基于循环一致对抗网络和少量学习的瓦瑟斯坦距离引导的三维多孔介质重建技术

IF 2.7 3区 工程技术 Q3 ENGINEERING, CHEMICAL Transport in Porous Media Pub Date : 2024-07-02 DOI:10.1007/s11242-024-02099-4
Mingyang Wang, Enzhi Wang, Xiaoli Liu, Congcong Wang
{"title":"基于循环一致对抗网络和少量学习的瓦瑟斯坦距离引导的三维多孔介质重建技术","authors":"Mingyang Wang,&nbsp;Enzhi Wang,&nbsp;Xiaoli Liu,&nbsp;Congcong Wang","doi":"10.1007/s11242-024-02099-4","DOIUrl":null,"url":null,"abstract":"<div><p>Numerical simulation studies of water–rock interaction mechanisms and pore-scale multiphase flow properties often require high computational efficiency and realistic geometries to enable a fast and accurate description of hydrodynamic behavior. In this paper, we have chosen to use deep learning models to achieve these requirements, firstly by using encoder structures to refine the image segmentation of void-solid structures on complex geometries of scanning electron microscopy (SEM) images of porous media through few-shot learning (FSL), not only obtaining an accuracy of 0.97, but also reducing the amount of annotation work. We then focus on pore-scale three-dimensional (3D) structural reconstruction using the unpaired image-to-image translation method, optimizing the cycle-consistent adversarial network (cycle-GAN) model via sliced Wasserstein distance (SWD) to transfer marine sedimentary sandstone features to the initial image, and the geometric stochastic reconstruction problems are transformed into optimization problems. Subsequently, the computational efficiency was improved by a factor of 21 by implementing the lattice Boltzmann simulation method (LBM) accelerated by GPU through compute-unified device architecture (CUDA). The flow field distribution and absolute permeability of the extracted 2D samples and the reconstructed 3D porous media structure were simulated. The results showed that our method could rapidly and accurately reconstruct the 3D structures of a given feature, ensuring statistical equivalence between the 3D reconstructed structures and 2D samples. We solve the problem of extrapolation-based 3D reconstruction of porous media and significantly reduce the time spent on structure extraction and numerical calculations.</p></div>","PeriodicalId":804,"journal":{"name":"Transport in Porous Media","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Sliced Wasserstein Distance-Guided Three-Dimensional Porous Media Reconstruction Based on Cycle-Consistent Adversarial Network and Few-Shot Learning\",\"authors\":\"Mingyang Wang,&nbsp;Enzhi Wang,&nbsp;Xiaoli Liu,&nbsp;Congcong Wang\",\"doi\":\"10.1007/s11242-024-02099-4\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Numerical simulation studies of water–rock interaction mechanisms and pore-scale multiphase flow properties often require high computational efficiency and realistic geometries to enable a fast and accurate description of hydrodynamic behavior. In this paper, we have chosen to use deep learning models to achieve these requirements, firstly by using encoder structures to refine the image segmentation of void-solid structures on complex geometries of scanning electron microscopy (SEM) images of porous media through few-shot learning (FSL), not only obtaining an accuracy of 0.97, but also reducing the amount of annotation work. We then focus on pore-scale three-dimensional (3D) structural reconstruction using the unpaired image-to-image translation method, optimizing the cycle-consistent adversarial network (cycle-GAN) model via sliced Wasserstein distance (SWD) to transfer marine sedimentary sandstone features to the initial image, and the geometric stochastic reconstruction problems are transformed into optimization problems. Subsequently, the computational efficiency was improved by a factor of 21 by implementing the lattice Boltzmann simulation method (LBM) accelerated by GPU through compute-unified device architecture (CUDA). The flow field distribution and absolute permeability of the extracted 2D samples and the reconstructed 3D porous media structure were simulated. The results showed that our method could rapidly and accurately reconstruct the 3D structures of a given feature, ensuring statistical equivalence between the 3D reconstructed structures and 2D samples. We solve the problem of extrapolation-based 3D reconstruction of porous media and significantly reduce the time spent on structure extraction and numerical calculations.</p></div>\",\"PeriodicalId\":804,\"journal\":{\"name\":\"Transport in Porous Media\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2024-07-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Transport in Porous Media\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s11242-024-02099-4\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, CHEMICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transport in Porous Media","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s11242-024-02099-4","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
引用次数: 0

