Multi-scale reconstruction of porous media from low-resolution core images using conditional generative adversarial networks

Multi-scale reconstruction of porous media from low-resolution core images using conditional generative adversarial networks Full article

Journal

Journal of Natural Gas Science and Engineering
ISSN: 1875-5100

Output data

Year: 2022, Volume: 99, Article number : 104411, Pages count : DOI: 10.1016/j.jngse.2022.104411

Tags

Deep learning; Digital rock; Generative adversarial network; Multi-scale; Porous media reconstruction

Authors

Yang Y. ^1,2 , Liu F. ^1,2 , Yao J. ^1,2 , Iglauer S. ³ , Sajjadi M. ⁴ , Zhang K. ² , Sun H. ^1,2 , Zhang L. ^1,2 , Zhong J. ^1,2 , Lisitsa V. ⁵

Affiliations

1	Key Laboratory of Unconventional Oil & Gas Development (China University of Petroleum (East China)), Ministry of Education, Qingdao, 266580, China
2	Research Center of Multiphase Flow in Porous Media, School of Petroleum Engineering, China University of Petroleum (East China), Qingdao, 266580, China
3	Petroleum Engineering Department, Edith Cowan University, Joondalup, WA 6027, Australia
4	Institute of Petroleum Engineering, College of Engineering, University of Tehran, Tehran, 1439956191, Iran
5	Institute of Mathematics SB RAS, Novosibirsk, 630090, Russian Federation

Funding (1)

Министерство науки и высшего образования РФ
Mathematical Center in Akademgorodok

075-15-2019-1613, 075-15-2022-281

Various rocks such as carbonate, coal or shale contain both micro- and macro-pores. To accurately predict the fluid flow and mechanical properties of these porous media, a multi-scale characterization of the pore space is of key importance. Hybrid superposition methods perform well in such multi-scale reconstructions, however, input images with two resolutions (high and low) and different reconstruction methods are required. In addition, the superposition algorithms are complex and human factors can introduce serious bias. Here we thus propose an effective approach based on conditional generative adversarial network (cGAN) for efficient and reliable multi-scale digital rock reconstruction based only on low-resolution core images. High-resolution core images with narrow field of view (FOV) and their corresponding large structure images were thus used to train the cGAN model. The model was validated with real sample images, and the model-generated images exhibited great agreement with the real pore structures. We also demonstrate that the proposed method can generate images independent of the structure size to some extent. This work provides an advanced image-generating model based on deep learning, and therefore aids in better and wider pore-scale characterization and process modeling, to improve understanding of subsurface science and engineering processes. © 2022 Elsevier B.V.

Yang Y. , Liu F. , Yao J. , Iglauer S. , Sajjadi M. , Zhang K. , Sun H. , Zhang L. , Zhong J. , Lisitsa V.
Multi-scale reconstruction of porous media from low-resolution core images using conditional generative adversarial networks
Journal of Natural Gas Science and Engineering. 2022. V.99. 104411 . DOI: 10.1016/j.jngse.2022.104411 WOS Scopus РИНЦ OpenAlex

Web of science:	WOS:000788705600005
Scopus:	2-s2.0-85122629986
Elibrary:	47910399
OpenAlex:	W4205768804

DB	Citing
Scopus	41
Web of science	32
OpenAlex	46
Elibrary	30