Cargando…
Discovering Superhard B–N–O Compounds by Iterative Machine Learning and Evolutionary Structure Predictions
[Image: see text] We searched for new superhard B–N–O compounds with an iterative machine learning (ML) procedure, where ML models are trained using sample crystal structures from an evolutionary algorithm. We first used cohesive energy to evaluate the thermodynamic stability of varying B(x)N(y)O(z)...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Chemical Society
2022
|
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9219054/ https://www.ncbi.nlm.nih.gov/pubmed/35755336 http://dx.doi.org/10.1021/acsomega.2c01818 |
_version_ | 1784732024448221184 |
---|---|
author | Chen, Wei-Chih Vohra, Yogesh K. Chen, Cheng-Chien |
author_facet | Chen, Wei-Chih Vohra, Yogesh K. Chen, Cheng-Chien |
author_sort | Chen, Wei-Chih |
collection | PubMed |
description | [Image: see text] We searched for new superhard B–N–O compounds with an iterative machine learning (ML) procedure, where ML models are trained using sample crystal structures from an evolutionary algorithm. We first used cohesive energy to evaluate the thermodynamic stability of varying B(x)N(y)O(z) compositions and then gradually focused on compositional regions with high cohesive energy and high hardness. The results converged quickly after a few iterations. Our resulting ML models show that B(x+2)N(x)O(3) compounds with x ≥ 3 (like B(5)N(3)O(3), B(6)N(4)O(3), etc.) are potentially superhard and thermodynamically favorable. Our meta-GGA density functional theory calculations indicate that these materials are also wide bandgap (≥4.4 eV) insulators, with the valence band maximum related to the p-orbitals of nitrogen atoms near vacant sites. This study demonstrates that an iterative method combining ML and ab initio simulations provides a powerful tool for discovering novel materials. |
format | Online Article Text |
id | pubmed-9219054 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | American Chemical Society |
record_format | MEDLINE/PubMed |
spelling | pubmed-92190542022-06-24 Discovering Superhard B–N–O Compounds by Iterative Machine Learning and Evolutionary Structure Predictions Chen, Wei-Chih Vohra, Yogesh K. Chen, Cheng-Chien ACS Omega [Image: see text] We searched for new superhard B–N–O compounds with an iterative machine learning (ML) procedure, where ML models are trained using sample crystal structures from an evolutionary algorithm. We first used cohesive energy to evaluate the thermodynamic stability of varying B(x)N(y)O(z) compositions and then gradually focused on compositional regions with high cohesive energy and high hardness. The results converged quickly after a few iterations. Our resulting ML models show that B(x+2)N(x)O(3) compounds with x ≥ 3 (like B(5)N(3)O(3), B(6)N(4)O(3), etc.) are potentially superhard and thermodynamically favorable. Our meta-GGA density functional theory calculations indicate that these materials are also wide bandgap (≥4.4 eV) insulators, with the valence band maximum related to the p-orbitals of nitrogen atoms near vacant sites. This study demonstrates that an iterative method combining ML and ab initio simulations provides a powerful tool for discovering novel materials. American Chemical Society 2022-06-09 /pmc/articles/PMC9219054/ /pubmed/35755336 http://dx.doi.org/10.1021/acsomega.2c01818 Text en © 2022 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by-nc-nd/4.0/Permits non-commercial access and re-use, provided that author attribution and integrity are maintained; but does not permit creation of adaptations or other derivative works (https://creativecommons.org/licenses/by-nc-nd/4.0/). |
spellingShingle | Chen, Wei-Chih Vohra, Yogesh K. Chen, Cheng-Chien Discovering Superhard B–N–O Compounds by Iterative Machine Learning and Evolutionary Structure Predictions |
title | Discovering Superhard B–N–O Compounds
by Iterative Machine Learning and Evolutionary Structure Predictions |
title_full | Discovering Superhard B–N–O Compounds
by Iterative Machine Learning and Evolutionary Structure Predictions |
title_fullStr | Discovering Superhard B–N–O Compounds
by Iterative Machine Learning and Evolutionary Structure Predictions |
title_full_unstemmed | Discovering Superhard B–N–O Compounds
by Iterative Machine Learning and Evolutionary Structure Predictions |
title_short | Discovering Superhard B–N–O Compounds
by Iterative Machine Learning and Evolutionary Structure Predictions |
title_sort | discovering superhard b–n–o compounds
by iterative machine learning and evolutionary structure predictions |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9219054/ https://www.ncbi.nlm.nih.gov/pubmed/35755336 http://dx.doi.org/10.1021/acsomega.2c01818 |
work_keys_str_mv | AT chenweichih discoveringsuperhardbnocompoundsbyiterativemachinelearningandevolutionarystructurepredictions AT vohrayogeshk discoveringsuperhardbnocompoundsbyiterativemachinelearningandevolutionarystructurepredictions AT chenchengchien discoveringsuperhardbnocompoundsbyiterativemachinelearningandevolutionarystructurepredictions |