Partial Scanning Transmission Electron Microscopy with Deep Learning

Abstract

Compressed sensing algorithms are used to decrease electron microscope scan time and electron beam exposure with minimal information loss. Following successful applications of deep learning to compressed sensing, we have developed a two-stage multiscale generative adversarial neural network to complete realistic 512$\times$512 scanning transmission electron micrographs from spiral, jittered gridlike, and other partial scans. For spiral scans and mean squared error based pre-training, this enables electron beam coverage to be decreased by 17.9$\times$ with a 3.8\% test set root mean squared intensity error, and by 87.0$\times$ with a 6.2\% error. Our generator networks are trained on partial scans created from a new dataset of 16227 scanning transmission electron micrographs. High performance is achieved with adaptive learning rate clipping of loss spikes and an auxiliary trainer network. Our source code, new dataset, and pre-trained models have been made publicly available at https://github.com/Jeffrey-Ede/partial-STEM

20 pages, 11 figures

References in corpus (6)

• Sparsity and Incoherence in Compressive Sampling
• Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations
• Resolution enhancement in scanning electron microscopy using deep learning
• Partial Scanning Transmission Electron Microscopy with Deep Learning
• Adaptive Learning Rate Clipping Stabilizes Learning
• Warwick Electron Microscopy Datasets

Cited by in corpus (11)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Deep learning in nano-photonics: inverse design and beyond
• Review: Deep Learning in Electron Microscopy
• Physics discovery in nanoplasmonic systems via autonomous experiments in Scanning Transmission Electron Microscopy
• Single-atom level determination of 3-dimensional surface atomic structure via neural network-assisted atomic electron tomography
• Partial Scanning Transmission Electron Microscopy with Deep Learning
• Adaptive Learning Rate Clipping Stabilizes Learning
• AtomVision: A machine vision library for atomistic images
• Warwick Electron Microscopy Datasets
• SIM-STEM Lab: Incorporating Compressed Sensing Theory for Fast STEM Simulation
• Advancing Time-Resolved Spectroscopies with Custom Scanning Units and Event-Based Electron Detection