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

Deep learning architectures have enriched data analytics in the geosciences,complementing traditional approaches to geological problems. Although deeplearning applications in geosciences show encouraging signs, the actualpotential remains untapped. This is primarily because geological datasets,particularly petrography, are limited, time-consuming, and expensive to obtain,requiring in-depth knowledge to provide a high-quality labeled dataset. Weapproached these issues by developing a novel deep learning framework based ongenerative adversarial networks (GANs) to create the first realistic syntheticpetrographic dataset. The StyleGAN2 architecture is selected to allow robustreplication of statistical and esthetical characteristics, and improving theinternal variance of petrographic data. The training dataset consists of 10070images of rock thin sections both in plane- and cross-polarized light. Thealgorithm trained for 264 GPU hours and reached a state-of-the-art Fr\'echetInception Distance (FID) score of 12.49 for petrographic images. We furtherobserved the FID values vary with lithology type and image resolution. Oursurvey established that subject matter experts found the generated images wereindistinguishable from real images. This study highlights that GANs are apowerful method for generating realistic synthetic data, experimenting with thelatent space, and as a future tool for self-labelling, reducing the effort ofcreating geological datasets.

PetroGAN: A novel GAN-based approach to generate realistic, label-free petrographic datasets