Cristin-resultat-ID: 1954978
Sist endret: 2. februar 2022, 15:29
NVI-rapporteringsår: 2021
Resultat
Vitenskapelig artikkel
2021

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

Bidragsytere:
  • Thomas Larsen Greiner
  • Jan Erik Lie
  • Odd Kolbjørnsen
  • Andreas Kjelsrud Evensen
  • Espen Harris Nilsen
  • Hao Zhao
  • mfl.

Tidsskrift

Geophysics
ISSN 0016-8033
e-ISSN 1942-2156
NVI-nivå 2

Om resultatet

Vitenskapelig artikkel
Publiseringsår: 2021
Publisert online: 2021
Trykket: 2022
Volum: 87
Hefte: 2
Sider: 59 - 73
Open Access

Importkilder

Scopus-ID: 2-s2.0-85119475455

Klassifisering

Vitenskapsdisipliner

Petroleumsgeologi og -geofysikk • Statistikk • Anvendt matematikk

Emneord

Inversjonsproblemer • Seismisk inversjon/avbildning • Seismisk prosessering

Beskrivelse Beskrivelse

Tittel

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

Sammendrag

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.

Bidragsytere

Thomas Larsen Greiner

  • Tilknyttet:
    Forfatter
    ved Lundin Norway AS
  • Tilknyttet:
    Forfatter
    ved Institutt for geofag ved Universitetet i Oslo

Jan-Erik Lie

Bidragsyterens navn vises på dette resultatet som Jan Erik Lie
  • Tilknyttet:
    Forfatter
    ved Lundin Norway AS

Odd Kolbjørnsen

  • Tilknyttet:
    Forfatter
    ved Matematisk institutt ved Universitetet i Oslo
  • Tilknyttet:
    Forfatter
    ved Lundin Norway AS

Andreas Kjelsrud Evensen

  • Tilknyttet:
    Forfatter
    ved Lundin Norway AS

Espen Harris Nilsen

  • Tilknyttet:
    Forfatter
    ved Lundin Norway AS
1 - 5 av 8 | Neste | Siste »