Work

Quantum chemical accuracy from density functional approximations via machine learning

Year: 2020

Type: article

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 −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 (C 6 H 4 (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.

Source: Nature Communications

DOI: 10.1038/s41467-020-19093-1

Authors: Mihail Bogojeski, Leslie Vogt-Maranto, Mark E. Tuckerman, Klaus-Robert Müller, Kieron Burke

Institutions: Technische Universität Berlin, New York University, New York University Shanghai, Courant Institute of Mathematical Sciences, Korea University, Max Planck Institute for Informatics, University of California, Irvine

Language: English

Topic: Advanced Chemical Physics Studies

Subfield: Atomic and Molecular Physics, and Optics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $5,380

Funders: National Science Foundation, U.S. Department of Defense, Deutsche Forschungsgemeinschaft, Bundesministerium für Bildung und Forschung, Korea University, Institute for Information and Communications Technology Promotion, Division of Chemistry, Army Research Office

Awards: G1067038318, G1372115314, G1395773357, G162064734, G2033548659, G237601077, G2747436919, G2804209865, G2953128317, CompLS - Runde 2 - Verbundprojekt: Patho234 - Multidimensionale Bildanalyse von reaktiven und neoplastischen Lymphknoten durch maschinelles Lernen - Teilprojekt D, G3515117348, Verbundprojekt: Bernstein Fokus Neurotechnologie - Nichtinvasive Neurotechnologie für Mensch-Maschine Interaktion - Teilprojekte A1, A3, A4, B4, W3, Zentrum, Verbundprojekt BIFOLD-BZML: Berlin Institute for the Foundations of Learning and Data, THEORY AND EXPERIMENT OF COCRYSTALS: PRINCIPLES, SYNTHESIS AND PROPERTIES, D-JPN Verbund: Adaptive Gehirn-Computer-Schnittstellen (BCI) in nichtstationären Umgebungen, Improving accuracy and applicability of density functional theory, G6274897657, G743358325, G7452299184, Verbundprojekt BIFOLD-BBDC: Berlin Institute for the Foundations of Learning and Data, EXC 2046: MATH+: Berlin Mathematics Research Center, G8727049869, G877632230

OpenAlex ID: W3093036756

FWCI: 18.91

Cites: 123

Cited by: 407

Related to: 9