUS:85092626669
VL - 11
JO - Nature Communications
JF - Nature Communications
SN - 2041-1723
IS - 1
M1 - 5223
ER -