Cargando…
On the generation of realistic synthetic petrographic datasets using a style-based GAN
Deep learning architectures have transformed data analytics in geosciences, complementing traditional approaches to geological problems. Although deep learning applications in geosciences show encouraging signs, their potential remains untapped due to limited data availability and the required in-de...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9334578/ https://www.ncbi.nlm.nih.gov/pubmed/35902601 http://dx.doi.org/10.1038/s41598-022-16034-4 |
_version_ | 1784759132811689984 |
---|---|
author | Ferreira, Ivan Ochoa, Luis Koeshidayatullah, Ardiansyah |
author_facet | Ferreira, Ivan Ochoa, Luis Koeshidayatullah, Ardiansyah |
author_sort | Ferreira, Ivan |
collection | PubMed |
description | Deep learning architectures have transformed data analytics in geosciences, complementing traditional approaches to geological problems. Although deep learning applications in geosciences show encouraging signs, their potential remains untapped due to limited data availability and the required in-depth knowledge to provide a high-quality labeled dataset. We approached these issues by developing a novel style-based deep generative adversarial network (GAN) model, PetroGAN, to create the first realistic synthetic petrographic datasets across different rock types. PetroGAN adopts the architecture of StyleGAN2 with adaptive discriminator augmentation (ADA) to allow robust replication of statistical and esthetical characteristics and improve the internal variance of petrographic data. In this study, the training dataset consists of > 10,000 thin section images both under plane- and cross-polarized lights. Here, using our proposed novel approach, the model reached a state-of-the-art Fréchet Inception Distance (FID) score of 12.49 for petrographic images. We further observed that the FID values vary with lithology type and image resolution. The generated images were validated through a survey where the participants have various backgrounds and level of expertise in geosciences. The survey established that even a subject matter expert observed the generated images were indistinguishable from real images. This study highlights that GANs are a powerful method for generating realistic synthetic data in geosciences. Moreover, they are a future tool for image self-labeling, reducing the effort in producing big, high-quality labeled geoscience datasets. Furthermore, our study shows that PetroGAN can be applied to other geoscience datasets, opening new research horizons in the application of deep learning to various fields in geosciences, particularly with the presence of limited datasets. |
format | Online Article Text |
id | pubmed-9334578 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Nature Publishing Group UK |
record_format | MEDLINE/PubMed |
spelling | pubmed-93345782022-07-30 On the generation of realistic synthetic petrographic datasets using a style-based GAN Ferreira, Ivan Ochoa, Luis Koeshidayatullah, Ardiansyah Sci Rep Article Deep learning architectures have transformed data analytics in geosciences, complementing traditional approaches to geological problems. Although deep learning applications in geosciences show encouraging signs, their potential remains untapped due to limited data availability and the required in-depth knowledge to provide a high-quality labeled dataset. We approached these issues by developing a novel style-based deep generative adversarial network (GAN) model, PetroGAN, to create the first realistic synthetic petrographic datasets across different rock types. PetroGAN adopts the architecture of StyleGAN2 with adaptive discriminator augmentation (ADA) to allow robust replication of statistical and esthetical characteristics and improve the internal variance of petrographic data. In this study, the training dataset consists of > 10,000 thin section images both under plane- and cross-polarized lights. Here, using our proposed novel approach, the model reached a state-of-the-art Fréchet Inception Distance (FID) score of 12.49 for petrographic images. We further observed that the FID values vary with lithology type and image resolution. The generated images were validated through a survey where the participants have various backgrounds and level of expertise in geosciences. The survey established that even a subject matter expert observed the generated images were indistinguishable from real images. This study highlights that GANs are a powerful method for generating realistic synthetic data in geosciences. Moreover, they are a future tool for image self-labeling, reducing the effort in producing big, high-quality labeled geoscience datasets. Furthermore, our study shows that PetroGAN can be applied to other geoscience datasets, opening new research horizons in the application of deep learning to various fields in geosciences, particularly with the presence of limited datasets. Nature Publishing Group UK 2022-07-27 /pmc/articles/PMC9334578/ /pubmed/35902601 http://dx.doi.org/10.1038/s41598-022-16034-4 Text en © The Author(s) 2022 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . |
spellingShingle | Article Ferreira, Ivan Ochoa, Luis Koeshidayatullah, Ardiansyah On the generation of realistic synthetic petrographic datasets using a style-based GAN |
title | On the generation of realistic synthetic petrographic datasets using a style-based GAN |
title_full | On the generation of realistic synthetic petrographic datasets using a style-based GAN |
title_fullStr | On the generation of realistic synthetic petrographic datasets using a style-based GAN |
title_full_unstemmed | On the generation of realistic synthetic petrographic datasets using a style-based GAN |
title_short | On the generation of realistic synthetic petrographic datasets using a style-based GAN |
title_sort | on the generation of realistic synthetic petrographic datasets using a style-based gan |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9334578/ https://www.ncbi.nlm.nih.gov/pubmed/35902601 http://dx.doi.org/10.1038/s41598-022-16034-4 |
work_keys_str_mv | AT ferreiraivan onthegenerationofrealisticsyntheticpetrographicdatasetsusingastylebasedgan AT ochoaluis onthegenerationofrealisticsyntheticpetrographicdatasetsusingastylebasedgan AT koeshidayatullahardiansyah onthegenerationofrealisticsyntheticpetrographicdatasetsusingastylebasedgan |