STEM image analysis based on deep learning: identification of vacancy defects and polymorphs of ${MoS_2}$
This work addresses the bottleneck of high-throughput data processing in materials science, offering an incremental improvement for researchers analyzing atomic-resolution images.
The researchers tackled the labor-intensive analysis of scanning transmission electron microscopy (STEM) images by applying a fully convolutional network (FCN) to identify sulfur vacancies and polymorph types in MoS2, achieving accuracy comparable to manual analysis.
Scanning transmission electron microscopy (STEM) is an indispensable tool for atomic-resolution structural analysis for a wide range of materials. The conventional analysis of STEM images is an extensive hands-on process, which limits efficient handling of high-throughput data. Here we apply a fully convolutional network (FCN) for identification of important structural features of two-dimensional crystals. ResUNet, a type of FCN, is utilized in identifying sulfur vacancies and polymorph types of ${MoS_2}$ from atomic resolution STEM images. Efficient models are achieved based on training with simulated images in the presence of different levels of noise, aberrations, and carbon contamination. The accuracy of the FCN models toward extensive experimental STEM images is comparable to that of careful hands-on analysis. Our work provides a guideline on best practices to train a deep learning model for STEM image analysis and demonstrates FCN's application for efficient processing of a large volume of STEM data.