Evolutionary computing and machine learning for discovering of low-energy defect configurations

Abstract Density functional theory (DFT) has become a standard tool for the study of point defects in materials. However, finding the most stable defective structures remains a very challenging task as it involves the solution of a multimodal optimization problem with a high-dimensional objective fu...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Marco Arrigoni, Georg K. H. Madsen
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/a88de3e9469f4940a039fdef29558a9d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a88de3e9469f4940a039fdef29558a9d
record_format	dspace
spelling	oai:doaj.org-article:a88de3e9469f4940a039fdef29558a9d2021-12-02T15:52:24ZEvolutionary computing and machine learning for discovering of low-energy defect configurations10.1038/s41524-021-00537-12057-3960https://doaj.org/article/a88de3e9469f4940a039fdef29558a9d2021-05-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00537-1https://doaj.org/toc/2057-3960Abstract Density functional theory (DFT) has become a standard tool for the study of point defects in materials. However, finding the most stable defective structures remains a very challenging task as it involves the solution of a multimodal optimization problem with a high-dimensional objective function. Hitherto, the approaches most commonly used to tackle this problem have been mostly empirical, heuristic, and/or based on domain knowledge. In this contribution, we describe an approach for exploring the potential energy surface (PES) based on the covariance matrix adaptation evolution strategy (CMA-ES) and supervised and unsupervised machine learning models. The resulting algorithm depends only on a limited set of physically interpretable hyperparameters and the approach offers a systematic way for finding low-energy configurations of isolated point defects in solids. We demonstrate its applicability on different systems and show its ability to find known low-energy structures and discover additional ones as well.Marco ArrigoniGeorg K. H. MadsenNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
spellingShingle	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765 Marco Arrigoni Georg K. H. Madsen Evolutionary computing and machine learning for discovering of low-energy defect configurations
description	Abstract Density functional theory (DFT) has become a standard tool for the study of point defects in materials. However, finding the most stable defective structures remains a very challenging task as it involves the solution of a multimodal optimization problem with a high-dimensional objective function. Hitherto, the approaches most commonly used to tackle this problem have been mostly empirical, heuristic, and/or based on domain knowledge. In this contribution, we describe an approach for exploring the potential energy surface (PES) based on the covariance matrix adaptation evolution strategy (CMA-ES) and supervised and unsupervised machine learning models. The resulting algorithm depends only on a limited set of physically interpretable hyperparameters and the approach offers a systematic way for finding low-energy configurations of isolated point defects in solids. We demonstrate its applicability on different systems and show its ability to find known low-energy structures and discover additional ones as well.
format	article
author	Marco Arrigoni Georg K. H. Madsen
author_facet	Marco Arrigoni Georg K. H. Madsen
author_sort	Marco Arrigoni
title	Evolutionary computing and machine learning for discovering of low-energy defect configurations
title_short	Evolutionary computing and machine learning for discovering of low-energy defect configurations
title_full	Evolutionary computing and machine learning for discovering of low-energy defect configurations
title_fullStr	Evolutionary computing and machine learning for discovering of low-energy defect configurations
title_full_unstemmed	Evolutionary computing and machine learning for discovering of low-energy defect configurations
title_sort	evolutionary computing and machine learning for discovering of low-energy defect configurations
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/a88de3e9469f4940a039fdef29558a9d
work_keys_str_mv	AT marcoarrigoni evolutionarycomputingandmachinelearningfordiscoveringoflowenergydefectconfigurations AT georgkhmadsen evolutionarycomputingandmachinelearningfordiscoveringoflowenergydefectconfigurations
_version_	1718385590126247936

Evolutionary computing and machine learning for discovering of low-energy defect configurations

Ejemplares similares