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

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

Nanophthalmos presenting with acute refractory angle-closure glaucoma: acute-phase histopathological evidence and bilateral comparative findings.

BMC ophthalmology·2026
Same author

Efficacy and safety of ozone autohemotherapy for zoster-associated pain: a meta-analysis and trial sequential analysis.

Frontiers in neurology·2026
Same author

Melatonin alleviates mitochondrial damage by regulating SIRT3‑mediated mitochondrial dynamics in granulosa cells under PCOS‑like conditions.

Molecular medicine reports·2026
Same author

Nomogram for Predicting Pancreatic Pseudocyst in Hypertriglyceridemic Acute Pancreatitis: A Retrospective Cohort Study.

Journal of inflammation research·2026
Same author

Retraction: HDAC regulates the diabetic vascular endothelial dysfunction by targeting MnSOD.

Bioscience reports·2026
Same author

Research Trends in Pain Management After Thoracoscopic Surgery (2015-2024): A Bibliometric Analysis.

Pain research & management·2026

相关实验视频

Updated: Jun 21, 2025

Author Spotlight: Advanced Techniques for Characterizing Tissue Mineralization in Bone Regeneration Research
07:29

Author Spotlight: Advanced Techniques for Characterizing Tissue Mineralization in Bone Regeneration Research

Published on: September 27, 2024

710

基于改进的DeepLab V3 Plus神经网络的多通道砂岩薄部分识别.

Jinzhi Zhong1, Yanjun Meng2,3, Zehao Liu4

  • 1School of Resources and Environmental Engineering, Hefei University of Technology, Hefei 230009, China.

ACS omega
|July 8, 2024
PubMed
概括

这项研究引入了一个增强的DeepLab V3 Plus模型,用于识别砂岩薄段中的矿物质. 新的多通道方法提高了识别矿物成分和孔状结构的准确性,以便更好地评估水库.

更多相关视频

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.7K
Localizing Protein in 3D Neural Stem Cell Culture: a Hybrid Visualization Methodology
21:47

Localizing Protein in 3D Neural Stem Cell Culture: a Hybrid Visualization Methodology

Published on: December 19, 2010

12.7K

相关实验视频

Last Updated: Jun 21, 2025

Author Spotlight: Advanced Techniques for Characterizing Tissue Mineralization in Bone Regeneration Research
07:29

Author Spotlight: Advanced Techniques for Characterizing Tissue Mineralization in Bone Regeneration Research

Published on: September 27, 2024

710
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.7K
Localizing Protein in 3D Neural Stem Cell Culture: a Hybrid Visualization Methodology
21:47

Localizing Protein in 3D Neural Stem Cell Culture: a Hybrid Visualization Methodology

Published on: December 19, 2010

12.7K

科学领域:

  • 地质科学是地球科学.
  • 石油地质学 石油地质学
  • 地球科学中的人工智能

背景情况:

  • 狭窄的砂岩气库在沙粒之间的小孔中储存天然气.
  • 准确地描述孔隙结构和矿物成分对于高效的气体提取至关重要.
  • 目前用于砂岩薄截面分析的现有自动化方法的准确性和速度都很低.

研究的目的:

  • 开发一种更准确,更高效的方法来识别砂岩细段中的矿物成分和孔状结构.
  • 通过深度学习增强地质薄段的自动化分析.
  • 通过精确的矿物鉴定,改进水库评估和天然气产量预测.

主要方法:

  • 将交叉偏光 (CPL) 和直角偏光 (XPL) 图像合并为多通道数据.
  • 使用一个增强的DeepLab V3 Plus模型,具有用于语义细分的注意力机制.
  • 训练多个网络,并为矿产识别选择最佳架构和数据集.
  • 计算矿物质大小,用于精确地分类和命名砂岩薄片.

主要成果:

  • 多通道识别方法实现了高识别精度,平均PA为89.8%,平均IOU为81.2%.
  • 与以前的自动识别方法相比,改进后的模型显示出更高的性能.
  • 注意力机制显著提高了语义细分网络的识别准确性.

结论:

  • 新的多通道方法提供了一种更精确的方法来识别砂岩薄片中的矿物成分和孔隙结构.
  • 这种技术对于准确的储量评估和预测石油和天然气产量至关重要.
  • 该方法显示了在识别和分类其他类型的地质薄段中应用的潜力.