Energy-free machine learning force field for aluminum
Abstract We used the machine learning technique of Li et al. (PRL 114, 2015) for molecular dynamics simulations. Atomic configurations were described by feature matrix based on internal vectors, and linear regression was used as a learning technique. We implemented this approach in the LAMMPS code....
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2017
|
Materias: | |
Acceso en línea: | https://doaj.org/article/13e9687800914490b751cb5d5f07ee43 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:13e9687800914490b751cb5d5f07ee43 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:13e9687800914490b751cb5d5f07ee432021-12-02T12:31:48ZEnergy-free machine learning force field for aluminum10.1038/s41598-017-08455-32045-2322https://doaj.org/article/13e9687800914490b751cb5d5f07ee432017-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-08455-3https://doaj.org/toc/2045-2322Abstract We used the machine learning technique of Li et al. (PRL 114, 2015) for molecular dynamics simulations. Atomic configurations were described by feature matrix based on internal vectors, and linear regression was used as a learning technique. We implemented this approach in the LAMMPS code. The method was applied to crystalline and liquid aluminum and uranium at different temperatures and densities, and showed the highest accuracy among different published potentials. Phonon density of states, entropy and melting temperature of aluminum were calculated using this machine learning potential. The results are in excellent agreement with experimental data and results of full ab initio calculations.Ivan KruglovOleg SergeevAlexey YanilkinArtem R. OganovNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-7 (2017) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Ivan Kruglov Oleg Sergeev Alexey Yanilkin Artem R. Oganov Energy-free machine learning force field for aluminum |
description |
Abstract We used the machine learning technique of Li et al. (PRL 114, 2015) for molecular dynamics simulations. Atomic configurations were described by feature matrix based on internal vectors, and linear regression was used as a learning technique. We implemented this approach in the LAMMPS code. The method was applied to crystalline and liquid aluminum and uranium at different temperatures and densities, and showed the highest accuracy among different published potentials. Phonon density of states, entropy and melting temperature of aluminum were calculated using this machine learning potential. The results are in excellent agreement with experimental data and results of full ab initio calculations. |
format |
article |
author |
Ivan Kruglov Oleg Sergeev Alexey Yanilkin Artem R. Oganov |
author_facet |
Ivan Kruglov Oleg Sergeev Alexey Yanilkin Artem R. Oganov |
author_sort |
Ivan Kruglov |
title |
Energy-free machine learning force field for aluminum |
title_short |
Energy-free machine learning force field for aluminum |
title_full |
Energy-free machine learning force field for aluminum |
title_fullStr |
Energy-free machine learning force field for aluminum |
title_full_unstemmed |
Energy-free machine learning force field for aluminum |
title_sort |
energy-free machine learning force field for aluminum |
publisher |
Nature Portfolio |
publishDate |
2017 |
url |
https://doaj.org/article/13e9687800914490b751cb5d5f07ee43 |
work_keys_str_mv |
AT ivankruglov energyfreemachinelearningforcefieldforaluminum AT olegsergeev energyfreemachinelearningforcefieldforaluminum AT alexeyyanilkin energyfreemachinelearningforcefieldforaluminum AT artemroganov energyfreemachinelearningforcefieldforaluminum |
_version_ |
1718394259971768320 |