Machine learning supported analysis of MOVPE grown β-Ga2O3 thin films on sapphire

被引：13

作者：

Chou, Ta-Shun ^{[1
]}

Bin Anooz, Saud ^{[1
]}

Grueneberg, Raimund ^{[1
]}

Dropka, Natasha ^{[1
]}

Miller, Wolfram ^{[1
]}

Tran, Thi Thuy Vi ^{[1
]}

Rehm, Jana ^{[1
]}

Albrecht, Martin ^{[1
]}

Popp, Andreas ^{[1
]}

机构：

[1] Leibniz Inst Kristallzuchtung IKZ, Max Born Str 2, D-12489 Berlin, Germany

来源：

JOURNAL OF CRYSTAL GROWTH | 2022年 / 592卷

关键词：

Computer simulation; Metalorganic vapor phase epitaxy; Gallium compounds; Oxides; NEURAL-NETWORKS; GAS-PHASE; OPTIMIZATION; LAYERS; TRIETHYLGALLIUM; DECOMPOSITION; SURFACE; MODEL;

D O I：

10.1016/j.jcrysgro.2022.126737

中图分类号：

O7 [晶体学];

学科分类号：

0702 ; 070205 ; 0703 ; 080501 ;

摘要：

In this work, we demonstrate a machine learning approach, Random Forest, for the beta-Ga2O3 growth rate prediction in the metal-organic vapor phase epitaxy (MOVPE) by analyzing the growth process of beta-Ga2O3 on sapphire optically. The proposed model can assess the complex non-linear dependencies among the growth parameters and optimize them for the optimal growth rate. The model based on the process parameters (e.g., precursor concentration, chamber pressure, and push gas) provides high predictive power, reaching the coefficient of determination (R-2) of 0.95 and 0.92 for the training and testing sets. The outcome of the model is applicable to both homoepitaxial and heteroepitaxial processes and on different substrate orientations.

引用

页数：9

共 45 条

[1] Fast growth rate of epitaxial β-Ga2O3 by close coupled showerhead MOCVD [J].

Alema, Fikadu ;

Hertog, Brian ;

Osinsky, Andrei ;

Mukhopadhyay, Partha ;

Toporkov, Mykyta ;

Schoenfeld, Winston V. .

JOURNAL OF CRYSTAL GROWTH, 2017, 475 :77-82

[2]

[Anonymous], 2021, IEEE Trans. Broadcast.

[3] Si- and Sn-Doped Homoepitaxial β-Ga2O3 Layers Grown by MOVPE on (010)-Oriented Substrates [J].

Baldini, Michele ;

Albrecht, Martin ;

Fiedler, Andreas ;

Irmscher, Klaus ;

Schewski, Robert ;

Wagner, Guenter .

ECS JOURNAL OF SOLID STATE SCIENCE AND TECHNOLOGY, 2017, 6 (02) :Q3040-Q3044

[4] Semiconducting Sn-doped β-Ga2O3 homoepitaxial layers grown by metal organic vapour-phase epitaxy [J].

Baldini, Michele ;

Albrecht, Martin ;

Fiedler, Andreas ;

Irmscher, Klaus ;

Klimm, Detlef ;

Schewski, Robert ;

Wagner, Guenter .

JOURNAL OF MATERIALS SCIENCE, 2016, 51 (07) :3650-3656

[5] Step flow growth of β-Ga2O3 thin films on vicinal (100) β-Ga2O3 substrates grown by MOVPE [J].

Bin Anooz, S. ;

Grueneberg, R. ;

Wouters, C. ;

Schewski, R. ;

Albrecht, M. ;

Fiedler, A. ;

Irmscher, K. ;

Galazka, Z. ;

Miller, W. ;

Wagner, G. ;

Schwarzkopf, J. ;

Popp, A. .

APPLIED PHYSICS LETTERS, 2020, 116 (18)

[6] Fast homoepitaxial growth of (100) β-Ga2O3 thin films via MOVPE [J].

Chou, Ta-Shun ;

Seyidov, Palvan ;

Bin Anooz, Saud ;

Grueneberg, Raimund ;

Thi Thuy Vi Tran ;

Irmscher, Klaus ;

Albrecht, Martin ;

Galazka, Zbigniew ;

Schwarzkopf, Jutta ;

Popp, Andreas .

AIP ADVANCES, 2021, 11 (11)

[7] Toward Precise n-Type Doping Control in MOVPE-Grown β-Ga2O3 Thin Films by Deep-Learning Approach [J].

Chou, Ta-Shun ;

Bin Anooz, Saud ;

Grueneberg, Raimund ;

Irmscher, Klaus ;

Dropka, Natasha ;

Rehm, Jana ;

Tran, Thi Thuy Vi ;

Miller, Wolfram ;

Seyidov, Palvan ;

Albrecht, Martin ;

Popp, Andreas .

CRYSTALS, 2022, 12 (01)

[8] Development and Optimization of VGF-GaAs Crystal Growth Process Using Data Mining and Machine Learning Techniques [J].

Dropka, Natasha ;

Boettcher, Klaus ;

Holena, Martin .

CRYSTALS, 2021, 11 (10)

[9] Optimization of magnetically driven directional solidification of silicon using artificial neural networks and Gaussian process models [J].

Dropka, Natasha ;

Holena, Martin .

JOURNAL OF CRYSTAL GROWTH, 2017, 471 :53-61

[10] Low pressure chemical vapor deposition of β-Ga2O3 thin films: Dependence on growth parameters [J].

Feng, Zixuan ;

Karim, Md Rezaul ;

Zhao, Hongping .

APL MATERIALS, 2019, 7 (02)

← 1 2 3 4 5 →