scholarly journals Molecular force fields with gradient-domain machine learning (GDML): Comparison and synergies with classical force fields

2020 ◽  
Vol 153 (12) ◽  
pp. 124109
Author(s):  
Huziel E. Sauceda ◽  
Michael Gastegger ◽  
Stefan Chmiela ◽  
Klaus-Robert Müller ◽  
Alexandre Tkatchenko
Keyword(s):  
Machine Learning ◽  
Force Fields ◽  
Molecular Force ◽  
Gradient Domain

scholarly journals Molecular force fields with gradient-domain machine learning: Construction and application to dynamics of small molecules with coupled cluster forces

2019 ◽  
Vol 150 (11) ◽  
pp. 114102 ◽  
Author(s):  
Huziel E. Sauceda ◽  
Stefan Chmiela ◽  
Igor Poltavsky ◽  
Klaus-Robert Müller ◽  
Alexandre Tkatchenko
Keyword(s):  
Machine Learning ◽  
Small Molecules ◽  
Force Fields ◽  
Coupled Cluster ◽  
Molecular Force ◽  
Gradient Domain

scholarly journals A transferable active-learning strategy for reactive molecular force fields

2021 ◽  
Author(s):  
Tom Young ◽  
Tristan Johnston-Wood ◽  
Volker L. Deringer ◽  
Fernanda Duarte
Keyword(s):  
Machine Learning ◽  
Active Learning ◽  
Learning Strategy ◽  
Force Fields ◽  
Molecular Simulations ◽  
Quantum Mechanical ◽  
Interatomic Potentials ◽  
Molecular Force ◽  
High Level ◽  
Active Learning Strategy

Predictive molecular simulations require fast, accurate and reactive interatomic potentials. Machine learning offers a promising approach to construct such potentials by fitting energies and forces to high-level quantum-mechanical data, but...

scholarly journals Machine learning of correlated dihedral potentials for atomistic molecular force fields

2018 ◽  
Vol 8 (1) ◽  
Author(s):  
Pascal Friederich ◽  
Manuel Konrad ◽  
Timo Strunk ◽  
Wolfgang Wenzel
Keyword(s):  
Machine Learning ◽  
Force Fields ◽  
Molecular Force

Utilizing Machine Learning for Efficient Parameterization of Coarse Grained Molecular Force Fields

2019 ◽  
Vol 59 (10) ◽  
pp. 4278-4288 ◽  
Author(s):  
James L. McDonagh ◽  
Ardita Shkurti ◽  
David J. Bray ◽  
Richard L. Anderson ◽  
Edward O. Pyzer-Knapp
Keyword(s):  
Machine Learning ◽  
Force Fields ◽  
Coarse Grained ◽  
Molecular Force

scholarly journals sGDML: Constructing accurate and data efficient molecular force fields using machine learning

2019 ◽  
Vol 240 ◽  
pp. 38-45 ◽  
Author(s):  
Stefan Chmiela ◽  
Huziel E. Sauceda ◽  
Igor Poltavsky ◽  
Klaus-Robert Müller ◽  
Alexandre Tkatchenko
Keyword(s):  
Machine Learning ◽  
Force Fields ◽  
Molecular Force

scholarly journals Machine learning of accurate energy-conserving molecular force fields

2017 ◽  
Vol 3 (5) ◽  
pp. e1603015 ◽  
Author(s):  
Stefan Chmiela ◽  
Alexandre Tkatchenko ◽  
Huziel E. Sauceda ◽  
Igor Poltavsky ◽  
Kristof T. Schütt ◽  
...  
Keyword(s):  
Machine Learning ◽  
Force Fields ◽  
Molecular Force ◽  
Energy Conserving

scholarly journals Gradient domain machine learning with composite kernels: improving the accuracy of PES and force fields for large molecules

2021 ◽  
Author(s):  
Kasra Asnaashari ◽  
Roman V Krems
Keyword(s):  
Machine Learning ◽  
Ab Initio Calculations ◽  
Ab Initio ◽  
Force Fields ◽  
Search Algorithm ◽  
Information Criterion ◽  
Absolute Error ◽  
Kernel Functions ◽  
Gradient Domain ◽  
The Mean

Abstract The generalization accuracy of machine learning models of potential energy surfaces (PES) and force fields (FF) for large polyatomic molecules can be improved either by increasing the number of training points or by improving the models. In order to build accurate models based on expensive {\it ab initio} calculations, much of recent work has focused on the latter. In particular, it has been shown that gradient domain machine learning (GDML) models produce accurate results for high-dimensional molecular systems with a small number of {\it ab initio} calculations. The present work extends GDML to models with composite kernels built to maximize inference from a small number of molecular geometries. We illustrate that GDML models can be improved by increasing the complexity of underlying kernels through a greedy search algorithm using Bayesian information criterion as the model selection metric. We show that this requires including anisotropy into kernel functions and produces models with significantly smaller generalization errors. The results are presented for ethanol, uracil, malonaldehyde and aspirin. For aspirin, the model with composite kernels trained by forces at 1000 randomly sampled molecular geometries produces a global 57-dimensional PES with the mean absolute accuracy 0.177 kcal/mol (61.9 cm$^{-1}$) and FFs with the mean absolute error 0.457 kcal/mol~Å$^{-1}$.

scholarly journals Improving molecular force fields across configurational space by combining supervised and unsupervised machine learning

2021 ◽  
Vol 154 (12) ◽  
pp. 124102
Author(s):  
Gregory Fonseca ◽  
Igor Poltavsky ◽  
Valentin Vassilev-Galindo ◽  
Alexandre Tkatchenko
Keyword(s):  
Machine Learning ◽  
Force Fields ◽  
Unsupervised Machine Learning ◽  
Configurational Space ◽  
Molecular Force

Molecular force fields. Part XII.—Force constant relationships in the non-metallic hydrides

1950 ◽  
Vol 46 (0) ◽  
pp. 137-146 ◽  
Author(s):  
D. F. Heath ◽  
J. W. Linnett ◽  
P. J. Wheatley
Keyword(s):  
Force Constant ◽  
Force Fields ◽  
Molecular Force
Sign in / Sign up

Export Citation Format

Share Document