Optimizing the morphology transition on MOVPE-grown (100) β-Ga2O3 film between step-flow growth and step-bunching: A machine learning-assisted approach

The step-bunching instability in (100) β-Ga2O3 films grown via metalorganic vapor phase epitaxy was investigated using a machine learning approach based on Random Forest (RF). This study reveals the interplay of Ga supersaturation (O2/Ga) and impurity effects as coexisting mechanisms driving the mor...

Full description

Saved in:
Bibliographic Details
Main Authors: Ta-Shun Chou, Saud Bin Anooz, Natasha Dropka, Han-Hsu Chen, Zbigniew Galazka, Martin Albrecht, Andreas Fiedler, Andreas Popp
Format: Article
Language:English
Published: AIP Publishing LLC 2025-05-01
Series:APL Materials
Online Access:http://dx.doi.org/10.1063/5.0261944
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849404321602469888
author Ta-Shun Chou
Saud Bin Anooz
Natasha Dropka
Han-Hsu Chen
Zbigniew Galazka
Martin Albrecht
Andreas Fiedler
Andreas Popp
author_facet Ta-Shun Chou
Saud Bin Anooz
Natasha Dropka
Han-Hsu Chen
Zbigniew Galazka
Martin Albrecht
Andreas Fiedler
Andreas Popp
author_sort Ta-Shun Chou
collection DOAJ
description The step-bunching instability in (100) β-Ga2O3 films grown via metalorganic vapor phase epitaxy was investigated using a machine learning approach based on Random Forest (RF). This study reveals the interplay of Ga supersaturation (O2/Ga) and impurity effects as coexisting mechanisms driving the morphological transition (from step-flow growth to step-bunching). The developed machine-learning framework accurately classifies growth morphology and offers valuable insights by correlating theoretical principles with experimental parameters. Critical growth parameters influencing the film morphology were identified. The corresponding strategy, high Ga supersaturation, is proposed to mitigate the step-bunching formation and maintain the desired step-flow growth mode. Despite the challenges posed by small datasets, the RF model demonstrates robust classification performance, establishing machine learning as a powerful tool for experimental science.
format Article
id doaj-art-2469412cee6b49a18c6ceea062d2bf5b
institution Kabale University
issn 2166-532X
language English
publishDate 2025-05-01
publisher AIP Publishing LLC
record_format Article
series APL Materials
spelling doaj-art-2469412cee6b49a18c6ceea062d2bf5b2025-08-20T03:37:02ZengAIP Publishing LLCAPL Materials2166-532X2025-05-01135051110051110-910.1063/5.0261944Optimizing the morphology transition on MOVPE-grown (100) β-Ga2O3 film between step-flow growth and step-bunching: A machine learning-assisted approachTa-Shun Chou0Saud Bin Anooz1Natasha Dropka2Han-Hsu Chen3Zbigniew Galazka4Martin Albrecht5Andreas Fiedler6Andreas Popp7Leibniz-Institut für Kristallzüchtung (IKZ), Max-Born-Str. 2, 12489 Berlin, GermanyLeibniz-Institut für Kristallzüchtung (IKZ), Max-Born-Str. 2, 12489 Berlin, GermanyLeibniz-Institut für Kristallzüchtung (IKZ), Max-Born-Str. 2, 12489 Berlin, GermanyLeibniz-Institut für Kristallzüchtung (IKZ), Max-Born-Str. 2, 12489 Berlin, GermanyLeibniz-Institut für Kristallzüchtung (IKZ), Max-Born-Str. 2, 12489 Berlin, GermanyLeibniz-Institut für Kristallzüchtung (IKZ), Max-Born-Str. 2, 12489 Berlin, GermanyLeibniz-Institut für Kristallzüchtung (IKZ), Max-Born-Str. 2, 12489 Berlin, GermanyLeibniz-Institut für Kristallzüchtung (IKZ), Max-Born-Str. 2, 12489 Berlin, GermanyThe step-bunching instability in (100) β-Ga2O3 films grown via metalorganic vapor phase epitaxy was investigated using a machine learning approach based on Random Forest (RF). This study reveals the interplay of Ga supersaturation (O2/Ga) and impurity effects as coexisting mechanisms driving the morphological transition (from step-flow growth to step-bunching). The developed machine-learning framework accurately classifies growth morphology and offers valuable insights by correlating theoretical principles with experimental parameters. Critical growth parameters influencing the film morphology were identified. The corresponding strategy, high Ga supersaturation, is proposed to mitigate the step-bunching formation and maintain the desired step-flow growth mode. Despite the challenges posed by small datasets, the RF model demonstrates robust classification performance, establishing machine learning as a powerful tool for experimental science.http://dx.doi.org/10.1063/5.0261944
spellingShingle Ta-Shun Chou
Saud Bin Anooz
Natasha Dropka
Han-Hsu Chen
Zbigniew Galazka
Martin Albrecht
Andreas Fiedler
Andreas Popp
Optimizing the morphology transition on MOVPE-grown (100) β-Ga2O3 film between step-flow growth and step-bunching: A machine learning-assisted approach
APL Materials
title Optimizing the morphology transition on MOVPE-grown (100) β-Ga2O3 film between step-flow growth and step-bunching: A machine learning-assisted approach
title_full Optimizing the morphology transition on MOVPE-grown (100) β-Ga2O3 film between step-flow growth and step-bunching: A machine learning-assisted approach
title_fullStr Optimizing the morphology transition on MOVPE-grown (100) β-Ga2O3 film between step-flow growth and step-bunching: A machine learning-assisted approach
title_full_unstemmed Optimizing the morphology transition on MOVPE-grown (100) β-Ga2O3 film between step-flow growth and step-bunching: A machine learning-assisted approach
title_short Optimizing the morphology transition on MOVPE-grown (100) β-Ga2O3 film between step-flow growth and step-bunching: A machine learning-assisted approach
title_sort optimizing the morphology transition on movpe grown 100 β ga2o3 film between step flow growth and step bunching a machine learning assisted approach
url http://dx.doi.org/10.1063/5.0261944
work_keys_str_mv AT tashunchou optimizingthemorphologytransitiononmovpegrown100bga2o3filmbetweenstepflowgrowthandstepbunchingamachinelearningassistedapproach
AT saudbinanooz optimizingthemorphologytransitiononmovpegrown100bga2o3filmbetweenstepflowgrowthandstepbunchingamachinelearningassistedapproach
AT natashadropka optimizingthemorphologytransitiononmovpegrown100bga2o3filmbetweenstepflowgrowthandstepbunchingamachinelearningassistedapproach
AT hanhsuchen optimizingthemorphologytransitiononmovpegrown100bga2o3filmbetweenstepflowgrowthandstepbunchingamachinelearningassistedapproach
AT zbigniewgalazka optimizingthemorphologytransitiononmovpegrown100bga2o3filmbetweenstepflowgrowthandstepbunchingamachinelearningassistedapproach
AT martinalbrecht optimizingthemorphologytransitiononmovpegrown100bga2o3filmbetweenstepflowgrowthandstepbunchingamachinelearningassistedapproach
AT andreasfiedler optimizingthemorphologytransitiononmovpegrown100bga2o3filmbetweenstepflowgrowthandstepbunchingamachinelearningassistedapproach
AT andreaspopp optimizingthemorphologytransitiononmovpegrown100bga2o3filmbetweenstepflowgrowthandstepbunchingamachinelearningassistedapproach