Leveraging generative adversarial networks to create realistic scanning transmission electron microscopy images

Abstract

The rise of automation and machine learning (ML) in electron microscopy has the potential to revolutionize materials research through autonomous data collection and processing. A significant challenge lies in developing ML models that rapidly generalize to large data sets under varying experimental conditions. We address this by employing a cycle generative adversarial network (CycleGAN) with a reciprocal space discriminator, which augments simulated data with realistic spatial frequency information. This allows the CycleGAN to generate images nearly indistinguishable from real data and provide labels for ML applications. We showcase our approach by training a fully convolutional network (FCN) to identify single atom defects in a 4.5 million atom data set, collected using automated acquisition in an aberration-corrected scanning transmission electron microscope (STEM). Our method produces adaptable FCNs that can adjust to dynamically changing experimental variables with minimal intervention, marking a crucial step towards fully autonomous harnessing of microscopy big data.

25 pages, 6 figures, 2 tables

References in corpus (3)

• Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations
• Towards Augmented Microscopy with Reinforcement Learning-Enhanced Workflows
• Contamination of TEM Holders Quantified and Mitigated with Open-Hardware, High-Vacuum Bakeout System

Cited by in corpus (5)

• Machine Learning Microscopic Form of Nematic Order in twisted double-bilayer graphene
• Auto-resolving the atomic structure at van der Waals interfaces using a generative model
• SAM-I-Am: Semantic Boosting for Zero-shot Atomic-Scale Electron Micrograph Segmentation
• Mind the Gap: Bridging the Divide Between AI Aspirations and the Reality of Autonomous Characterization
• Noise2Void for Denoising Atomic Resolution Scanning Transmission Electron Microscopy Images