A deep learning approach to identify local structures in atomic-resolution transmission electron microscopy images

Abstract

Recording atomic-resolution transmission electron microscopy (TEM) images is becoming increasingly routine. A new bottleneck is then analyzing this information, which often involves time-consuming manual structural identification. We have developed a deep learning-based algorithm for recognition of the local structure in TEM images, which is stable to microscope parameters and noise. The neural network is trained entirely from simulation but is capable of making reliable predictions on experimental images. We apply the method to single sheets of defected graphene, and to metallic nanoparticles on an oxide support.

arXiv commentv2: Typo in author list corrected

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations
• Comparison of optimal performance at 300 keV of three direct electron detectors for use in low dose electron microscopy
• A deep convolutional neural network approach to single-particle recognition in cryo-electron microscopy
• Automated image acquisition for low-dose STEM at atomic resolution
• Progress in structure recovery from low dose exposures: Mixed molecular adsorption, exploitation of symmetry and reconstruction from the minimum signal level

Cited by in corpus (28)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Overview: Computer vision and machine learning for microstructural characterization and analysis
• Deep Learning Enabled Strain Mapping of Single-Atom Defects in 2D Transition Metal Dichalcogenides with Sub-picometer Precision
• Machine learning in nuclear materials research
• Review: Deep Learning in Electron Microscopy
• Machine Learning Pipeline for Segmentation and Defect Identification from High Resolution Transmission Electron Microscopy Data
• Leveraging generative adversarial networks to create realistic scanning transmission electron microscopy images
• A deep learning approach for determining the chiral indices of carbon nanotubes from high-resolution transmission electron microscopy images
• Developing and Evaluating Deep Neural Network-based Denoising for Nanoparticle TEM Images with Ultra-low Signal-to-Noise
• STEM image analysis based on deep learning: identification of vacancy defects and polymorphs of $Mo{S}_2$
• An Automated Scanning Transmission Electron Microscope Guided by Sparse Data Analytics
• On Machine Learning Force Fields for Metallic Nanoparticles
• Semi-supervised machine learning model for analysis of nanowire morphologies from transmission electron microscopy images
• Atomic mechanisms for the Si atom dynamics in graphene: chemical transformations at the edge and in the bulk
• AtomVision: A machine vision library for atomistic images
• Fast improvement of TEM image with low-dose electrons by deep learning
• Reconstructing the exit wave in high-resolution transmission electron microscopy using machine learning
• Auto-resolving the atomic structure at van der Waals interfaces using a generative model
• Creation and Microscopic Origins of Single-Photon Emitters in Transition Metal Dichalcogenides and Hexagonal Boron Nitride
• Understanding Important Features of Deep Learning Models for Transmission Electron Microscopy Image Segmentation
• Defect complexes in CrSBr revealed through electron microscopy and deep learning
• Quantifying Noise Limitations of Neural Network Segmentations in High-Resolution Transmission Electron Microscopy
• Artificial Intelligence-Assisted Workflow for Transmission Electron Microscopy: From Data Analysis Automation to Materials Knowledge Unveiling
• Image Difference Metrics for High-Resolution Electron Microscopy
• Defect contrast with 4D-STEM: Understanding crystalline order with virtual detectors and beam modification
• Machine-learning semi-local density functional theory for many-body lattice models at zero and finite temperature
• $3D$ Crystal Image Analysis based on Fast Synchrosqueezed Transforms
• Deep Learning Segmentation of Complex Features in Atomic-Resolution Phase Contrast Transmission Electron Microscopy Images