Picture for Gavin Graham

Gavin Graham

Generating unrepresented proportions of geological facies using Generative Adversarial Networks

Add code
Mar 17, 2022
Alhasan Abdellatif, Ahmed H. Elsheikh, Gavin Graham, Daniel Busby, Philippe Berthet

Figure 1 for Generating unrepresented proportions of geological facies using Generative Adversarial Networks
Figure 2 for Generating unrepresented proportions of geological facies using Generative Adversarial Networks
Figure 3 for Generating unrepresented proportions of geological facies using Generative Adversarial Networks
Figure 4 for Generating unrepresented proportions of geological facies using Generative Adversarial Networks

In this work, we investigate the capacity of Generative Adversarial Networks (GANs) in interpolating and extrapolating facies proportions in a geological dataset. The new generated realizations with unrepresented (aka. missing) proportions are assumed to belong to the same original data distribution. Specifically, we design a conditional GANs model that can drive the generated facies toward new proportions not found in the training set. The presented study includes an investigation of various training settings and model architectures. In addition, we devised new conditioning routines for an improved generation of the missing samples. The presented numerical experiments on images of binary and multiple facies showed good geological consistency as well as strong correlation with the target conditions.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon