Neural network for parameters determination and seismic pattern detection

Kou-Yuan Huang*, Jiun De You, Kai Ju Chen, Hung Lin Lai, An Jin Don

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Neural network can determine the parameters of line and hyperbola. So it is adopted to detect line pattern of direct wave and hyperbola pattern of reflection wave in a seismogram. The distance calculation from point to hyperbola is calculated from the time difference. This calculation makes the parameter learning feasible. The neural network can calculate the total error for distance from point to patterns. The parameter learning rule is derived by gradient descent method to minimize the total error. Experimental results show that line and hyperbola can be detected in simulated seismic data. The detection results can improve the seismic interpretation.

Original languageEnglish
Title of host publicationSociety of Exploration Geophysicists - SEG International Exposition and 76tth Annual Meeting 2006, SEG 2006
PublisherSociety of Exploration Geophysicists
Pages2285-2289
Number of pages5
ISBN (Print)9781604236972
DOIs
StatePublished - 1 Jan 2006
EventSociety of Exploration Geophysicists International Exposition and 76tth Annual Meeting 2006, SEG 2006 - New Orleans, United States
Duration: 1 Oct 20066 Oct 2006

Publication series

NameSociety of Exploration Geophysicists - SEG International Exposition and 76tth Annual Meeting 2006, SEG 2006

Conference

ConferenceSociety of Exploration Geophysicists International Exposition and 76tth Annual Meeting 2006, SEG 2006
CountryUnited States
CityNew Orleans
Period1/10/066/10/06

Fingerprint Dive into the research topics of 'Neural network for parameters determination and seismic pattern detection'. Together they form a unique fingerprint.

Cite this