Seismic data interpolation using an anti-over-fitting mixed-scale dense convolutional neural network

Conference Paper (2023)
Author(s)

D. Zhang (TU Delft - Applied Geophysics and Petrophysics)

Eric Eric Verschuur (TU Delft - Applied Geophysics and Petrophysics, TU Delft - ImPhys/Verschuur group)

Research Group
Applied Geophysics and Petrophysics
Copyright
© 2023 D. Zhang, D.J. Verschuur
DOI related publication
https://doi.org/10.3997/2214-4609.2023101026
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 D. Zhang, D.J. Verschuur
Research Group
Applied Geophysics and Petrophysics
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

Seismic data interpolation is a topic well suited for deep learning (DL) applications. Scaling operation-based DL neural networks, e.g., U-Net, have been popular since its booming development in the field of seismic data processing. Although many successful studies using U-Net on seismic data, scientists start to realize the downside of its implementation, i.e., large trainable parameters (normally larger than 1 million), the potential risks of over-fitting, and tedious hyper-parameter selection. Therefore, in this abstract, we introduce a mixed-scale dense convolutional neural network (MS-DCNN) for seismic data interpolation with relatively few trainable parameters to reduce the risk of over-fitting. This MS-DCNN was originally developed for biomedical image processing. In addition, this neural network can be trained with relatively small training set. Via a field data case study, the different behavior of U-Net and MS-DCNN is analyzed and compared for a specific interpolation problem, where 9 consecutive shot records were missing from a 2D line of marine seismic data.

Files

1026.pdf
(pdf | 1.1 Mb)
License info not available