BIGDML—Towards accurate quantum machine learning force fields for materials

Most machine-learning force fields dismiss long-range interactions. Here the authors demonstrate the BIGDML approach for building materials’ potential energy surfaces that enables a broad range of materials simulations within accuracies better than 1 meV/atom using just 10–200 structures for trainin...

Full description

Bibliographic Details
Main Authors: Huziel E. Sauceda, Luis E. Gálvez-González, Stefan Chmiela, Lauro Oliver Paz-Borbón, Klaus-Robert Müller, Alexandre Tkatchenko
Format: Article
Language:English
Published: Nature Portfolio 2022-06-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-022-31093-x
_version_ 1818234256872177664
author Huziel E. Sauceda
Luis E. Gálvez-González
Stefan Chmiela
Lauro Oliver Paz-Borbón
Klaus-Robert Müller
Alexandre Tkatchenko
author_facet Huziel E. Sauceda
Luis E. Gálvez-González
Stefan Chmiela
Lauro Oliver Paz-Borbón
Klaus-Robert Müller
Alexandre Tkatchenko
author_sort Huziel E. Sauceda
collection DOAJ
description Most machine-learning force fields dismiss long-range interactions. Here the authors demonstrate the BIGDML approach for building materials’ potential energy surfaces that enables a broad range of materials simulations within accuracies better than 1 meV/atom using just 10–200 structures for training.
first_indexed 2024-12-12T11:35:11Z
format Article
id doaj.art-12448a9a30fc406b930ba187509c527b
institution Directory Open Access Journal
issn 2041-1723
language English
last_indexed 2024-12-12T11:35:11Z
publishDate 2022-06-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj.art-12448a9a30fc406b930ba187509c527b2022-12-22T00:25:40ZengNature PortfolioNature Communications2041-17232022-06-0113111610.1038/s41467-022-31093-xBIGDML—Towards accurate quantum machine learning force fields for materialsHuziel E. Sauceda0Luis E. Gálvez-González1Stefan Chmiela2Lauro Oliver Paz-Borbón3Klaus-Robert Müller4Alexandre Tkatchenko5Departamento de Materia Condensada, Instituto de Física, Universidad Nacional Autónoma de MéxicoPrograma de Doctorado en Ciencias (Física), División de Ciencias Exactas y Naturales, Universidad de Sonora, Blvd. Luis Encinas & RosalesMachine Learning Group, Technische Universität BerlinDepartamento de Física Química, Instituto de Física, Universidad Nacional Autónoma de MéxicoMachine Learning Group, Technische Universität BerlinDepartment of Physics and Materials Science, University of LuxembourgMost machine-learning force fields dismiss long-range interactions. Here the authors demonstrate the BIGDML approach for building materials’ potential energy surfaces that enables a broad range of materials simulations within accuracies better than 1 meV/atom using just 10–200 structures for training.https://doi.org/10.1038/s41467-022-31093-x
spellingShingle Huziel E. Sauceda
Luis E. Gálvez-González
Stefan Chmiela
Lauro Oliver Paz-Borbón
Klaus-Robert Müller
Alexandre Tkatchenko
BIGDML—Towards accurate quantum machine learning force fields for materials
Nature Communications
title BIGDML—Towards accurate quantum machine learning force fields for materials
title_full BIGDML—Towards accurate quantum machine learning force fields for materials
title_fullStr BIGDML—Towards accurate quantum machine learning force fields for materials
title_full_unstemmed BIGDML—Towards accurate quantum machine learning force fields for materials
title_short BIGDML—Towards accurate quantum machine learning force fields for materials
title_sort bigdml towards accurate quantum machine learning force fields for materials
url https://doi.org/10.1038/s41467-022-31093-x
work_keys_str_mv AT huzielesauceda bigdmltowardsaccuratequantummachinelearningforcefieldsformaterials
AT luisegalvezgonzalez bigdmltowardsaccuratequantummachinelearningforcefieldsformaterials
AT stefanchmiela bigdmltowardsaccuratequantummachinelearningforcefieldsformaterials
AT laurooliverpazborbon bigdmltowardsaccuratequantummachinelearningforcefieldsformaterials
AT klausrobertmuller bigdmltowardsaccuratequantummachinelearningforcefieldsformaterials
AT alexandretkatchenko bigdmltowardsaccuratequantummachinelearningforcefieldsformaterials