Deep Unsupervised 4D Seismic 3D Time-Shift Estimation with Convolutional Neural Networks

This is a Preprint and has not been peer reviewed.

Downloads

Download Preprint

Authors

Jesper Sören Dramsch , Anders Nymark Christensen, Colin MacBeth, Mikael Lüthje

Abstract

We present a novel 3D warping technique for the estimation of 4D seismic time-shift. This unsupervised method provides a diffeomorphic 3D time shift field that includes uncertainties, therefore it does not need prior time-shift data to be trained. This results in a widely applicable method in time-lapse seismic data analysis. We explore the generalization of the method to unseen data both in the same geological setting and in a different field, where the generalization error stays constant and within an acceptable range across test cases. We further explore upsampling of the warp field from a smaller network to decrease computational cost and see some deterioration of the warp field quality as a result.

DOI

https://doi.org/10.31223/osf.io/82bnj

Subjects

Applied Statistics, Earth Sciences, Geophysics and Seismology, Physical Sciences and Mathematics, Statistics and Probability

Keywords

machine learning, Deep learning, Geophysics, Unsupervised learning, seismic, time-lapse, Neural Network, 3D time shifts, 4D, 4D seismic, image registration, image warping, registration, time-lapse seismic, time shifts, unsupervised, warping

Dates

Published: 2019-10-31 04:04

Last Updated: 2020-08-14 20:26

Older Versions
License

CC BY Attribution 4.0 International

Add a Comment

You must log in to post a comment.


Comments

There are no comments or no comments have been made public for this article.