Identification and Suppression of Multiple Reflections in Marine Seismic Data with Neural Networks

  • Robert Essenreiter
  • Martin Karrenbach
  • Sven Treitel
Part of the Modern Approaches in Geophysics book series (MAGE, volume 21)


The process of generating multiple reflections in the earth is generally non-linear. We present a technique for identifying and attenuating multiple reflections in seismic data using non-linear filters i.e. multilayer perceptron neural networks. The aim is to separate the multiple wavefield from the primary wavefield and suppress it in order to create a multiple-free seismic section. A neural network is trained with modeled data that are generated from well-log information and then applied to the areas between the boreholes. Input to the neural network is either the seismic trace itself, or a number of selected, representative attributes computed from the seismic trace. The method is demonstrated on synthetic data and is validated by comparing it to the linear Wiener-filter technique.


Seismic Data Multiple Reflection Wiener Filter Deep Reflector Seismic Trace 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Backus, M. M., 1959, Water reverberations–their nature and elimination: Geophysics, XXIV, 233–261.Google Scholar
  2. Berkhout, A. J., and Verschuur, D. J., 1997, Estimation of multiple scattering by iterative inversion, part I: theoretical considerations: Geophysics, 62, 1586–1595.Google Scholar
  3. Berryhill, J. R., and Kim, Y. C., 1986, Deep-water peg legs and multiples: emulation and suppression: Geophysics, 51, 2177–2184.Google Scholar
  4. Calderòn-Macias, C., Sen, M. K., and Stoffa, P. L., 1997, Hopfield neural networks, and mean field annealing for seismic deconvolution and multiple attenuation: Geophysics, 62, 992–1002.Google Scholar
  5. Calderòn-Macias, C., 1997, Artificial neural systems for interpretation and inversion of seismic data: Ph.D. thesis, University of Texas at Austin.Google Scholar
  6. Carrion, P. M., 1986, A layer-stripping technique for suppression of water-bottom multiple reflections: Geophysical Prospecting, 34, 330–342.Google Scholar
  7. Fuchs, K., and Mueller, G., 1971, Computation of synthetic seismograms with the reflectivity method and comparison with observations: Geophys. J. Roy. Astr. Soc., 23.Google Scholar
  8. Helbig, K., and Brouwer, J. H., 1993, Surface multiples as a tool of calibration in shallow avo studies: 55th Mtg. Eur. Assoc. Expl Geophys., Abstracts, Session: A040.Google Scholar
  9. Kneib, G., and Bardan, V., 1997, 3d targeted multiple attenuation: Geophysical Prospecting, 45, 701–714.Google Scholar
  10. Peacock, K. L., and Treitel, S., 1969, Predictive deconvolution: theory and practice: Geophysics, 34, 155–169.Google Scholar
  11. Riedmiller, M., and Braun, H., 1993, A direct adaptive method for faster backpropagation learning: The rprop algorithm: IEEE International Conference on Neural Networks, San Francisco, CA, March 28-April 1, 1993, IEEE.Google Scholar
  12. Robinson, E. A., and Treitel, S., 1980, Geophysical signal analysis: Prentice-Hall, Inc.Google Scholar
  13. Schneider, W. A., Prince, E. R. J., and Giles, B. F., 1965, A new data-processing technique for multiple attenuation exploiting differential normal moveout: Geophysics, 30, 348–362.Google Scholar
  14. Taner, M. T., 1980, Long period sea-floor multiples and their suppression: Geophysical Prospecting, 28, 30–48.CrossRefGoogle Scholar
  15. Verschuur, D. J., and Berkhout, A. J., 1997, Estimation of multiple scattering by iterative inversion, part II: practical aspects and examples: Geophysics, 62, 1596–1611.Google Scholar
  16. Weglein, A. B., Carvalho, P. M., and Stolt, R. H., 1992, Nonlinear inverse scattering for multiple suppression: application to real data. part I: 62nd Ann. Internat. Mtg., Soc. Expl. Geophys., Expanded Abstracts, 1093–1095.Google Scholar
  17. Wiggins, J. W., 1988, Attenuation of complex water-bottom multiples by wave-equation-based prediction and subtraction: Geophysics, 53, 1527–1539.Google Scholar
  18. Yilmaz, O., 1987, Seismic data processing: Society of Exploration Geophysicists, Tulsa, OK.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2003

Authors and Affiliations

  • Robert Essenreiter
    • 1
  • Martin Karrenbach
    • 2
  • Sven Treitel
    • 3
  1. 1.PGS Seres ASLysakerNorway
  2. 2.Geophysical InstituteUniversity of KarlsruheKarlsruheGermany
  3. 3.TriDekon, Inc.TulsaUSA

Personalised recommendations