Modern machine learning force fields (ML-FF) are able to yield energy and force predictions at the accuracy of high-level ab initio methods, but at a much lower computational cost. On the other hand, classical molecular mechanics force fields (MM-FF) employ fixed functional forms and tend to be less accurate, but considerably faster and transferable between molecules of the same class. In this work, we investigate how both approaches can complement each other. We contrast the ability of ML-FF for reconstructing dynamic and thermodynamic observables to MM-FFs in order to gain a qualitative understanding of the differences between the two approaches. This analysis enables us to modify the generalized AMBER force field by reparametrizing short-range and bonded interactions with more expressive terms to make them more accurate, without sacrificing the key properties that make MM-FFs so successful.
Skip Nav Destination
Molecular force fields with gradient-domain machine learning (GDML): Comparison and synergies with classical force fields
Article navigation
28 September 2020
Research Article|
September 24 2020
Molecular force fields with gradient-domain machine learning (GDML): Comparison and synergies with classical force fields
Special Collection:
Machine Learning Meets Chemical Physics
Huziel E. Sauceda
;
Huziel E. Sauceda
a)
1
Department of Physics and Materials Science, University of Luxembourg
, L-1511 Luxembourg, Luxembourg
2
Machine Learning Group, Technische Universität Berlin
, 10587 Berlin, Germany
3
BASLEARN, BASF-TU Joint Lab, Technische Universität Berlin
, 10587 Berlin, Germany
a)Authors to whom correspondence should be addressed: [email protected]; [email protected]; and [email protected]
Search for other works by this author on:
Michael Gastegger
;
Michael Gastegger
2
Machine Learning Group, Technische Universität Berlin
, 10587 Berlin, Germany
3
BASLEARN, BASF-TU Joint Lab, Technische Universität Berlin
, 10587 Berlin, Germany
4
DFG Cluster of Excellence “Unifying Systems in Catalysis” (UniSysCat), Technische Universität Berlin
, 10623 Berlin, Germany
Search for other works by this author on:
Stefan Chmiela
;
Stefan Chmiela
2
Machine Learning Group, Technische Universität Berlin
, 10587 Berlin, Germany
Search for other works by this author on:
Klaus-Robert Müller
;
Klaus-Robert Müller
a)
2
Machine Learning Group, Technische Universität Berlin
, 10587 Berlin, Germany
5
Department of Artificial Intelligence, Korea University
, Anam-dong, Seongbuk-gu, Seoul 136-713, South Korea
6
Max Planck Institute for Informatics
, Stuhlsatzenhausweg, 66123 Saarbrücken, Germany
7
Google Research, Brain Team
, Berlin, Germany
a)Authors to whom correspondence should be addressed: [email protected]; [email protected]; and [email protected]
Search for other works by this author on:
Alexandre Tkatchenko
Alexandre Tkatchenko
a)
1
Department of Physics and Materials Science, University of Luxembourg
, L-1511 Luxembourg, Luxembourg
a)Authors to whom correspondence should be addressed: [email protected]; [email protected]; and [email protected]
Search for other works by this author on:
a)Authors to whom correspondence should be addressed: [email protected]; [email protected]; and [email protected]
Note: This paper is part of the JCP Special Topic on Machine Learning Meets Chemical Physics.
J. Chem. Phys. 153, 124109 (2020)
Article history
Received:
July 25 2020
Accepted:
September 02 2020
Citation
Huziel E. Sauceda, Michael Gastegger, Stefan Chmiela, Klaus-Robert Müller, Alexandre Tkatchenko; Molecular force fields with gradient-domain machine learning (GDML): Comparison and synergies with classical force fields. J. Chem. Phys. 28 September 2020; 153 (12): 124109. https://doi.org/10.1063/5.0023005
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Citing articles via
DeePMD-kit v2: A software package for deep potential models
Jinzhe Zeng, Duo Zhang, et al.
CREST—A program for the exploration of low-energy molecular chemical space
Philipp Pracht, Stefan Grimme, et al.
Freezing point depression of salt aqueous solutions using the Madrid-2019 model
Cintia P. Lamas, Carlos Vega, et al.
Related Content
Ensemble learning of coarse-grained molecular dynamics force fields with a kernel approach
J. Chem. Phys. (May 2020)
Molecular force fields with gradient-domain machine learning: Construction and application to dynamics of small molecules with coupled cluster forces
J. Chem. Phys. (March 2019)
Efficient force field and energy emulation through partition of permutationally equivalent atoms
J. Chem. Phys. (May 2022)
FCHL revisited: Faster and more accurate quantum machine learning
J. Chem. Phys. (January 2020)
Masked pretraining strategy for neural potentials
AIP Advances (September 2024)