Seismic inversion with deep learning

A proposal for litho-type classification

Journal Article (2021)
Author(s)

S. Pintea (TU Delft - Pattern Recognition and Bioinformatics)

S. Sharma (TU Delft - ImPhys/Computational Imaging)

Femke Vossepoel (TU Delft - Reservoir Engineering)

Jan van Gemert (TU Delft - Pattern Recognition and Bioinformatics)

Marco Loog (TU Delft - Pattern Recognition and Bioinformatics)

Eric Verschuur (TU Delft - ImPhys/Computational Imaging)

Research Group
Pattern Recognition and Bioinformatics
Copyright
© 2021 S. Pintea, S. Sharma, F.C. Vossepoel, J.C. van Gemert, M. Loog, D.J. Verschuur
DOI related publication
https://doi.org/10.1007/s10596-021-10118-2
More Info
expand_more
Publication Year
2021
Language
English
Copyright
© 2021 S. Pintea, S. Sharma, F.C. Vossepoel, J.C. van Gemert, M. Loog, D.J. Verschuur
Research Group
Pattern Recognition and Bioinformatics
Issue number
2
Volume number
26 (2022)
Pages (from-to)
351-364
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

This article investigates bypassing the inversion steps involved in a standard litho-type classification pipeline and performing the litho-type classification directly from imaged seismic data. We consider a set of deep learning methods that map the seismic data directly into litho-type classes, trained on two variants of synthetic seismic data: (i) one in which we image the seismic data using a local Radon transform to obtain angle gathers, (ii) and another in which we start from the subsurface-offset gathers, based on correlations over the seismic data. Our results indicate that this single-step approach provides a faster alternative to the established pipeline while being convincingly accurate. We observe that adding the background model as input to the deep network optimization is essential in correctly categorizing litho-types. Also, starting from the angle gathers obtained by imaging in the Radon domain is more informative than using the subsurface offset gathers as input.