GAN learning complex fluvial facies distribution from process-based modelling

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This work shows the advantages and disadvantages of modelling complex geological models using generative adversarial networks (GAN). A process-based model, FLUMY, is used to create the training dataset. Compared to previous work in this area, this dataset contains varied geo-body geometry, asymmetrical channel sinuosity and irregular meander morphology. In short, this training dataset is closer to the real complexity of fluvial reservoir. The results indicate our GAN can capture complex multi-facies distribution, their relationships, and facies geometry. However, the GAN generated realizations contain many geologically unrealistic features. In this paper, we list two types of unrealistic features, named 'mislabelling' and 'incorrect channel-levee relationship'. Two proposed methods are proved that they can reduce the amount of the unrealistic features. Embedding one-hot encoder in GAN can cure the 'mislabelling' issue. Multi-discriminator strategy is helpful to assist GAN to learn spatial relationships among different facies better.

Original languageEnglish
Title of host publication82nd EAGE Conference and Exhibition 2021
PublisherEAGE Publishing BV
Pages5268-5272
Number of pages5
Volume7
ISBN (Electronic)9781713841449
Publication statusPublished - 2021
Event82nd EAGE Conference and Exhibition 2021 - Amsterdam, Virtual, Netherlands
Duration: 18 Oct 202121 Oct 2021

Conference

Conference82nd EAGE Conference and Exhibition 2021
Abbreviated titleEAGE 2021
Country/TerritoryNetherlands
CityAmsterdam, Virtual
Period18/10/2121/10/21

ASJC Scopus subject areas

  • Geochemistry and Petrology
  • Geology
  • Geophysics
  • Geotechnical Engineering and Engineering Geology

Fingerprint

Dive into the research topics of 'GAN learning complex fluvial facies distribution from process-based modelling'. Together they form a unique fingerprint.

Cite this