Location of subsurface targets in geophysical data using neural networks

Research output: Contribution to journalArticle

76 Citations (Scopus)

Abstract

Neural networks were used to estimate the offset, depth, and conductivity-area product of a conductive target given an electromagnetic ellipticity image of the target. Five different neural network paradigms and five different representations of the ellipticity image were compared. For input patterns with less than 100 elements, the directed random search and functional line networks gave the best results. For patterns with more than 100 elements, self-organizing map to back propagation was most accurate. Using the whole ellipticity image gave the most accurate results for all the network paradigms. -from Authors

Original languageEnglish (US)
Pages (from-to)1534-1544
Number of pages11
JournalGeophysics
Volume57
Issue number12
StatePublished - 1992
Externally publishedYes

Fingerprint

ellipticity
Neural networks
Self organizing maps
Backpropagation
back propagation
organizing
conductivity
electromagnetism
estimates
products
product

ASJC Scopus subject areas

  • Geochemistry and Petrology
  • Geophysics

Cite this

Location of subsurface targets in geophysical data using neural networks. / Poulton, Mary M; Sternberg, Ben K; Glass, C. E.

In: Geophysics, Vol. 57, No. 12, 1992, p. 1534-1544.

Research output: Contribution to journalArticle

@article{b3ca4adfeb4d465c9e8a57da4a6f6b48,
title = "Location of subsurface targets in geophysical data using neural networks",
abstract = "Neural networks were used to estimate the offset, depth, and conductivity-area product of a conductive target given an electromagnetic ellipticity image of the target. Five different neural network paradigms and five different representations of the ellipticity image were compared. For input patterns with less than 100 elements, the directed random search and functional line networks gave the best results. For patterns with more than 100 elements, self-organizing map to back propagation was most accurate. Using the whole ellipticity image gave the most accurate results for all the network paradigms. -from Authors",
author = "Poulton, {Mary M} and Sternberg, {Ben K} and Glass, {C. E.}",
year = "1992",
language = "English (US)",
volume = "57",
pages = "1534--1544",
journal = "Geophysics",
issn = "0016-8033",
publisher = "Society of Exploration Geophysicists",
number = "12",

}

TY - JOUR

T1 - Location of subsurface targets in geophysical data using neural networks

AU - Poulton, Mary M

AU - Sternberg, Ben K

AU - Glass, C. E.

PY - 1992

Y1 - 1992

N2 - Neural networks were used to estimate the offset, depth, and conductivity-area product of a conductive target given an electromagnetic ellipticity image of the target. Five different neural network paradigms and five different representations of the ellipticity image were compared. For input patterns with less than 100 elements, the directed random search and functional line networks gave the best results. For patterns with more than 100 elements, self-organizing map to back propagation was most accurate. Using the whole ellipticity image gave the most accurate results for all the network paradigms. -from Authors

AB - Neural networks were used to estimate the offset, depth, and conductivity-area product of a conductive target given an electromagnetic ellipticity image of the target. Five different neural network paradigms and five different representations of the ellipticity image were compared. For input patterns with less than 100 elements, the directed random search and functional line networks gave the best results. For patterns with more than 100 elements, self-organizing map to back propagation was most accurate. Using the whole ellipticity image gave the most accurate results for all the network paradigms. -from Authors

UR - http://www.scopus.com/inward/record.url?scp=0027009209&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027009209&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0027009209

VL - 57

SP - 1534

EP - 1544

JO - Geophysics

JF - Geophysics

SN - 0016-8033

IS - 12

ER -