Monitoring MBE substrate deoxidation via RHEED image-sequence analysis by deep learning

TL;DR

This paper introduces a deep learning-based method for automated, accurate, and robust detection of substrate deoxidation in MBE processes using RHEED image sequences, eliminating the need for expert interpretation.

Contribution

It presents a novel combination of auto-encoder and convolutional classifier for real-time, label-free monitoring of substrate deoxidation in MBE, with high robustness over extended periods.

Findings

Accurately identifies deoxidation moments in RHEED sequences

Maintains performance over months without re-training

Operates effectively on raw RHEED images without additional data

Abstract

Reflection high-energy electron diffraction (RHEED) is a powerful tool in molecular beam epitaxy (MBE), but RHEED images are often difficult to interpret, requiring experienced operators. We present an approach for automated surveillance of GaAs substrate deoxidation in MBE reactors using deep learning based RHEED image-sequence classification. Our approach consists of an non-supervised auto-encoder (AE) for feature extraction, combined with a supervised convolutional classifier network. We demonstrate that our lightweight network model can accurately identify the exact deoxidation moment. Furthermore we show that the approach is very robust and allows accurate deoxidation detection during months without requiring re-training. The main advantage of the approach is that it can be applied to raw RHEED images without requiring further information such as the rotation angle, temperature, etc.