Reconstruction of 3D Shale Digital Rock Based on Generative Adversarial Network

doi:10.11885/j.issn.1674-5086.2021.01.15.02

Abstract

Abstract: The pore structure of shale oil reservoir is complex, and the shale cores are hard to acquire. Accurately characterizing the pore structure of shale reservoir is the key to the study on the fluid seepage law in shale reservoir. Based on the three-dimensional focused ion beam scanning (3D FIB SEM) images of real shale cores, the structure of the original generative adversarial network model is redesigned. At the same time, to ensure that the reconstruction results can fully reflect the pore structure information of the shale core, the size of the training sample is increased, and the model is trained to generate three-dimensional shale digital rock. The porosity of the reconstructed digital rock and the original core are compared, and the pore network model is extracted from the reconstructed digital rock, then the pore structure properties are analyzed. The porosity, pore and throat sizes, connectivity, and coordination relationship of the reconstructed digital rock are highly in agreement with the original cores, which verifies that the generative model can generate high-quality three-dimensional shale digital rock. Finally, several digital rocks are generated, and the mean value and variation range of various pore structure parameters are calculated. It is proved that the generated digital rocks have stable pore space characteristics, and the trained generative model has good stability.

Key words: shale, digital rock, generative adversarial networks, image reconstruction, parameter evaluation

CLC Number:

TE319

YANG Yongfei, LIU Fugui, YAO Jun, SONG Huajun, WANG Min. Reconstruction of 3D Shale Digital Rock Based on Generative Adversarial Network[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2021, 43(5): 73-83.

0
/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: http://journal15.magtechjournal.com/Jwk_xnzk/EN/10.11885/j.issn.1674-5086.2021.01.15.02

