Cargando…
Bandgap prediction of two-dimensional materials using machine learning
The bandgap of two-dimensional (2D) materials plays an important role in their applications to various devices. For instance, the gapless nature of graphene limits the use of this material to semiconductor device applications, whereas the indirect bandgap of molybdenum disulfide is suitable for elec...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8363013/ https://www.ncbi.nlm.nih.gov/pubmed/34388173 http://dx.doi.org/10.1371/journal.pone.0255637 |
_version_ | 1783738282844094464 |
---|---|
author | Zhang, Yu Xu, Wenjing Liu, Guangjie Zhang, Zhiyong Zhu, Jinlong Li, Meng |
author_facet | Zhang, Yu Xu, Wenjing Liu, Guangjie Zhang, Zhiyong Zhu, Jinlong Li, Meng |
author_sort | Zhang, Yu |
collection | PubMed |
description | The bandgap of two-dimensional (2D) materials plays an important role in their applications to various devices. For instance, the gapless nature of graphene limits the use of this material to semiconductor device applications, whereas the indirect bandgap of molybdenum disulfide is suitable for electrical and photo-device applications. Therefore, predicting the bandgap rapidly and accurately for a given 2D material structure has great scientific significance in the manufacturing of semiconductor devices. Compared to the extremely high computation cost of conventional first-principles calculations, machine learning (ML) based on statistics may be a promising alternative to predicting bandgaps. Although ML algorithms have been used to predict the properties of materials, they have rarely been used to predict the properties of 2D materials. In this study, we apply four ML algorithms to predict the bandgaps of 2D materials based on the computational 2D materials database (C2DB). Gradient boosted decision trees and random forests are more effective in predicting bandgaps of 2D materials with an R(2) >90% and root-mean-square error (RMSE) of ~0.24 eV and 0.27 eV, respectively. By contrast, support vector regression and multi-layer perceptron show that R(2) is >70% with RMSE of ~0.41 eV and 0.43 eV, respectively. Finally, when the bandgap calculated without spin-orbit coupling (SOC) is used as a feature, the RMSEs of the four ML models decrease greatly to 0.09 eV, 0.10 eV, 0.17 eV, and 0.12 eV, respectively. The R(2) of all the models is >94%. These results show that the properties of 2D materials can be rapidly obtained by ML prediction with high precision. |
format | Online Article Text |
id | pubmed-8363013 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-83630132021-08-14 Bandgap prediction of two-dimensional materials using machine learning Zhang, Yu Xu, Wenjing Liu, Guangjie Zhang, Zhiyong Zhu, Jinlong Li, Meng PLoS One Research Article The bandgap of two-dimensional (2D) materials plays an important role in their applications to various devices. For instance, the gapless nature of graphene limits the use of this material to semiconductor device applications, whereas the indirect bandgap of molybdenum disulfide is suitable for electrical and photo-device applications. Therefore, predicting the bandgap rapidly and accurately for a given 2D material structure has great scientific significance in the manufacturing of semiconductor devices. Compared to the extremely high computation cost of conventional first-principles calculations, machine learning (ML) based on statistics may be a promising alternative to predicting bandgaps. Although ML algorithms have been used to predict the properties of materials, they have rarely been used to predict the properties of 2D materials. In this study, we apply four ML algorithms to predict the bandgaps of 2D materials based on the computational 2D materials database (C2DB). Gradient boosted decision trees and random forests are more effective in predicting bandgaps of 2D materials with an R(2) >90% and root-mean-square error (RMSE) of ~0.24 eV and 0.27 eV, respectively. By contrast, support vector regression and multi-layer perceptron show that R(2) is >70% with RMSE of ~0.41 eV and 0.43 eV, respectively. Finally, when the bandgap calculated without spin-orbit coupling (SOC) is used as a feature, the RMSEs of the four ML models decrease greatly to 0.09 eV, 0.10 eV, 0.17 eV, and 0.12 eV, respectively. The R(2) of all the models is >94%. These results show that the properties of 2D materials can be rapidly obtained by ML prediction with high precision. Public Library of Science 2021-08-13 /pmc/articles/PMC8363013/ /pubmed/34388173 http://dx.doi.org/10.1371/journal.pone.0255637 Text en © 2021 Zhang et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Zhang, Yu Xu, Wenjing Liu, Guangjie Zhang, Zhiyong Zhu, Jinlong Li, Meng Bandgap prediction of two-dimensional materials using machine learning |
title | Bandgap prediction of two-dimensional materials using machine learning |
title_full | Bandgap prediction of two-dimensional materials using machine learning |
title_fullStr | Bandgap prediction of two-dimensional materials using machine learning |
title_full_unstemmed | Bandgap prediction of two-dimensional materials using machine learning |
title_short | Bandgap prediction of two-dimensional materials using machine learning |
title_sort | bandgap prediction of two-dimensional materials using machine learning |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8363013/ https://www.ncbi.nlm.nih.gov/pubmed/34388173 http://dx.doi.org/10.1371/journal.pone.0255637 |
work_keys_str_mv | AT zhangyu bandgappredictionoftwodimensionalmaterialsusingmachinelearning AT xuwenjing bandgappredictionoftwodimensionalmaterialsusingmachinelearning AT liuguangjie bandgappredictionoftwodimensionalmaterialsusingmachinelearning AT zhangzhiyong bandgappredictionoftwodimensionalmaterialsusingmachinelearning AT zhujinlong bandgappredictionoftwodimensionalmaterialsusingmachinelearning AT limeng bandgappredictionoftwodimensionalmaterialsusingmachinelearning |