Molecular force fields with gradient-domain machine learning

Construction and application to dynamics of small molecules with coupled cluster forces

Huziel E. Sauceda, Stefan Chmiela, Igor Poltavsky, Klaus Muller, Alexandre Tkatchenko

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We present the construction of molecular force fields for small molecules (less than 25 atoms) using the recently developed symmetrized gradient-domain machine learning (sGDML) approach [Chmiela et al., Nat. Commun. 9, 3887 (2018) and Chmiela et al., Sci. Adv. 3, e1603015 (2017)]. This approach is able to accurately reconstruct complex high-dimensional potential-energy surfaces from just a few 100s of molecular conformations extracted from ab initio molecular dynamics trajectories. The data efficiency of the sGDML approach implies that atomic forces for these conformations can be computed with high-level wavefunction-based approaches, such as the “gold standard” coupled-cluster theory with single, double and perturbative triple excitations [CCSD(T)]. We demonstrate that the flexible nature of the sGDML model recovers local and non-local electronic interactions (e.g., H-bonding, proton transfer, lone pairs, changes in hybridization states, steric repulsion, and n → π * interactions) without imposing any restriction on the nature of interatomic potentials. The analysis of sGDML molecular dynamics trajectories yields new qualitative insights into dynamics and spectroscopy of small molecules close to spectroscopic accuracy.

Original languageEnglish
Article number114102
JournalJournal of Chemical Physics
Volume150
Issue number11
DOIs
Publication statusPublished - 2019 Mar 21

Fingerprint

machine learning
field theory (physics)
Learning systems
gradients
Molecules
Conformations
Molecular dynamics
molecules
Trajectories
trajectories
molecular dynamics
Potential energy surfaces
Proton transfer
Wave functions
constrictions
potential energy
interactions
Spectroscopy
Atoms
Hydrogen

ASJC Scopus subject areas

  • Physics and Astronomy(all)
  • Physical and Theoretical Chemistry

Cite this

Molecular force fields with gradient-domain machine learning : Construction and application to dynamics of small molecules with coupled cluster forces. / Sauceda, Huziel E.; Chmiela, Stefan; Poltavsky, Igor; Muller, Klaus; Tkatchenko, Alexandre.

In: Journal of Chemical Physics, Vol. 150, No. 11, 114102, 21.03.2019.

Research output: Contribution to journalArticle

Sauceda, Huziel E. ; Chmiela, Stefan ; Poltavsky, Igor ; Muller, Klaus ; Tkatchenko, Alexandre. / Molecular force fields with gradient-domain machine learning : Construction and application to dynamics of small molecules with coupled cluster forces. In: Journal of Chemical Physics. 2019 ; Vol. 150, No. 11.
@article{7b054ff22dc0481d95d1a8787cc99880,
title = "Molecular force fields with gradient-domain machine learning: Construction and application to dynamics of small molecules with coupled cluster forces",
abstract = "We present the construction of molecular force fields for small molecules (less than 25 atoms) using the recently developed symmetrized gradient-domain machine learning (sGDML) approach [Chmiela et al., Nat. Commun. 9, 3887 (2018) and Chmiela et al., Sci. Adv. 3, e1603015 (2017)]. This approach is able to accurately reconstruct complex high-dimensional potential-energy surfaces from just a few 100s of molecular conformations extracted from ab initio molecular dynamics trajectories. The data efficiency of the sGDML approach implies that atomic forces for these conformations can be computed with high-level wavefunction-based approaches, such as the “gold standard” coupled-cluster theory with single, double and perturbative triple excitations [CCSD(T)]. We demonstrate that the flexible nature of the sGDML model recovers local and non-local electronic interactions (e.g., H-bonding, proton transfer, lone pairs, changes in hybridization states, steric repulsion, and n → π * interactions) without imposing any restriction on the nature of interatomic potentials. The analysis of sGDML molecular dynamics trajectories yields new qualitative insights into dynamics and spectroscopy of small molecules close to spectroscopic accuracy.",
author = "Sauceda, {Huziel E.} and Stefan Chmiela and Igor Poltavsky and Klaus Muller and Alexandre Tkatchenko",
year = "2019",
month = "3",
day = "21",
doi = "10.1063/1.5078687",
language = "English",
volume = "150",
journal = "Journal of Chemical Physics",
issn = "0021-9606",
publisher = "American Institute of Physics Publising LLC",
number = "11",

}

TY - JOUR

T1 - Molecular force fields with gradient-domain machine learning

T2 - Construction and application to dynamics of small molecules with coupled cluster forces

AU - Sauceda, Huziel E.

AU - Chmiela, Stefan

AU - Poltavsky, Igor

AU - Muller, Klaus

AU - Tkatchenko, Alexandre

PY - 2019/3/21

Y1 - 2019/3/21

N2 - We present the construction of molecular force fields for small molecules (less than 25 atoms) using the recently developed symmetrized gradient-domain machine learning (sGDML) approach [Chmiela et al., Nat. Commun. 9, 3887 (2018) and Chmiela et al., Sci. Adv. 3, e1603015 (2017)]. This approach is able to accurately reconstruct complex high-dimensional potential-energy surfaces from just a few 100s of molecular conformations extracted from ab initio molecular dynamics trajectories. The data efficiency of the sGDML approach implies that atomic forces for these conformations can be computed with high-level wavefunction-based approaches, such as the “gold standard” coupled-cluster theory with single, double and perturbative triple excitations [CCSD(T)]. We demonstrate that the flexible nature of the sGDML model recovers local and non-local electronic interactions (e.g., H-bonding, proton transfer, lone pairs, changes in hybridization states, steric repulsion, and n → π * interactions) without imposing any restriction on the nature of interatomic potentials. The analysis of sGDML molecular dynamics trajectories yields new qualitative insights into dynamics and spectroscopy of small molecules close to spectroscopic accuracy.

AB - We present the construction of molecular force fields for small molecules (less than 25 atoms) using the recently developed symmetrized gradient-domain machine learning (sGDML) approach [Chmiela et al., Nat. Commun. 9, 3887 (2018) and Chmiela et al., Sci. Adv. 3, e1603015 (2017)]. This approach is able to accurately reconstruct complex high-dimensional potential-energy surfaces from just a few 100s of molecular conformations extracted from ab initio molecular dynamics trajectories. The data efficiency of the sGDML approach implies that atomic forces for these conformations can be computed with high-level wavefunction-based approaches, such as the “gold standard” coupled-cluster theory with single, double and perturbative triple excitations [CCSD(T)]. We demonstrate that the flexible nature of the sGDML model recovers local and non-local electronic interactions (e.g., H-bonding, proton transfer, lone pairs, changes in hybridization states, steric repulsion, and n → π * interactions) without imposing any restriction on the nature of interatomic potentials. The analysis of sGDML molecular dynamics trajectories yields new qualitative insights into dynamics and spectroscopy of small molecules close to spectroscopic accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85063040498&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063040498&partnerID=8YFLogxK

U2 - 10.1063/1.5078687

DO - 10.1063/1.5078687

M3 - Article

VL - 150

JO - Journal of Chemical Physics

JF - Journal of Chemical Physics

SN - 0021-9606

IS - 11

M1 - 114102

ER -