Neural network pattern recognition of subsurface EM images

Mary M Poulton, Ben K Sternberg, Charles E. Glass

Research output: Contribution to journalArticle

40 Citations (Scopus)

Abstract

Neural networks are computer simulations of the brain's neural functions; as such they perform well on the same types of problems on which humans perform well, namely pattern recognition. Neural networks have shown the capability to learn human speech, read handwritten signatures and recpgnize human faces. Applied to geophysical data, neural networks offer the ability to estimate model parameters in near realtime. A backpropagation neural network was trained to estimate the spatial location (offset and depth) of a target given an image of the electromegnetic ellipticity. Three components of the magnetic field were measured from which the ellipticity was calculated. Theoretical ellipticity images were used for training the neural network; field data were used to test it. The input data representation was important in obtaining results with 10% error or less from the neural network; generally, smaller input vectors yielded more accurate results. Five different representations were examined: the whole image, the subsampled image, trough-peak-trough, peak amplitude and frequency domain. The frequency-domain representation estimated the target locations in the field data with the least error, 0.4% for the offset and 1.5% for the depth. The network was examined for its ability to generalize, to extrapolate beyond the spatial limits of the training set and to ignore discrepancies between synthetic and field data. The generalization from synthetic training data to synthetic test data had errors near 5% for most offset estimates and near 2% for most depth estimates. We considered extrapolation errors satisfactory (10%) up to 1.5 model spacings beyond the limits of the training set.

Original languageEnglish (US)
Pages (from-to)21-36
Number of pages16
JournalJournal of Applied Geophysics
Volume29
Issue number1
DOIs
StatePublished - 1992

Fingerprint

pattern recognition
ellipticity
education
estimates
troughs
trough
computer simulation
brain
extrapolation
spacing
computerized simulation
signatures
magnetic field
magnetic fields

ASJC Scopus subject areas

  • Geophysics

Cite this

Neural network pattern recognition of subsurface EM images. / Poulton, Mary M; Sternberg, Ben K; Glass, Charles E.

In: Journal of Applied Geophysics, Vol. 29, No. 1, 1992, p. 21-36.

Research output: Contribution to journalArticle

@article{ef2e53859c24470e9b985d00565e8f63,
title = "Neural network pattern recognition of subsurface EM images",
abstract = "Neural networks are computer simulations of the brain's neural functions; as such they perform well on the same types of problems on which humans perform well, namely pattern recognition. Neural networks have shown the capability to learn human speech, read handwritten signatures and recpgnize human faces. Applied to geophysical data, neural networks offer the ability to estimate model parameters in near realtime. A backpropagation neural network was trained to estimate the spatial location (offset and depth) of a target given an image of the electromegnetic ellipticity. Three components of the magnetic field were measured from which the ellipticity was calculated. Theoretical ellipticity images were used for training the neural network; field data were used to test it. The input data representation was important in obtaining results with 10{\%} error or less from the neural network; generally, smaller input vectors yielded more accurate results. Five different representations were examined: the whole image, the subsampled image, trough-peak-trough, peak amplitude and frequency domain. The frequency-domain representation estimated the target locations in the field data with the least error, 0.4{\%} for the offset and 1.5{\%} for the depth. The network was examined for its ability to generalize, to extrapolate beyond the spatial limits of the training set and to ignore discrepancies between synthetic and field data. The generalization from synthetic training data to synthetic test data had errors near 5{\%} for most offset estimates and near 2{\%} for most depth estimates. We considered extrapolation errors satisfactory (10{\%}) up to 1.5 model spacings beyond the limits of the training set.",
author = "Poulton, {Mary M} and Sternberg, {Ben K} and Glass, {Charles E.}",
year = "1992",
doi = "10.1016/0926-9851(92)90010-I",
language = "English (US)",
volume = "29",
pages = "21--36",
journal = "Journal of Applied Geophysics",
issn = "0926-9851",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - Neural network pattern recognition of subsurface EM images

AU - Poulton, Mary M

AU - Sternberg, Ben K

AU - Glass, Charles E.

PY - 1992

Y1 - 1992

N2 - Neural networks are computer simulations of the brain's neural functions; as such they perform well on the same types of problems on which humans perform well, namely pattern recognition. Neural networks have shown the capability to learn human speech, read handwritten signatures and recpgnize human faces. Applied to geophysical data, neural networks offer the ability to estimate model parameters in near realtime. A backpropagation neural network was trained to estimate the spatial location (offset and depth) of a target given an image of the electromegnetic ellipticity. Three components of the magnetic field were measured from which the ellipticity was calculated. Theoretical ellipticity images were used for training the neural network; field data were used to test it. The input data representation was important in obtaining results with 10% error or less from the neural network; generally, smaller input vectors yielded more accurate results. Five different representations were examined: the whole image, the subsampled image, trough-peak-trough, peak amplitude and frequency domain. The frequency-domain representation estimated the target locations in the field data with the least error, 0.4% for the offset and 1.5% for the depth. The network was examined for its ability to generalize, to extrapolate beyond the spatial limits of the training set and to ignore discrepancies between synthetic and field data. The generalization from synthetic training data to synthetic test data had errors near 5% for most offset estimates and near 2% for most depth estimates. We considered extrapolation errors satisfactory (10%) up to 1.5 model spacings beyond the limits of the training set.

AB - Neural networks are computer simulations of the brain's neural functions; as such they perform well on the same types of problems on which humans perform well, namely pattern recognition. Neural networks have shown the capability to learn human speech, read handwritten signatures and recpgnize human faces. Applied to geophysical data, neural networks offer the ability to estimate model parameters in near realtime. A backpropagation neural network was trained to estimate the spatial location (offset and depth) of a target given an image of the electromegnetic ellipticity. Three components of the magnetic field were measured from which the ellipticity was calculated. Theoretical ellipticity images were used for training the neural network; field data were used to test it. The input data representation was important in obtaining results with 10% error or less from the neural network; generally, smaller input vectors yielded more accurate results. Five different representations were examined: the whole image, the subsampled image, trough-peak-trough, peak amplitude and frequency domain. The frequency-domain representation estimated the target locations in the field data with the least error, 0.4% for the offset and 1.5% for the depth. The network was examined for its ability to generalize, to extrapolate beyond the spatial limits of the training set and to ignore discrepancies between synthetic and field data. The generalization from synthetic training data to synthetic test data had errors near 5% for most offset estimates and near 2% for most depth estimates. We considered extrapolation errors satisfactory (10%) up to 1.5 model spacings beyond the limits of the training set.

UR - http://www.scopus.com/inward/record.url?scp=0026464605&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026464605&partnerID=8YFLogxK

U2 - 10.1016/0926-9851(92)90010-I

DO - 10.1016/0926-9851(92)90010-I

M3 - Article

VL - 29

SP - 21

EP - 36

JO - Journal of Applied Geophysics

JF - Journal of Applied Geophysics

SN - 0926-9851

IS - 1

ER -