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

Abstract

In this work, we demonstrate a machine learning approach, Random Forest, for the β-Ga2O3 growth rate prediction in the metal–organic vapor phase epitaxy (MOVPE) by analyzing the growth process of β-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 (R2) 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.