Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Vertically Stacked Indium Gallium Zinc Oxide-Based Three-Dimensional Integrated Circuits.

ACS nano·2026

Same author

Micro-Expression Recognition Based on Dual-Stream Motion-Anchored Cross-Fusion Network.

Sensors (Basel, Switzerland)·2026

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

Association between hair loss and cardiometabolic diseases in Chinese adults: a cross-sectional analysis in Tianning Cohort.

Journal of epidemiology·2026

Same author

Atomic-Resolution Mapping of Electric Fields and Strain across Single-Crystalline/Amorphous Interfaces.

Nano letters·2026

Same journal

Correction to "Ultrasonication-Triggered Ubiquitous Assembly of Magnetic Janus Amphiphilic Nanoparticles in Cancer Theranostic Applications".

Nano letters·2026

Same journal

Tunable Proximity Valley Splitting Via Interfacial Exchange Pinning in WSe<sub>2</sub>-CrBr<sub>3</sub>-CrPS<sub>4</sub> Heterostructures.

Nano letters·2026

Same journal

Nanoscale Organization of Membrane Tension during Neutrophil Extracellular Trap Formation Revealed by Fluorescence Lifetime Imaging.

Nano letters·2026

Same journal

Pressure-Tuned Plasmonic Propagation on a Silver Nanowire.

Nano letters·2026

Same journal

Intrinsic Superconducting Gap in Bilayer KCa<sub>2</sub>Fe<sub>4</sub>As<sub>4</sub>F<sub>2</sub> and Decoupled Monolayer FeAs.

Nano letters·2026

Same journal

Programmable Hydrogen-Assisted Chemical Vapor Deposition Growth and Bipolar Transport in Two-Dimensional MoO<sub>2</sub> Nanoflakes.

Nano letters·2026

查看所有相关文章

Search research articles

相关实验视频

Updated: Jun 17, 2025

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

基于单一图像的深度学习,用于精确的原子缺陷识别.

Kangshu Li¹, Xiaocang Han¹, Yuan Meng¹

¹School of Materials Science and Engineering, Peking University, Beijing 100871, China.

|August 6, 2024

概括

此摘要是机器生成的。

这项研究引入了一种新的深度学习方法,用于使用单扫描传输电子显微镜 (STEM) 图像分析材料缺陷. 它显著减少了对材料科学缺陷检测的广泛数据和人类偏差的需求.

关键词:

深度学习是一种深度学习.发现缺陷检测检测缺陷检测扫描传输电子显微镜扫描传输电子显微镜过渡金属二甲基二甲基化物

更多相关视频

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

相关实验视频

Last Updated: Jun 17, 2025

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

High-Speed Ultraviolet Photoacoustic Microscopy for Histological Imaging with Virtual-Staining assisted by Deep Learning

Published on: April 28, 2022

科学领域:

材料科学材料科学材料科学
凝聚物质物理学凝聚物质物理学
计算材料科学科学计算材料科学

背景情况:

缺陷工程对于定制材料特性至关重要.
传统的STEM缺陷分析方法容易产生噪音和偏差.
检测缺陷的深度学习 (DL) 需要大量的标记数据集,这是一项挑战.

研究的目的:

开发一种基于DL的方法来检测STEM图像中的缺陷,从而最大限度地减少数据需求和噪声敏感性.
在二维 (2D) 材料中可视化原子缺陷和剂.

主要方法:

使用CycleGAN和U-Nets,是一种深度学习模型.
使用最少的数据训练模型,特别是单元细胞级图像.
应用了分析单层MoS₂的方法.

主要成果:

在单层MoS₂中成功可视化了原子缺陷和氧剂.
用单个实验性STEM图像展示了一种有效的方法.
展示了模型克服图像噪声和降低注释成本的能力.

结论:

拟议的方法可以在最小的训练数据下有效检测缺陷.
这种方法可以扩展到各种2D材料.
提供了一种强大的新方法来利用材料科学中的DL进行缺陷分析.