Unsupervised deep learning with higher-order total-variation regularization for multidimensional seismic data reconstruction

Thomas André Larsen Greiner, Jan Erik Lie, Odd Kolbjørnsen, Andreas Kjelsrud Evensen, Espen Harris Nilsen, Hao Zhao, Vasily Demyanov, Leiv J. Gelius

Research output: Contribution to journalArticlepeer-review

3 Citations (SciVal)
21 Downloads (Pure)

Abstract

In 3D marine seismic acquisition, the seismic wavefield is not sampled uniformly in the spatial directions. This leads to a seismic wavefield consisting of irregularly and sparsely populated traces with large gaps between consecutive sail-lines especially in the near-offsets. The problem of reconstructing the complete seismic wavefield from a subsampled and incomplete wavefield, is formulated as an underdetermined inverse problem. We investigate unsupervised deep learning based on a convolutional neural network (CNN) for multidimensional wavefield reconstruction of irregularly populated traces defined on a regular grid. The proposed network is based on an encoder-decoder architecture with an overcomplete latent representation, including appropriate regularization penalties to stabilize the solution. We proposed a combination of penalties, which consists of the L2-norm penalty on the network parameters, and a first- and second-order total-variation (TV) penalty on the model. We demonstrate the performance of the proposed method on broad-band synthetic data, and field data represented by constant-offset gathers from a source-over-cable data set from the Barents Sea. In the field data example we compare the results to a full production flow from a contractor company, which is based on a 5D Fourier interpolation approach. In this example, our approach displays improved reconstruction of the wavefield with less noise in the sparse near-offsets compared to the industry approach, which leads to improved structural definition of the near offsets in the migrated sections.

Original languageEnglish
JournalGeophysics
Early online date12 Nov 2021
DOIs
Publication statusE-pub ahead of print - 12 Nov 2021

ASJC Scopus subject areas

  • Geochemistry and Petrology

Fingerprint

Dive into the research topics of 'Unsupervised deep learning with higher-order total-variation regularization for multidimensional seismic data reconstruction'. Together they form a unique fingerprint.

Cite this