English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper presents a methodology and workflow that overcome the limitationsof the conventional Generative Adversarial Networks (GANs) for geologicalfacies modeling. It attempts to improve the training stability and guaranteethe diversity of the generated geology through interpretable latent vectors.The resulting samples are ensured to have the equal probability (or an unbiaseddistribution) as from the training dataset. This is critical when applying GANsto generate unbiased and representative geological models that can be furtherused to facilitate objective uncertainty evaluation and optimal decision-makingin oil field exploration and development.  We proposed and implemented a new variant of GANs called Info-WGAN for thegeological facies modeling that combines Information Maximizing GenerativeAdversarial Network (InfoGAN) with Wasserstein distance and Gradient Penalty(GP) for learning interpretable latent codes as well as generating stable andunbiased distribution from the training data. Different from the original GANdesign, InfoGAN can use the training images with full, partial, or no labels toperform disentanglement of the complex sedimentary types exhibited in thetraining dataset to achieve the variety and diversity of the generated samples.This is accomplished by adding additional categorical variables that providedisentangled semantic representations besides the mere randomized latent vectorused in the original GANs. By such means, a regularization term is used tomaximize the mutual information between such latent categorical codes and thegenerated geological facies in the loss function.  Furthermore, the resulting unbiased sampling by Info-WGAN makes the dataconditioning much easier than the conventional GANs in geological modelingbecause of the variety and diversity as well as the equal probability of theunconditional sampling by the generator.

Generating Geological Facies Models with Fidelity to Diversity and Statistics of Training Images using Improved Generative Adversarial Networks