摘要

水-岩相互作用机制和孔隙尺度多相流特性的数值模拟研究通常需要较高的计算效率和逼真的几何形状,以便快速准确地描述流体动力学行为。在本文中,我们选择使用深度学习模型来实现这些要求,首先使用编码器结构,通过少量学习(FSL)对多孔介质扫描电子显微镜(SEM)图像的复杂几何形状上的空-固结构进行图像细分,不仅获得了 0.97 的精度,还减少了标注工作量。然后,我们利用非配对图像到图像平移方法重点研究孔隙尺度的三维(3D)结构重建,通过切片瓦瑟斯坦距离(SWD)优化循环一致性对抗网络(cycle-consistent adversarial network,CAN)模型,将海洋沉积砂岩特征转移到初始图像,并将几何随机重建问题转化为优化问题。随后,通过计算统一设备架构(CUDA)在 GPU 上加速实施晶格玻尔兹曼模拟方法(LBM),计算效率提高了 21 倍。模拟了提取的二维样本和重建的三维多孔介质结构的流场分布和绝对渗透率。结果表明,我们的方法可以快速、准确地重建给定特征的三维结构,并确保三维重建结构与二维样本之间的统计等效性。我们解决了基于外推法的多孔介质三维重建问题,大大缩短了结构提取和数值计算的时间。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

摘要图片

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Sliced Wasserstein Distance-Guided Three-Dimensional Porous Media Reconstruction Based on Cycle-Consistent Adversarial Network and Few-Shot Learning

Numerical simulation studies of water–rock interaction mechanisms and pore-scale multiphase flow properties often require high computational efficiency and realistic geometries to enable a fast and accurate description of hydrodynamic behavior. In this paper, we have chosen to use deep learning models to achieve these requirements, firstly by using encoder structures to refine the image segmentation of void-solid structures on complex geometries of scanning electron microscopy (SEM) images of porous media through few-shot learning (FSL), not only obtaining an accuracy of 0.97, but also reducing the amount of annotation work. We then focus on pore-scale three-dimensional (3D) structural reconstruction using the unpaired image-to-image translation method, optimizing the cycle-consistent adversarial network (cycle-GAN) model via sliced Wasserstein distance (SWD) to transfer marine sedimentary sandstone features to the initial image, and the geometric stochastic reconstruction problems are transformed into optimization problems. Subsequently, the computational efficiency was improved by a factor of 21 by implementing the lattice Boltzmann simulation method (LBM) accelerated by GPU through compute-unified device architecture (CUDA). The flow field distribution and absolute permeability of the extracted 2D samples and the reconstructed 3D porous media structure were simulated. The results showed that our method could rapidly and accurately reconstruct the 3D structures of a given feature, ensuring statistical equivalence between the 3D reconstructed structures and 2D samples. We solve the problem of extrapolation-based 3D reconstruction of porous media and significantly reduce the time spent on structure extraction and numerical calculations.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Transport in Porous Media
Transport in Porous Media 工程技术-工程:化工
CiteScore
5.30
自引率
7.40%
发文量
155
审稿时长
4.2 months
期刊介绍: -Publishes original research on physical, chemical, and biological aspects of transport in porous media- Papers on porous media research may originate in various areas of physics, chemistry, biology, natural or materials science, and engineering (chemical, civil, agricultural, petroleum, environmental, electrical, and mechanical engineering)- Emphasizes theory, (numerical) modelling, laboratory work, and non-routine applications- Publishes work of a fundamental nature, of interest to a wide readership, that provides novel insight into porous media processes- Expanded in 2007 from 12 to 15 issues per year. Transport in Porous Media publishes original research on physical and chemical aspects of transport phenomena in rigid and deformable porous media. These phenomena, occurring in single and multiphase flow in porous domains, can be governed by extensive quantities such as mass of a fluid phase, mass of component of a phase, momentum, or energy. Moreover, porous medium deformations can be induced by the transport phenomena, by chemical and electro-chemical activities such as swelling, or by external loading through forces and displacements. These porous media phenomena may be studied by researchers from various areas of physics, chemistry, biology, natural or materials science, and engineering (chemical, civil, agricultural, petroleum, environmental, electrical, and mechanical engineering).
期刊最新文献
Pore-to-Core Upscaling of Two-Phase Flow in Mixed-Wet Porous Media: Part II-A Dynamic Pore-Network Modeling Approach Pore-to-Core Upscaling of Two-Phase Flow in Mixed-Wet Porous Media: Part I—Seamless Pore-Network Extraction Analysis of Comparative Thermo-Hydraulic Performance of sCO2 and H2O as Heat-Exchange Fluids in Enhanced Geothermal Systems MHD Mixed Convection Flow Over a Permeable Vertical Flat Plate Embedded in a Darcy–Forchheimer Porous Medium Large Scale Voxel-Based FEM Formulation for NMR Relaxation in Porous Media
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1