Image:
Eirik Østmo / Torger Grytå

VI seminar #30 - Mind the Gap: Repurposing Generative Adversarial Networks in Geosciences

The program will be available shortly. Please check back later.

Mind the Gap: Repurposing Generative Adversarial Networks in Geosciences

Dr. Ardiansyah Koeshidayatullah

Ardiansyah Koeshidayatullah, PhD, Assistant Professor
Geosciences Department
College of Petroleum Engineering and Geosciences 
King Fahd University of Petroleum and Minerals
Saudi Arabia

Abstract: The rapid growth of artificial intelligence (AI) technology and its applications in recent years have revolutionized the process of data analytics in many scientific fields, including geosciences. Geosciences has traditionally been a descriptive science and fundamentally relies upon visual recognition and identification of different geological features, from satellite images to subsurface seismic, to study Earth’s history. Geological image data provides the immense potential to apply advanced AI methods, such as deep convolutional neural network to improve and optimize different geological and geophysical characterization workflows. Despite the increasing efforts and interest toward implementing AI in various geosciences tasks, its actual potential remains untapped, and further exploration is required. In geosciences, the prospect of AI application is primarily hindered by the following: (i) limited availability of high-quality labeled datasets and (ii) inherited imbalance dataset distribution. These limitations are compounded by overexploitation of the transfer learning method to mitigate such issues, discarding the explainability of the AI black-box problems. Here, we aim to utilize and repurpose generative adversarial networks to overcome such challenges by providing (i) a way to significantly increase the number of high-quality labelled dataset and (ii) a novel workflow for self-supervised and weakly-supervised image classification and segmentation in geosciences.

In compliance with GDPR consent requirements, presentations given in a Visual Intelligence context maybe recorded with the consent of the speaker. All recordings are edited toremove all faces, names and voices of other participants. Questions and comments by the audience will hence be removed and will not appear in the recording. With the freely given consent from the speaker, recorded presentation may be posted on the Visual Intelligence YouTube channel.

This seminar is open for members of the consortium. If you want to participate as a guest please sign up.

Sign up here