Generation of pore-space images using improved pyramid Wasserstein generative adversarial networks

IF 4 2区 环境科学与生态学 Q1 WATER RESOURCES Advances in Water Resources Pub Date : 2024-06-11 DOI:10.1016/j.advwatres.2024.104748
Linqi Zhu , Branko Bijeljic , Martin J. Blunt
{"title":"Generation of pore-space images using improved pyramid Wasserstein generative adversarial networks","authors":"Linqi Zhu ,&nbsp;Branko Bijeljic ,&nbsp;Martin J. Blunt","doi":"10.1016/j.advwatres.2024.104748","DOIUrl":null,"url":null,"abstract":"<div><p>High-resolution three-dimensional X-ray microscopy can be used to image the pore space of materials. Machine learning algorithms can generate a statistical ensemble of representative images of arbitrary sizes for rock characterization, modeling, and analysis. However, current methods struggle to capture features at different spatial scales observed in many complex rocks which have a wide range of pore size. We use the Improved Pyramid Wasserstein Generative Adversarial Network (IPWGAN) to automatically reproduce multi-scale features in segmented three-dimensional images of porous materials, enabling the reliable generation of large-scale representations of complex porous media. A Laplacian pyramid generator is introduced, which creates pore-space features across a hierarchy of spatial scales. Feature statistics mixing regularization enhances the discriminator’s ability to distinguish between real and generated images by mixing their feature statistics, thereby indirectly enhancing the generator’s ability to capture and reproduce multi-scale pore-space features, leading to increased diversity and realism in the generated images. The method has been tested on five sandstone and carbonate samples. The generated images, which can be of any size – including cm-scale ten-billion-cell images – demonstrate the power of the approach. These images have two-point correlation functions, porosity, permeability, Euler characteristic, curvature, and specific surface area closer to those of the training datasets than existing machine learning techniques. The generated images accurately capture geometric and flow properties, demonstrating a considerable improvement over previously published studies using generative adversarial networks. For instance, the mean relative error in the calculated absolute permeability between the Berea sandstone images generated by IPWGAN and the corresponding real rock images can be reduced by 79%. The work allows representative models of a wide range of porous media to be generated, offering potential benefits in carbon dioxide sequestration, underground hydrogen storage, and enhanced oil recovery.</p></div>","PeriodicalId":7614,"journal":{"name":"Advances in Water Resources","volume":"190 ","pages":"Article 104748"},"PeriodicalIF":4.0000,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0309170824001350/pdfft?md5=c7bbf71b0b9bbaee3a3cbcf1e89720f6&pid=1-s2.0-S0309170824001350-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in Water Resources","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0309170824001350","RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"WATER RESOURCES","Score":null,"Total":0}
引用次数: 0

Abstract

High-resolution three-dimensional X-ray microscopy can be used to image the pore space of materials. Machine learning algorithms can generate a statistical ensemble of representative images of arbitrary sizes for rock characterization, modeling, and analysis. However, current methods struggle to capture features at different spatial scales observed in many complex rocks which have a wide range of pore size. We use the Improved Pyramid Wasserstein Generative Adversarial Network (IPWGAN) to automatically reproduce multi-scale features in segmented three-dimensional images of porous materials, enabling the reliable generation of large-scale representations of complex porous media. A Laplacian pyramid generator is introduced, which creates pore-space features across a hierarchy of spatial scales. Feature statistics mixing regularization enhances the discriminator’s ability to distinguish between real and generated images by mixing their feature statistics, thereby indirectly enhancing the generator’s ability to capture and reproduce multi-scale pore-space features, leading to increased diversity and realism in the generated images. The method has been tested on five sandstone and carbonate samples. The generated images, which can be of any size – including cm-scale ten-billion-cell images – demonstrate the power of the approach. These images have two-point correlation functions, porosity, permeability, Euler characteristic, curvature, and specific surface area closer to those of the training datasets than existing machine learning techniques. The generated images accurately capture geometric and flow properties, demonstrating a considerable improvement over previously published studies using generative adversarial networks. For instance, the mean relative error in the calculated absolute permeability between the Berea sandstone images generated by IPWGAN and the corresponding real rock images can be reduced by 79%. The work allows representative models of a wide range of porous media to be generated, offering potential benefits in carbon dioxide sequestration, underground hydrogen storage, and enhanced oil recovery.

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
利用改进的金字塔瓦瑟斯坦生成式对抗网络生成异质孔隙空间图像
高分辨率三维 X 射线显微镜可用于对材料的孔隙空间进行成像。机器学习算法可以生成任意尺寸的代表性图像的统计集合,用于岩石表征、建模和分析。然而,目前的方法很难捕捉到在许多复杂岩石中观察到的不同空间尺度的特征,因为这些岩石的孔隙尺寸范围很广。我们使用改进的金字塔瓦瑟斯坦生成对抗网络(IPWGAN)来自动再现多孔材料三维图像中的多尺度特征,从而可靠地生成复杂多孔介质的大尺度图像。该方法引入了拉普拉斯金字塔生成器,可创建跨空间尺度层次的孔隙空间特征。特征统计混合正则化通过混合特征统计增强了判别器区分真实图像和生成图像的能力,从而间接增强了生成器捕捉和再现多尺度孔隙空间特征的能力,从而提高了生成图像的多样性和真实性。该方法已在五个砂岩和碳酸盐岩样本上进行了测试。生成的图像可以是任何尺寸的,包括厘米级的百亿细胞图像,这证明了该方法的强大功能。与现有的机器学习技术相比,这些图像的两点相关函数、孔隙度、渗透率、欧拉特性、曲率和比表面积更接近训练数据集。生成的图像能准确捕捉几何和流动特性,与之前发表的使用生成式对抗网络的研究相比有了很大改进。例如,IPWGAN 生成的贝里亚砂岩图像与相应的真实岩石图像之间计算出的绝对渗透率的平均相对误差可减少 79%。这项工作可以生成多种多孔介质的代表性模型,为二氧化碳封存、地下储氢和提高石油采收率带来潜在的好处。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Advances in Water Resources
Advances in Water Resources 环境科学-水资源
CiteScore
9.40
自引率
6.40%
发文量
171
审稿时长
36 days
期刊介绍: Advances in Water Resources provides a forum for the presentation of fundamental scientific advances in the understanding of water resources systems. The scope of Advances in Water Resources includes any combination of theoretical, computational, and experimental approaches used to advance fundamental understanding of surface or subsurface water resources systems or the interaction of these systems with the atmosphere, geosphere, biosphere, and human societies. Manuscripts involving case studies that do not attempt to reach broader conclusions, research on engineering design, applied hydraulics, or water quality and treatment, as well as applications of existing knowledge that do not advance fundamental understanding of hydrological processes, are not appropriate for Advances in Water Resources. Examples of appropriate topical areas that will be considered include the following: • Surface and subsurface hydrology • Hydrometeorology • Environmental fluid dynamics • Ecohydrology and ecohydrodynamics • Multiphase transport phenomena in porous media • Fluid flow and species transport and reaction processes
期刊最新文献
Study on the effects of non-uniformity of microbial growth on permeability changes in porous media On transient qanat discharge in an unconfined aquifer underlain by a fractured aquifer An extension of the box method discrete fracture model (Box-DFM) to include low-permeable barriers with minimal additional degrees of freedom In search of non-stationary dependence between estuarine river discharge and storm surge based on large-scale climate teleconnections Numerical analysis of solute transport and longitudinal dispersion coefficients in vegetated flow
×
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