中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 深海科学与工程研究所
  3. 中国科学院深海科学与工程研究所
  4. 研究生部
Generation of pore-space images using improved pyramid Wasserstein

文献类型：期刊论文

作者Zhu, Linqi1,2; Bijeljic, Branko1; Blunt, Martin J.1
刊名ADVANCES IN WATER RESOURCES
出版日期2024-08-01
卷号190页码:9
关键词Pore-space generation Wasserstein generative adversarial networks Feature statistics mixing regularization Upscaling
ISSN号0309-1708
DOI10.1016/j.advwatres.2024.104748
英文摘要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.
WOS关键词POROUS-MEDIA ; RECONSTRUCTION ; SANDSTONES ; NETWORK ; FLOW
资助项目National Natural Science Foundation of China[42106213] ; Hainan Provincial Natural Science Foundation of China[422RC746] ; Hainan Provincial Natural Science Foundation of China[421QN0908] ; National Key Research and Devel-opment Program of China[2021YFC3100601] ; Hainan Province Science and Technology Special Fund, PR China[ZDYF2024SHFZ 147] ; International Postdoctoral Exchange Fellowship Program, PR China
WOS研究方向Water Resources
语种英语
WOS记录号WOS:001333691300001
出版者ELSEVIER SCI LTD
资助机构National Natural Science Foundation of China ; Hainan Provincial Natural Science Foundation of China ; National Key Research and Devel-opment Program of China ; Hainan Province Science and Technology Special Fund, PR China ; International Postdoctoral Exchange Fellowship Program, PR China
源URL[http://ir.idsse.ac.cn/handle/183446/11707]  
专题研究生部
深海科学研究部_深海地球物理与资源研究室
通讯作者Zhu, Linqi
作者单位1.Imperial Coll London, Dept Earth Sci & Engn, London SW7 2BP, England
2.Chinese Acad Sci, Inst Deep Sea Sci & Engn, Key Lab Marine Geophys & Georesource, Sanya 572000, Peoples R China
推荐引用方式
GB/T 7714		 Zhu, Linqi,Bijeljic, Branko,Blunt, Martin J.. Generation of pore-space images using improved pyramid Wasserstein[J]. ADVANCES IN WATER RESOURCES,2024,190:9.
APA Zhu, Linqi,Bijeljic, Branko,&Blunt, Martin J..(2024).Generation of pore-space images using improved pyramid Wasserstein.ADVANCES IN WATER RESOURCES,190,9.
MLA Zhu, Linqi,et al."Generation of pore-space images using improved pyramid Wasserstein".ADVANCES IN WATER RESOURCES 190(2024):9.

入库方式： OAI收割

来源：深海科学与工程研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。