Seismic attribute selection and clustering to detect and classify surface waves in multicomponent seismic data by using k-means algorithm

Seismic records are characterized by a high level of complexity resulting from the interaction of different types of waves propagating in the subsurface. Interpretation of the different wave modes and features present in a seismic record generally is done by expert judgment, and its automatization is a problem that has not been resolved completely. We present a methodology that uses pattern recognition to select the best seismic attributes that should be chosen to detect and classify surface waves in a seismic record, based on the notion of similarity, and that is applied on the automatic interpretation of three different seismic-data record sets. The classification obtained for these different real data sets exhibits well-differentiated zones that improve and automatize the expert judgment interpretation.

[1]  Brian L. N. Kennett,et al.  Automatic Phase-Detection and Identification by Full Use of a Single Three-Component Broadband Seismogram , 2000 .

[2]  A. Jurkevics.  Polarization analysis of three-component array data , 1988 .

[3]  Frank Scherbaum,et al.  Dynamic Bayesian Networks for Real-Time Classification of Seismic Signals , 2007, PKDD.

[4]  Matthias Ohrnberger,et al.  Continuous automatic classification of seismic signals of volcanic origin at Mt. Merapi, Java, Indonesia , 2001 .

[5]  C. R. Pinnegar,et al.  Polarization analysis and polarization filtering of three-component signals with the time–frequency S transform , 2006 .

[6]  Iván-Javier Sánchez-Galvis,et al.  SVD POLARIZATION FILTER TAKING INTO ACCOUNT THE PLANARITY OF GROUND ROLL ENERGY , 2016 .

[7]  Igor B. Morozov,et al.  Instantaneous polarization attributes and directional filtering , 1996 .

[8]  Manfred Joswig.  Pattern Recognition for Earthquake Detection , 1987, ASST.

[9]  Gemma Musacchio,et al.  Polarization filter with singular value decomposition , 2001 .

[10]  Frank Scherbaum,et al.  Unsupervised pattern recognition in continuous seismic wavefield records using Self-Organizing Maps , 2010 .

[11]  J. Caers,et al.  Stochastic Simulation of Patterns Using Distance-Based Pattern Modeling , 2010 .

[12]  J-M Kendall,et al.  Signal Extraction and Automated Polarization Analysis of Multicomponent Array Data , 2006 .

[13]  Lorie K. Bear,et al.  Multi-wavelet analysis of three-component seismic arrays: Application to measure effective anisotropy at Piñon Flats, California , 1999, Bulletin of the Seismological Society of America.

[14]  John E. Vidale,et al.  Complex polarization analysis of particle motion , 1986 .

[15]  Olena Tiapkina,et al.  Single-station SVD-based polarization filtering of ground roll: Perfection and investigation of limitations and pitfalls , 2012 .

[16]  Frank Scherbaum,et al.  Unsupervised feature selection and general pattern discovery using Self-Organizing Maps for gaining insights into the nature of seismic wavefields , 2009, Comput. Geosci..

[17]  Robert E. Sheriff,et al.  Encyclopedic dictionary of applied geophysics , 2002 .