Generating unrepresented proportions of geological facies using Generative Adversarial Networks

TL;DR

This paper explores the use of conditional GANs to generate geological facies with unrepresented proportions, enabling interpolation and extrapolation beyond the original dataset.

Contribution

It introduces a novel conditional GAN framework with new conditioning routines for generating missing facies proportions in geological data.

Findings

Generated realizations match geological consistency.

Strong correlation with target facies proportions.

Effective in interpolating and extrapolating missing data.

Abstract

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.