http://journal15.magtechjournal.com/Jwk_xnzk/EN/Y2021/V43/I5/73

References

[1] 姚军,孙海,黄朝琴,等. 页岩气藏开发中的关键力学问题[J]. 中国科学,2013,43(12):1527-1547. doi:10.1360/132013-97 YAO Jun, SUN Hai, HUANG Zhaoqin, et al. Key mechanical problems in the development of shale gas reservoirs[J]. Science China, 2013, 43(12):1527-1547. doi:10.1360/132013-97
[2] 杨永飞,刘志辉,姚军,等. 基于叠加数字岩心和孔隙网络模型的页岩基质储层孔隙空间表征方法[J]. 中国科学,2018,48(5):488-498. doi:10.1360/N092017-00076 YANG Yongfei, LIU Zhihui, YAO Jun, et al. Pore space characterization method of shale matrix formation based on superposed digital rock and pore-network model[J]. Science China, 2018, 48(5):488-498. doi:10.1360/N092017-00076
[3] 姚军,赵秀才. 数字岩心及孔隙级渗流模拟理论[M].北京:石油工业出版社,2010. YAO Jun, ZHAO Xiucai. Digital core and pore scale simulation theory[M]. Beijing:Petroleum Industry Press, 2010.
[4] ZHU Linqi, ZHANG Chong, ZHANG Chaomo, et al. Challenges and prospects of digital core-reconstruction research[J]. Geofluids, 2019(2):1-29.
[5] YANG Yongfei, YAO Jun, WANG Chenchen, et al. New pore space characterization method of shale matrix formation by considering organic and inorganic pores[J]. Journal of Natural Gas Science and Engineering, 2015, 27(2):496-503. doi:10.1016/j.jngse.2015.08.017
[6] YAO Jun, WANG Chenchen, YANG Yongfei, et al. The construction of carbonate digital rock with hybrid superposition method[J]. Journal of Petroleum Science and Engineering, 2013, 10(5):263-267. doi:10.1016/j.petrol.2013.10.005
[7] 王晨晨,姚军,杨永飞,等. 碳酸盐岩双孔隙数字岩心结构特征分析[J]. 中国石油大学学报(自然科学版),2013,37(2):71-74. doi:10.3969/j.issn.1673-5005.2013.02.012 WANG Chenchen, YAO Jun, YANG Yongfei, et al. Structure characteristics analysis of carbonate dual pore digital rock[J]. Journal of China University Petroleum, 2013, 37(2):71-74. doi:10.3969/j.issn.1673-5005.2013.02.012
[8] 姚军,孙海,李爱芬,等. 现代油气渗流力学体系及其发展趋势[J]. 科学通报,2018,63(4):425-451. doi:10.1360/N972017-00161 YAO Jun, SUN Hai, LI Aifen, et al. Modern system of multiphase flow in porous media and its development trend[J]. Chinese Science Bulletin, 2018, 63(4):425-451. doi:10.1360/N972017-00161
[9] SUNDARARAGHAVAN V, ZABARAS N. Classification and reconstruction of three-dimensional microstructures using support vector machines[J]. Computational Materials Science, 2005, 32(2):223-239.
[10] LI Xiaolin, ZHANG Yichi, ZHAO He, et al. A transfer learning approach for microstructure reconstruction and structure-property predictions[J]. Scientific Reports, 2018, 8(1):13461. 10.1038/s41598-018-31571-7
[11] WANG Yuzhu, ARNS C H, RAHMAN S S, et al. Porous structure reconstruction using convolutional neural networks[J]. Mathematical Geosciences, 2018, 50(7):781-799. doi:10.1007/s11004-018-9743-0
[12] GOODFELLOW I J, POUGETABADIE J, MIRZA M, et al. Generative adversarial nets[C]. Canada:MIT Press, 2014.
[13] MOSSER L, DUBRULE O, BLUNT M J. Reconstruction of three-dimensional porous media using generative adversarial neural networks[J]. Physical Review E, 2017, 96(4):043309. doi:10.1103/PhysRevE.96.043309
[14] MOSSER L, DUBRULE O, BLUNT M J, et al. Stochastic reconstruction of an olitic limestone by generative adversarial networks[J]. Transport in Porous Media, 2018, 125(1):81-103. doi:10.1007/s11242-018-1039-9
[15] SHAMS R, MASIHI M, BOOZARJOMEHRY R B, et al. Coupled generative adversarial and autoencoder neural networks to reconstruct three dimensional multiscale porous media[J]. Journal of Petroleum Science and Engineering, 2020, 186:15. doi:10.1016/j.petrol.2019.106794
[16] FENG Junxi, HE Xiaohai, TENG Qizhi, et al. Reconstruction of porous media from extremely limited information using conditional generative adversarial networks[J]. Physical Review, 2019, 4(3):1-11. doi:10.1103/PhysRevE.100.033308
[17] CHEN Honggang, HE Xiaohai, TENG Qizhi, et al. Super resolution of real world rock microcomputed tomography images using cycle-consistent generative adversarial networks[J]. Physical Review E, 2020, 101(2):15. doi:10.1103/PhysRevE.101.023305
[18] FOKINA D, MURAVLEVA E, OVCHINNIKOV G, et al. Microstructure synthesis using style-based generative adversarial networks[J]. Physical Review E, 2020, 101(4):13. doi:10.1103/PhysRevE.101.043308
[19] ZHA Wenshu, LI Xingbao, LI Daolun, et al. Shale digital core image generation based on generative adversarial networks[J]. Journal of Energy Resources Technology, 2020, 143(3):1-16. doi:10.1115/1.4048052
[20] ZHA Wenshu, LI Xingbao, XING Yan, et al. Reconstruction of shale image based on wasserstein generative adversarial networks with gradient penalty[J]. Advances in Geo-Energy Research, 2020, 4(1):107-114. doi:10.26804/ager.2020.01.10
[21] 杨永飞,王晨晨,姚军,等. 页岩基质微观孔隙结构分析新方法[J]. 地球科学,2016,41(6):1067-1073. YANG Yongfei, WANG Chenchen, YAO Jun, et al. A new method for microscopic pore structure analysis in shale matrix[J]. Earth Science, 2016,41(6):1067-1073
[22] 姚军,王晨晨,杨永飞,等. 碳酸盐岩双孔隙网络模型的构建方法和微观渗流模拟研究[J]. 中国科学,2013,43(7):896-902. YAO Jun, WANG Chenchen, YANG Yongfei, et al. The construction method and microscopic flow simulation of carbonate dual pore network model[J]. Science China, 2013,43(7):896-902.
[23] ANDREW M. A quantified study of segmentation techniques on geological XRM and FIB-SEM images[J]. Computational Geosciences, 2018, 22(6):1503-1512. doi:10.1007/s10596-018-9768-y
[24] RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. Computer Science, 2015(7):1-16.