Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Electron Microscope Tomography and Single-particle Reconstruction01:07

Electron Microscope Tomography and Single-particle Reconstruction

2.4K
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...
2.4K

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

Spatial-adaptive active learning identifies ultra-durable and highly active catalysts for acidic oxygen evolution reaction.

Science bulletin·2026
Same author

XQueryer: an intelligent crystal structure identifier for powder X-ray diffraction.

National science review·2025
Same author

First-Order Phase Transformation in Highly Concentrated Electrolyte for High-Rate and Long-Cycle Aqueous Zn-Ion Battery.

Angewandte Chemie (International ed. in English)·2025
Same author

Ferromagnetic Surface Segregation via Stress-Concentration Coupling Boosts the Oxygen Evolution Reaction in RuO<sub>2</sub>.

ACS nano·2025
Same author

Grain Boundary Oxygen Improving the Acidic Oxygen Evolution Reaction of Zn-RuO<sub>2</sub>@ZnO.

Journal of the American Chemical Society·2025
Same author

Machine Learning-Engineered Nanozyme System for Synergistic Anti-Tumor Ferroptosis/Apoptosis Therapy.

Small (Weinheim an der Bergstrasse, Germany)·2024

相关实验视频

Updated: Jun 11, 2025

Using Tomoauto: A Protocol for High-throughput Automated Cryo-electron Tomography
11:33

Using Tomoauto: A Protocol for High-throughput Automated Cryo-electron Tomography

Published on: January 30, 2016

10.9K

机器学习辅助的晶体学重建来自原子探头断层图像的图像.

Jie-Ming Pu1, Shuai Chen1,2, Tong-Yi Zhang1,2,3

  • 1Materials Genome Institute, Shanghai University, Shanghai 200444, People's Republic of China.

Journal of physics. Condensed matter : an Institute of Physics journal
|September 30, 2024
PubMed
概括

这项研究引入了一种新的机器学习方法,使用深度学习模型从原子探头断层扫描 (APT) 数据中重建晶体信息,显著改善纳米级材料分析.

关键词:
原子探头断层扫描 (tomography) 是一种原子探头断层扫描.卷积神经网络是一种卷积神经网络.高通量模拟的高通量模拟机器学习是机器学习.变量自动编码器变量自动编码器变压器的愿景 变压器的愿景

更多相关视频

Picometer-Precision Atomic Position Tracking through Electron Microscopy
15:04

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

7.3K
Cryo-Electron Tomography Remote Data Collection and Subtomogram Averaging
08:55

Cryo-Electron Tomography Remote Data Collection and Subtomogram Averaging

Published on: July 12, 2022

4.8K

相关实验视频

Last Updated: Jun 11, 2025

Using Tomoauto: A Protocol for High-throughput Automated Cryo-electron Tomography
11:33

Using Tomoauto: A Protocol for High-throughput Automated Cryo-electron Tomography

Published on: January 30, 2016

10.9K
Picometer-Precision Atomic Position Tracking through Electron Microscopy
15:04

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

7.3K
Cryo-Electron Tomography Remote Data Collection and Subtomogram Averaging
08:55

Cryo-Electron Tomography Remote Data Collection and Subtomogram Averaging

Published on: July 12, 2022

4.8K

科学领域:

  • 材料科学 材料科学 材料科学
  • 数据科学数据科学数据科学
  • 晶体学 晶体学是指结晶学.

背景情况:

  • 原子探头断层扫描 (APT) 提供3D原子尺度组合分析,但难以准确的晶体学重建.
  • 从APT数据中恢复精确的晶体信息仍然是一个重大挑战,因为该技术固有的局限性.

研究的目的:

  • 开发和验证一种新的计算方法,用于从APT数据中重建晶体信息.
  • 利用深度学习来利用APT对纳米级材料进行增强分析.

主要方法:

  • 一个经过修改的前向模拟过程产生了大量的Al单晶数据集 (100,000张图像).
  • 三种深度学习模型 - - 卷积神经网络 (CNN),视觉转换器 (ViT) 和变化自编码器 (VAE) - - 被训练用于晶体重建.
  • 视觉变压器 (ViT) 模型在恢复晶体方向方面表现出卓越的性能.

主要成果:

  • ViT模型在恢复晶体学定向方面取得了高精度,其中旋转角 φ, ψ 和 θ 的 R2 值分别为 0.93,0.97 和 0.93.
  • 平均百分比误差 (MPE) 在 ψ 角度仅为 0.35%,表明精确的方向恢复.
  • 这项研究验证了深度学习在从APT中提取详细的晶体学数据方面的有效性.

结论:

  • 深度学习模型,特别是ViT,可以有效地从APT数据中恢复晶体信息.
  • 这种方法克服了APT数据分析的先前局限性,使得纳米级材料的表征更加精确.
  • 这些发现为原子探头断层扫描中先进的人工智能应用铺平了道路.