Machine-learning-assisted thin-film growth: Bayesian optimization in molecular beam epitaxy of SrRuO3 thin films
Materials informatics exploiting machine learning techniques, e.g., Bayesian optimization (BO), have the potential to reduce the number of thin-film growth runs for optimization of thin-film growth conditions through incremental updates of machine learning models in accordance with newly measured da...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
AIP Publishing LLC
2019-10-01
|
Series: | APL Materials |
Online Access: | http://dx.doi.org/10.1063/1.5123019 |
id |
doaj-d57a92298f4f4bbbbb420ad49da24744 |
---|---|
record_format |
Article |
spelling |
doaj-d57a92298f4f4bbbbb420ad49da247442020-11-24T21:42:06ZengAIP Publishing LLCAPL Materials2166-532X2019-10-01710101114101114-710.1063/1.5123019Machine-learning-assisted thin-film growth: Bayesian optimization in molecular beam epitaxy of SrRuO3 thin filmsYuki K. Wakabayashi0Takuma Otsuka1Yoshiharu Krockenberger2Hiroshi Sawada3Yoshitaka Taniyasu4Hideki Yamamoto5NTT Basic Research Laboratories, NTT Corporation, Atsugi, Kanagawa 243-0198, JapanNTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto 619-0237, JapanNTT Basic Research Laboratories, NTT Corporation, Atsugi, Kanagawa 243-0198, JapanNTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto 619-0237, JapanNTT Basic Research Laboratories, NTT Corporation, Atsugi, Kanagawa 243-0198, JapanNTT Basic Research Laboratories, NTT Corporation, Atsugi, Kanagawa 243-0198, JapanMaterials informatics exploiting machine learning techniques, e.g., Bayesian optimization (BO), have the potential to reduce the number of thin-film growth runs for optimization of thin-film growth conditions through incremental updates of machine learning models in accordance with newly measured data. Here, we demonstrated BO-based molecular beam epitaxy (MBE) of SrRuO3, one of the most intensively studied materials in the research field of oxide electronics, mainly owing to its unique nature as a ferromagnetic metal. To simplify the intricate search space of entangled growth conditions, we ran the BO for a single condition while keeping the other conditions fixed. As a result, high-crystalline-quality SrRuO3 film exhibiting a high residual resistivity ratio of over 50 as well as strong perpendicular magnetic anisotropy was developed in only 24 MBE growth runs in which the Ru flux rate, growth temperature, and O3-nozzle-to-substrate distance were optimized. Our BO-based search method provides an efficient experimental design that is not as dependent on the experience and skills of individual researchers, and it reduces experimental time and cost, which will accelerate materials research.http://dx.doi.org/10.1063/1.5123019 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yuki K. Wakabayashi Takuma Otsuka Yoshiharu Krockenberger Hiroshi Sawada Yoshitaka Taniyasu Hideki Yamamoto |
spellingShingle |
Yuki K. Wakabayashi Takuma Otsuka Yoshiharu Krockenberger Hiroshi Sawada Yoshitaka Taniyasu Hideki Yamamoto Machine-learning-assisted thin-film growth: Bayesian optimization in molecular beam epitaxy of SrRuO3 thin films APL Materials |
author_facet |
Yuki K. Wakabayashi Takuma Otsuka Yoshiharu Krockenberger Hiroshi Sawada Yoshitaka Taniyasu Hideki Yamamoto |
author_sort |
Yuki K. Wakabayashi |
title |
Machine-learning-assisted thin-film growth: Bayesian optimization in molecular beam epitaxy of SrRuO3 thin films |
title_short |
Machine-learning-assisted thin-film growth: Bayesian optimization in molecular beam epitaxy of SrRuO3 thin films |
title_full |
Machine-learning-assisted thin-film growth: Bayesian optimization in molecular beam epitaxy of SrRuO3 thin films |
title_fullStr |
Machine-learning-assisted thin-film growth: Bayesian optimization in molecular beam epitaxy of SrRuO3 thin films |
title_full_unstemmed |
Machine-learning-assisted thin-film growth: Bayesian optimization in molecular beam epitaxy of SrRuO3 thin films |
title_sort |
machine-learning-assisted thin-film growth: bayesian optimization in molecular beam epitaxy of srruo3 thin films |
publisher |
AIP Publishing LLC |
series |
APL Materials |
issn |
2166-532X |
publishDate |
2019-10-01 |
description |
Materials informatics exploiting machine learning techniques, e.g., Bayesian optimization (BO), have the potential to reduce the number of thin-film growth runs for optimization of thin-film growth conditions through incremental updates of machine learning models in accordance with newly measured data. Here, we demonstrated BO-based molecular beam epitaxy (MBE) of SrRuO3, one of the most intensively studied materials in the research field of oxide electronics, mainly owing to its unique nature as a ferromagnetic metal. To simplify the intricate search space of entangled growth conditions, we ran the BO for a single condition while keeping the other conditions fixed. As a result, high-crystalline-quality SrRuO3 film exhibiting a high residual resistivity ratio of over 50 as well as strong perpendicular magnetic anisotropy was developed in only 24 MBE growth runs in which the Ru flux rate, growth temperature, and O3-nozzle-to-substrate distance were optimized. Our BO-based search method provides an efficient experimental design that is not as dependent on the experience and skills of individual researchers, and it reduces experimental time and cost, which will accelerate materials research. |
url |
http://dx.doi.org/10.1063/1.5123019 |
work_keys_str_mv |
AT yukikwakabayashi machinelearningassistedthinfilmgrowthbayesianoptimizationinmolecularbeamepitaxyofsrruo3thinfilms AT takumaotsuka machinelearningassistedthinfilmgrowthbayesianoptimizationinmolecularbeamepitaxyofsrruo3thinfilms AT yoshiharukrockenberger machinelearningassistedthinfilmgrowthbayesianoptimizationinmolecularbeamepitaxyofsrruo3thinfilms AT hiroshisawada machinelearningassistedthinfilmgrowthbayesianoptimizationinmolecularbeamepitaxyofsrruo3thinfilms AT yoshitakataniyasu machinelearningassistedthinfilmgrowthbayesianoptimizationinmolecularbeamepitaxyofsrruo3thinfilms AT hidekiyamamoto machinelearningassistedthinfilmgrowthbayesianoptimizationinmolecularbeamepitaxyofsrruo3thinfilms |
_version_ |
1725918967600513024 |