Abstract
Linking the pore-scale and reservoir-scale subsurface fluid flow remains an open challenge in areas such as oil recovery and Carbon Capture and Storage (CCS). One of the main factors hindering our knowledge of such a process is the scarcity of physical samples from geological areas of interest. One way to tackle this issue is by creating accurate, digital representations of the available rock samples to perform numerical fluid flow simulations. Recent advancements in Machine Learning and Deep Generative Modeling open up a new promising avenue for generating realistic digital rock samples at low cost. This is particularly the case for Generative Adversarial Networks (GANs) due to their ability to learn complex high-dimensional distributions and produce high-quality samples. The present study introduces a novel Wasserstein GAN with gradient penalty (WGAN-GP) to generate 3D high-quality porous media samples. Moreover, a comprehensive set of evaluation metrics inspired by the geometry and topology of the structure and the fluid flow properties is established to assess the quality of the generative process.
Original language | English (US) |
---|---|
Title of host publication | Second EAGE Subsurface Intelligence Workshop |
Publisher | European Association of Geoscientists & Engineers |
DOIs | |
State | Published - 2022 |
Bibliographical note
KAUST Repository Item: Exported on 2022-11-14Acknowledgements: The authors thank King Abdullah University of Science and Technology (KAUST) for supporting this research. We also thank Prof. Mohamed Elhoseiny and Prof. Shuyu Sun for their insightful comments on Generative Models and fluid flow at the pore scale, respectively. For computing resources, this study used The KAUST Supercomputing Laboratory.