Syntactic Pattern Recognition for Seismic Oil Exploration

Kou-Yuan Huang

Research output: Book/ReportBookpeer-review


The use of pattern recognition has become more and more important in seismic oil exploration. Interpreting a large volume of seismic data is a challenging problem. Seismic reflection data in the one-shot seismogram and stacked seismogram may contain some structural information from the response of the subsurface. Syntactic/structural pattern recognition techniques can recognize the structural seismic patterns and improve seismic interpretations.

The syntactic analysis methods include: (1) the error-correcting finite-state parsing, (2) the modified error-correcting Earley's parsing, (3) the parsing using the match primitive measure, (4) the Levenshtein distance computation, (5) the likelihood ratio test, (6) the error-correcting tree automata, and (7) a hierarchical system.

Syntactic seismic pattern recognition can be one of the milestones of a geophysical intelligent interpretation system. The syntactic methods in this book can be applied to other areas, such as the medical diagnosis system. The book will benefit geophysicists, computer scientists and electrical engineers.
Original languageEnglish
PublisherWorld Scientific Publishing Co. Pte Ltd
Number of pages148
ISBN (Print) 9789810246006
StatePublished - May 2002

Fingerprint Dive into the research topics of 'Syntactic Pattern Recognition for Seismic Oil Exploration'. Together they form a unique fingerprint.

Cite this