Reconstruction of shale image based on Wasserstein Generative Adversarial Networks with gradient penalty
Abstract view|756|times PDF download|217|times
Abstract
Generative Adversarial Networks (GANs), as most popular artificial intelligence models in the current image generation field, have excellent image generation capabilities. Based on Wasserstein GANs with gradient penalty, this paper proposes a novel digital core reconstruction method. First, a convolutional neural network is used as a generative network to learn the distribution of real shale samples, and then a convolutional neural network is constructed as a discriminative network to distinguish reconstructed shale samples from real ones. Through this confrontation training method, realistic digital core samples of shale can be reconstructed. The paper uses two-point covariance function, Frechet Inception Distance and Kernel Inception Distance, to evaluate the quality of digital core samples of shale reconstructed by GANs. The results show that the covariance function can test the similarity between generated and real shale samples, and that GANs can efficiently reconstruct digital core samples of shale with high-quality. Compared with multiple point statistics, the new method does not require prior inference of the probability distribution of the training data, and directly uses noise vector to generate digital core samples of shale without using constraints of "hard data" in advance. It is easy to produce an unlimited number of new samples. Furthermore, the training time is also shorter, only 4 hours in this paper. Therefore, the new method has some good points compared with current methods.
Cited as: Zha, W., Li, X., Xing, Y., He, L., Li, D. Reconstruction of shale image based on Wasserstein Generative Adversarial Networks with gradient penalty. Advances in Geo-Energy Research, 2020, 4(1): 107-114, doi: 10.26804/ager.2020.01.10
Keywords
Full Text:
PDFReferences
Arjovsk, M., Chintala, S., Bottou, L. Wasserstein GAN. Paper Presented at the International Conference on Machine Learning, Sydney, Australia, 6-11 August, 2017.
Bi ´nkowski, M., Sutherland, D.J., Arbel, M., et al. Demystifying mmd gans. Paper Presented at the International Conference on Machine Learning, Stockholm, Sweden, 10-15 July, 2018.
Bontrager, P., Roy, A., Togelius, J., et al. Deepmasterprints: Generating masterprints for dictionary attacks via latent variable evolution. Paper Presented at the International Conference on BTAS, Los Angeles, USA, 22-25 October, 2018.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al. Generative adversarial nets. Paper Presented at the International Conference on Advances in Neural Information Processing Systems, Montreal, Canada, 8-13 December, 2014.
Gulrajani, I., Ahmed, F., Arjovsky, M., et al. Improved training of Wasserstein GANs. Paper Presented at the International Conference on Advances in Neural Information Processing Systems, Long Beach, USA, 4-9 December, 2017.
Heusel, M., Ramsauer, H., Unterthiner, T., et al. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Paper Presented at the International Conference on Advances in Neural Information Processing Systems, Long Beach, USA, 4-9 December, 2017.
Ji, L., Lin, M., Jiang, W., et al. An improved method for reconstructing the digital core model of heterogeneous porous media. Transp. Porous Media 2018, 121(2): 389-406.
Jiao, Y., Stillinger, F.H., Torquato, S. Modeling heterogeneous materials via two-point correlation functions: II. Algorithmic details and applications. Phys. Rev. E 2008, 77(3): 031135.
Karras, T., Aila, T., Laine, S., et al. Progressive growing of GANs for improved quality, stability, and variation. Paper Presented at the International Conference on Learning Representations, Toulon, France, 24-26 April, 2017.
Li, D., Zhang, L., Wang, J., et al. Composition-Transient analysis in shale-gas reservoirs with consideration of multicomponent adsorption. SPE J. 2016, 21(2): 648-664.
Lin, C., Wu, Y., Ren, L., et al. Review of digital core modeling methods. Progress in Geophysics 2018, 33(2): 679-689.
(in Chinese) Lin, M., Jiang, W., Li, Y., et al. Several questions in the micro-scale flow of shale oil/gas. Bulletin of Mineralogy, Petrology and Geochemistry 2015, 34(1): 18-28. (in Chinese)
Lin, W., Li, X., Yang, Z., et al. Construction of dual pore 3-D digital cores with a hybrid method combined with physical experiment method and numerical reconstruction method. Transp. Porous Media 2017, 120(1): 227-238.
Liu, S., Sang, S., Wang, G., et al. FIB-SEM and X-ray CT characterization of interconnected pores in high-rank coal formed from regional metamorphism. J. Petrol. Sci. Eng. 2017, 148: 21-31.
Mao, X., Li, Q., Xie, H., et al. Least squares generative adversarial networks. Paper Presented at the International Conference on Computer Vision and Pattern Recognition, Hawaii, USA, 21-26 July, 2017.
Mosser, L., Dubrule, O., Blunt, M.J. Reconstruction of three-dimensional porous media using generative adversarial neural networks. Phys. Rev. E 2017, 96(4): 043309.
Okabe, H., Blunt, M.J. Pore space reconstruction of vuggy carbonates using microtomography and multiplepoint statistics. Water Resour. Res. 2007, 43(12): 3-7.
Otsu, N. A Threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 1979, 9(1): 62-66.
Pedregosa, F., Varoquaux, G., Gramfort, A., et al. Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 2011, 12: 2825-2830.
Radford, A., Metz, L., Chintala, S. Unsupervised representation learning with deep convolutional generative adversarial networks. Paper Presented at the International Conference on Learning Representations, San Diego, USA, 7-9 May, 2015.
Scott, G., Wu, K., Zhou, Y. Multi-scale image-based pore space characterisation and pore network generation: Case study of a north sea sandstone reservoir. Transp. Porous Media 2019, 129(3): 855-884.
Tahmasebi, P., Hezarkhani, A., Sahimi, M. Multiple-point geostatistical modeling based on the crosscorrelation functions. Comput. Geosci. 2012. 16(3): 779-797.
Tahmasebi, P., Javadpour, F., Sahimi, M. Three-dimensional stochastic characterization of shale SEM images. Transp. Porous Media 2015, 110(3): 521-531.
Yang, Y., Yao, J., Wang, C., et al. New pore space characterization method of shale matrix formation by considering organic and inorganic pores. J. Nat. Gas Sci. Eng. 2015, 27: 496-503.
Yao, J., Zhao, X., Yi, Y., et al. The current situation and prospect on digital core technology. Petroleum Geology and Recovery Efficiency 2005, 12(6): 52-54. (in Chinese)
Zhang, J., Li, S., Wang, L., et al. A new method for calculating gas saturation of low-resistivity shale gas reservoirs. Nat. Gas Ind. B 2017, 4(5): 346-353.
Zhang, L., Ning, Z., Shi, P. Input-Output approach to control for fuzzy Markov jump systems with time-varying delays and uncertain packet dropout rate. IEEE Trans. Cybernet. 2014, 45(11): 2449-2460.
Zhang, T., Li, D., Lu, D., et al. Research on the reconstruction method of porous media using multiple-point geostatistics. Sci. China Phys. Mechan. Astron. 2010, 53(1): 122-134.
Zuluaga, M.A., Orkisz, M., Dong, P., et al. Bone canalicular network segmentation in 3D Nano-CT images through geodesic voting and image tessellation. Phys. Med. Biol. 2014, 59(9): 2155-2171.
Refbacks
- There are currently no refbacks.
Copyright (c) 2020 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.