Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

A novel berberine derivative B12 exhibits superior anti-obesity effects via targeting brown and white adipocyte dynamics.

International journal of obesity (2005)·2026

Same author

Learning Moisture-Induced Damage From Vision: Diffusion Models for Real-Time Monitoring of Additive Manufacturing Processes.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

Injectable Thermal-Protective Hydrogel Enables Curative Tumor Ablation via Chemo-Immunomodulation.

ACS applied materials & interfaces·2026

Same author

Lactate-Driven Restriction of Mitochondrial Permeability Transition Promotes Resistance to Chemo-Immunotherapy by Suppressing Tumor PANoptosis.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

Coded Caching Scheme for Multiaccess Cache-Assisted Partially Connected Linear Network via Multi-Antenna Placement Delivery Array.

Entropy (Basel, Switzerland)·2026

Same author

Surface-Spin-Induced Magnetic Loss Enhancement in Ultralight Electromagnetic Absorbers.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same journal

Flexible Dual-Modal Sensing Transistor Enabled by Deep Learning Decoupling for Independent Light and Temperature Reconstruction.

Nano-micro letters·2026

Same journal

CuS-Bridged MXene-Based Photoresponsive Phase Change Materials Enabling Thermoelectric Cogeneration and Microwave Absorption.

Nano-micro letters·2026

Same journal

NIR and Oxidative Stress-Modulated Intestinal Peristalsis Motion of Tubular Conductive Thermo-Hydrogel Actuator.

Nano-micro letters·2026

Same journal

Droplet-Merging and Dissolution-Induced Intermediate State Strategy Enabled Efficiency > 17.5% for the Printed Organic Solar Cells.

Nano-micro letters·2026

Same journal

Nano-Confined Solar-Thermal Water Purification Boosted by Physical Field Disturbance Coupled with Ultrafast Non-Radical Advanced Oxidation Process.

Nano-micro letters·2026

Same journal

In Situ Probing of Electrochemical Hydrogen Evolution Reaction Intermediates: From Single-Crystal Models to Nano-Catalysts.

Nano-micro letters·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 1, 2025

Fabrication of Gate-tunable Graphene Devices for Scanning Tunneling Microscopy Studies with Coulomb Impurities

Fabrication of Gate-tunable Graphene Devices for Scanning Tunneling Microscopy Studies with Coulomb Impurities

Published on: July 24, 2015

Machine Learning-Based Detection of Graphene Defects with Atomic Precision.

Bowen Zheng¹, Grace X Gu²

¹Department of Mechanical Engineering, University of California, Berkeley, CA, 94720, USA.

Nano-Micro Letters

|June 17, 2021

Summary

This summary is machine-generated.

Machine learning detects graphene defects by analyzing thermal vibrations. This approach offers high accuracy for non-destructive evaluation and accelerates the discovery of new graphene materials.

Keywords:

Defects Graphene Machine learning Molecular dynamics Nanomaterials

More Related Videos

Development and Functionalization of Electrolyte-Gated Graphene Field-Effect Transistor for Biomarker Detection

Development and Functionalization of Electrolyte-Gated Graphene Field-Effect Transistor for Biomarker Detection

Published on: February 1, 2022

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

Related Experiment Videos

Last Updated: Nov 1, 2025

Fabrication of Gate-tunable Graphene Devices for Scanning Tunneling Microscopy Studies with Coulomb Impurities

Fabrication of Gate-tunable Graphene Devices for Scanning Tunneling Microscopy Studies with Coulomb Impurities

Published on: July 24, 2015

Development and Functionalization of Electrolyte-Gated Graphene Field-Effect Transistor for Biomarker Detection

Development and Functionalization of Electrolyte-Gated Graphene Field-Effect Transistor for Biomarker Detection

Published on: February 1, 2022

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

Area of Science:

Materials Science
Condensed Matter Physics
Nanotechnology

Background:

Graphene defects significantly alter its properties and device performance.
Current atomic-resolution defect detection methods are complex and require extensive sample preparation.
Thermal vibration properties implicitly contain defect information, offering an alternative detection pathway.

Purpose of the Study:

To develop a machine learning (ML)-based strategy for detecting graphene defects.
To explore the correlation between thermal vibration features and defect locations.
To establish non-destructive evaluation methods for graphene.

Main Methods:

Utilized machine learning to analyze thermal vibration properties of graphene.
Developed two prediction strategies: atom-based (using atom indices) and domain-based (using domain discretization).
Correlated hidden patterns between thermal vibration data and defect positions.

Main Results:

The atom-based method successfully detected single-atom vacancies.
The domain-based method identified an unknown number of multiple vacancies with atomic precision.
Both ML methods achieved approximately 90% prediction accuracy on test data, showing good extrapolation capabilities.

Conclusions:

The proposed ML approach provides an effective, non-destructive method for graphene defect detection.
This strategy accelerates nanomaterial discovery and evaluation.
The findings demonstrate the potential of data-driven methods in materials science.