Identification and classification of multiple reflections with self-organizing maps

Artificial neural networks can be used effectively to identify and classify multiple events in a seismic data set. We use a specialized neural network, a self-organizing map (SOM), that tries to establish rules for the characterization of the physical problem. Selected seismic data attributes from CMP gathers are used as input patterns, such that the SOM arranges the data to form clusters in an abstract space. We show with synthetic and real data how the SOM can identify and classify primaries and multiples, and how it can classify the various types of multiple corresponding to a certain generating mechanism in the subsurface.

[1]  Mrinal K. Sen,et al.  Hopfield neural networks, and mean field annealing for seismic deconvolution and multiple attenuation , 1997 .

[2]  D. J. Verschuur,et al.  Estimation of multiple scattering by iterative inversion, Part I: Theoretical considerations , 1997 .

[3]  Robert Essenreiter.  Identification and attenuation of multiple reflections with neural networks , 1999 .

[4]  B. Gelchinsky,et al.  Multiple prediction using the homeomorphic‐imaging technique , 1998 .

[5]  K. Helbig,et al.  Surface multiples as a tool of calibration in shallow AVO studies , 1993 .

[6]  Arthur B. Weglein,et al.  Nonlinear Inverse Scattering For Multiple Suppression: Application to Real Data. Part I , 1992 .

[7]  William A. Schneider,et al.  A new data-processing technique for multiple attenuation exploiting differential normal moveout , 1965 .

[8]  Sven Treitel,et al.  Multiple reflection attenuation in seismic data using backpropagation , 1998, IEEE Trans. Signal Process..

[9]  Sven Treitel,et al.  Identification and Suppression of Multiple Reflections in Marine Seismic Data with Neural Networks , 2003 .

[10]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[11]  Walter Dandy,et al.  The Brain , 1966 .

[12]  P. Hubral.  Computing true amplitude reflections in a laterally inhomogeneous earth , 1983 .

[13]  G. Höcht,et al.  Common reflection surface stacking method — Imaging with an unknown velocity model , 1998 .

[14]  James A. Anderson,et al.  A simple neural network generating an interactive memory , 1972 .

[15]  Peter Hubral,et al.  Elastic Waves in Random Media: Fundamentals of Seismic Stratigraphic Filtering , 1998 .

[16]  N. A. Anstey,et al.  Reflections on AMPLITUDES , 1971 .

[17]  D. J. Verschuur,et al.  Estimation of multiple scattering by iterative inversion; Part II, Practical aspects and examples , 1997 .

[18]  V. Bardan,et al.  3D targeted multiple attenuation , 1997 .

[19]  Sven Treitel,et al.  Geophysical Signal Analysis , 2000 .

[20]  M. Carpenter,et al.  The Brain , 1971, Neurology.

[21]  P. Carrion,et al.  A LAYER‐STRIPPING TECHNIQUE FOR THE SUPPRESSION OF WATER‐BOTTOM MULTIPLE REFLECTIONS* , 1986 .

[22]  James A. Anderson,et al.  Cognitive and psychological computation with neural models , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[23]  J. R. Berryhill,et al.  Deep-water peg legs and multiples: Emulation and suppression , 1986 .

[24]  J. W. Wiggins,et al.  Attenuation of complex water-bottom multiples by wave-equation-based prediction and subtraction , 1988 .

[25]  S. Treitel.  PREDICTIVE DECONVOLUTION: THEORY AND PRACTICE , 1969 .