Keywords
hydrocarbon reservoir
neural network
generative adversarial network
porous media
porosity
How to Cite
Abstract
In this study, a convolutional generative adversarial neural network generating 3D images of porous media (rock) was developed. The neural network can be modified to generate porous media with specific properties such as porosity factor, permeability factor, composition and sizes of the grains, channels, and voids.
References
Воробьев К. А., Воробьев А. Е., Тчаро Х. Цифровизация нефтяной промышленности: технология «цифровой» керн. Вестник Евразийской науки. 2018;10(3). Режим доступа: https://esj.today/78nzvn318.html.
Балашов В. А., Свенков Е. Б. Цифровой керн. Моделирование микротечений в поровом пространстве пород-коллекторов. Neftegaz.ru. 2019;7. Режим доступа: https://magazine.neftegaz.ru/articles/tsifrovizatsiya/475125-tsifrovoy-kern-modelirovanie-mikrotecheniy-v-porovom-prostranstve-porod-kollektorov/.
Стулов П. А., Егоров А. А., Гавриленко Т. В. Современные технологии создания модели порового пространства горных пород. Вестник кибернетики. 2019;1:47–54.
Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio. Generative Adversarial Networks. 2014. Режим доступа: https://arxiv.org/abs/1406.2661.
Hui J. GAN – What is Generative Adversarial Networks GAN? Режим доступа: https://medium.com/@jonathan_hui/gan-whats-generative-adversarial-networks-and-its-application-f39ed278ef09.
Alec Radford, Luke Metz, Soumith Chintala. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. 2015. Режим доступа: https://arxiv.org/abs/1511.06434.
Martin Arjovsky, Soumith Chintala, Léon Bottou. Wasserstein GAN. 2017. Режим доступа: https://arxiv.org/abs/1701.07875.
Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, Aaron Courville. Improved Training of Wasserstein GANs. 2017. Режим доступа: https://arxiv.org/abs/1704.00028.
Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen. Progressive Growing of GANs for Improved Quality, Stability, and Variation. 2017. Режим доступа: https://arxiv.org/abs/1710.10196.
Mehdi Mirza, Simon Osindero. Conditional Generative Adversarial Nets. 2014. Режим доступа: https://arxiv.org/abs/1411.1784.
Berea Sandstone Extraction / Imperial College London. Режим доступа: https://www.imperial.ac.uk/earth-science/research/research-groups/perm/research/pore-scale-modelling/micro-ct-images-and-networks/berea-sandstone/.
Lukas Mosser, Olivier Dubrule, Martin J. Blunt. Reconstruction of Three-Dimensional Porous Media Using Generative Adversarial Neural Networks. 2017. Режим доступа: https://arxiv.org/pdf/1704.03225.pdf.