Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Super-resolution Fluorescence Microscopy01:37

Super-resolution Fluorescence Microscopy

6.8K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
6.8K
Electron Microscope Tomography and Single-particle Reconstruction01:07

Electron Microscope Tomography and Single-particle Reconstruction

2.3K
Transmission electron microscopy (TEM) can be used to determine the 3D structure of biological samples with the help of techniques such as electron microscope tomography and single-particle reconstruction. While single-particle reconstruction can examine macromolecules and macromolecular complexes in vitro conditions only, tomography permits the study of cell components or small cells in vivo.
Electron Tomography
Electron tomography can be performed either in TEM or STEM (scanning transmission...
2.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Implanting Atomically Dispersed Fe and Mo Sites into 3D Scaffolds: A Scalable Route to Bifunctional Water Splitting Electrocatalysts.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Subsurface Vacancy Engineering Enables Atomically Clean and Oxidation-Resistant Copper Interfaces for Anode-Free Lithium Metal Batteries.

ACS nano·2026
Same author

Observation of Kondo cloud-coupling in a mirror-symmetric carbon nanotube array-molybdenum structure.

Nature communications·2026
Same author

Artificial Intelligence for Materials Science: Transforming Research Paradigms.

Chemical reviews·2026
Same author

Carbon Nanotube-Aramid Fiber Enabled Dielectric Dispersion in Paper Composites for Ultrabroadband Lightweight Absorbers.

Nano letters·2026
Same author

Knittable, thermally insulating, and sustainable aerogel fibers enabled by ion-mediated hierarchical assembly.

Nature communications·2026

Related Experiment Video

Updated: May 26, 2025

Author Spotlight: Enhancing CryoEM Sample Preparation Using Graphene Monolayer on Microscopy Grids
07:57

Author Spotlight: Enhancing CryoEM Sample Preparation Using Graphene Monolayer on Microscopy Grids

Published on: November 10, 2023

1.7K

Exploring Structure Diversity in Atomic Resolution Microscopy With Graph.

Zheng Luo1, Ming Feng2,3, Zijian Gao2

  • 1College of Aerospace Science and Engineering, Department of Materials Science and Engineering, Hunan Key Laboratory of Mechanism and Technology of Quantum Information, National University of Defense Technology, Changsha, 410000, China.

Advanced Materials (Deerfield Beach, Fla.)
|February 24, 2025
PubMed
Summary
This summary is machine-generated.

A new equivariant graph neural network (EGNN) framework analyzes atomic structures more efficiently than traditional deep learning models. This approach enhances robustness and reduces computational parameters for diverse atomic configurations.

Keywords:
atomic structuresdefectsgraph neural networkmachine learningtransmission electron microscopy

More Related Videos

Graphene Enclosure of Chemically Fixed Mammalian Cells for Liquid-Phase Electron Microscopy
10:12

Graphene Enclosure of Chemically Fixed Mammalian Cells for Liquid-Phase Electron Microscopy

Published on: September 21, 2020

7.1K
Application of High-speed Super-resolution SPEED Microscopy in Live Primary Cilium
07:53

Application of High-speed Super-resolution SPEED Microscopy in Live Primary Cilium

Published on: January 16, 2018

8.3K

Related Experiment Videos

Last Updated: May 26, 2025

Author Spotlight: Enhancing CryoEM Sample Preparation Using Graphene Monolayer on Microscopy Grids
07:57

Author Spotlight: Enhancing CryoEM Sample Preparation Using Graphene Monolayer on Microscopy Grids

Published on: November 10, 2023

1.7K
Graphene Enclosure of Chemically Fixed Mammalian Cells for Liquid-Phase Electron Microscopy
10:12

Graphene Enclosure of Chemically Fixed Mammalian Cells for Liquid-Phase Electron Microscopy

Published on: September 21, 2020

7.1K
Application of High-speed Super-resolution SPEED Microscopy in Live Primary Cilium
07:53

Application of High-speed Super-resolution SPEED Microscopy in Live Primary Cilium

Published on: January 16, 2018

8.3K

Area of Science:

  • Materials Science
  • Artificial Intelligence
  • Computational Chemistry

Background:

  • Deep learning (DL) models excel at analyzing atomic-resolution micrographs but struggle with diverse atomic configurations due to fixed-size image patch limitations.
  • Existing DL methods lack efficiency and flexibility when processing complex atomic structures like vacancies, phases, grain boundaries, and doping.

Purpose of the Study:

  • To develop a novel few-shot learning framework using equivariant graph neural networks (EGNN) for analyzing diverse atomic structures.
  • To improve the robustness and computational efficiency of analyzing atomic-resolution micrographs compared to image-driven DL models.
  • To enable quantitative extraction of atomic-scale structural features and unveil self-assembly dynamics.

Main Methods:

  • Developed a few-shot learning framework based on equivariant graph neural networks (EGNN).
  • Applied the EGNN framework to analyze various atomic structures, including vacancies, phases, grain boundaries, and doping.
  • Integrated EGNN sub-models into a versatile toolkit for processing varied configurations in a task chain.

Main Results:

  • The EGNN framework demonstrated significantly enhanced robustness and reduced computing parameters (by three orders of magnitude) compared to image-driven DL models.
  • Effectively analyzed aggregated vacancy lines with flexible lattice distortion.
  • Enabled quantitative and straightforward extraction of atomic-scale structural features, revealing self-assembly dynamics of vacancy lines under electron beam irradiation.
  • Discovered novel doping configurations with superior electrocatalytic properties for hydrogen evolution reactions.

Conclusions:

  • The EGNN-based framework offers a powerful, fast, accurate, and intelligent tool for exploring atomic structure diversity.
  • This approach overcomes limitations of fixed-size image patch DL models, enabling more flexible and efficient analysis.
  • The study highlights the potential of graph-based deep learning for advancing materials science and discovering new functional materials.