Saved in:
Bibliographic Details
Main Authors: Lasscock, Ben, Sansal, Altay, Valenciano, Alejandro
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.13593
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909143709777920
author Lasscock, Ben
Sansal, Altay
Valenciano, Alejandro
author_facet Lasscock, Ben
Sansal, Altay
Valenciano, Alejandro
contents This article presents a self-supervised generative AI approach to seismic data processing and interpretation using a Masked AutoEncoder (MAE) with a Vision Transformer (ViT) backbone. We modified the MAE-ViT architecture to process 3D seismic mini-cubes to analyze post-stack seismic data. The MAE model can semantically categorize seismic features, demonstrated through t-SNE visualization, much like large language models (LLMs) understand text. After we fine-tune the model, its ability to interpolate seismic volumes in 3D showcases a downstream application. The study's use of an open-source dataset from the "Onward - Patch the Planet" competition ensures transparency and reproducibility of the results. The findings are significant as they represent a step towards utilizing state-of-the-art technology for seismic processing and interpretation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2403_13593
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Encoding the Subsurface in 3D with Seismic
Lasscock, Ben
Sansal, Altay
Valenciano, Alejandro
Geophysics
This article presents a self-supervised generative AI approach to seismic data processing and interpretation using a Masked AutoEncoder (MAE) with a Vision Transformer (ViT) backbone. We modified the MAE-ViT architecture to process 3D seismic mini-cubes to analyze post-stack seismic data. The MAE model can semantically categorize seismic features, demonstrated through t-SNE visualization, much like large language models (LLMs) understand text. After we fine-tune the model, its ability to interpolate seismic volumes in 3D showcases a downstream application. The study's use of an open-source dataset from the "Onward - Patch the Planet" competition ensures transparency and reproducibility of the results. The findings are significant as they represent a step towards utilizing state-of-the-art technology for seismic processing and interpretation tasks.
title Encoding the Subsurface in 3D with Seismic
topic Geophysics
url https://arxiv.org/abs/2403.13593