Estimating one-dimensional models from frequency-domain electromagnetic data using modular neural networks

Mary M Poulton, Ralf A. Birken

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

An artificial neural network interpretation system is being used to interpret data from a frequency-domain electromagnetic (EM) geophysical system in near real time. The interpretation system integrates 45 separate networks in a data visualization shell. The networks produce interpretations at three different transmitter-receiver (Tx-Rx) separations for half-space and layered-earth interpretations. Modular neural networks (MNN's) were found to be the only paradigm that could successfully perform the layered-earth interpretations. An MNN with 16 inputs, five local experts, each with seven hidden processing elements, and three outputs was trained on 4795 patterns for 200 epochs. For two-layer models with a resistivity contrast greater than 2:1, resistivity estimates had greater than 96% accuracy for the first-layer resistivity, greater than 98% for the second-layer resistivity, and greater than 96% for the thickness of the first layer. If the contrast is less than 2:1, the resistivity accuracies are unaffected but thickness estimates for layers less than 2 m are unreliable. A Tx-Rx separation of 16 m with maximum depth of penetration of 8 m was assumed for the example cited.

Original languageEnglish (US)
Pages (from-to)547-555
Number of pages9
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume36
Issue number2
DOIs
StatePublished - Mar 1998

Fingerprint

electrical resistivity
estimating
electromagnetism
Neural networks
Earth (planet)
Data visualization
Transceivers
scientific visualization
transmitter receivers
estimates
half space
half spaces
artificial neural network
visualization
Processing
penetration
time measurement
shell
output

ASJC Scopus subject areas

  • Computers in Earth Sciences
  • Geochemistry and Petrology
  • Geophysics
  • Electrical and Electronic Engineering

Cite this

Estimating one-dimensional models from frequency-domain electromagnetic data using modular neural networks. / Poulton, Mary M; Birken, Ralf A.

In: IEEE Transactions on Geoscience and Remote Sensing, Vol. 36, No. 2, 03.1998, p. 547-555.

Research output: Contribution to journalArticle

@article{64bf6531d0ae4084b435a2ce77846a02,
title = "Estimating one-dimensional models from frequency-domain electromagnetic data using modular neural networks",
abstract = "An artificial neural network interpretation system is being used to interpret data from a frequency-domain electromagnetic (EM) geophysical system in near real time. The interpretation system integrates 45 separate networks in a data visualization shell. The networks produce interpretations at three different transmitter-receiver (Tx-Rx) separations for half-space and layered-earth interpretations. Modular neural networks (MNN's) were found to be the only paradigm that could successfully perform the layered-earth interpretations. An MNN with 16 inputs, five local experts, each with seven hidden processing elements, and three outputs was trained on 4795 patterns for 200 epochs. For two-layer models with a resistivity contrast greater than 2:1, resistivity estimates had greater than 96{\%} accuracy for the first-layer resistivity, greater than 98{\%} for the second-layer resistivity, and greater than 96{\%} for the thickness of the first layer. If the contrast is less than 2:1, the resistivity accuracies are unaffected but thickness estimates for layers less than 2 m are unreliable. A Tx-Rx separation of 16 m with maximum depth of penetration of 8 m was assumed for the example cited.",
author = "Poulton, {Mary M} and Birken, {Ralf A.}",
year = "1998",
month = "3",
doi = "10.1109/36.662737",
language = "English (US)",
volume = "36",
pages = "547--555",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Estimating one-dimensional models from frequency-domain electromagnetic data using modular neural networks

AU - Poulton, Mary M

AU - Birken, Ralf A.

PY - 1998/3

Y1 - 1998/3

N2 - An artificial neural network interpretation system is being used to interpret data from a frequency-domain electromagnetic (EM) geophysical system in near real time. The interpretation system integrates 45 separate networks in a data visualization shell. The networks produce interpretations at three different transmitter-receiver (Tx-Rx) separations for half-space and layered-earth interpretations. Modular neural networks (MNN's) were found to be the only paradigm that could successfully perform the layered-earth interpretations. An MNN with 16 inputs, five local experts, each with seven hidden processing elements, and three outputs was trained on 4795 patterns for 200 epochs. For two-layer models with a resistivity contrast greater than 2:1, resistivity estimates had greater than 96% accuracy for the first-layer resistivity, greater than 98% for the second-layer resistivity, and greater than 96% for the thickness of the first layer. If the contrast is less than 2:1, the resistivity accuracies are unaffected but thickness estimates for layers less than 2 m are unreliable. A Tx-Rx separation of 16 m with maximum depth of penetration of 8 m was assumed for the example cited.

AB - An artificial neural network interpretation system is being used to interpret data from a frequency-domain electromagnetic (EM) geophysical system in near real time. The interpretation system integrates 45 separate networks in a data visualization shell. The networks produce interpretations at three different transmitter-receiver (Tx-Rx) separations for half-space and layered-earth interpretations. Modular neural networks (MNN's) were found to be the only paradigm that could successfully perform the layered-earth interpretations. An MNN with 16 inputs, five local experts, each with seven hidden processing elements, and three outputs was trained on 4795 patterns for 200 epochs. For two-layer models with a resistivity contrast greater than 2:1, resistivity estimates had greater than 96% accuracy for the first-layer resistivity, greater than 98% for the second-layer resistivity, and greater than 96% for the thickness of the first layer. If the contrast is less than 2:1, the resistivity accuracies are unaffected but thickness estimates for layers less than 2 m are unreliable. A Tx-Rx separation of 16 m with maximum depth of penetration of 8 m was assumed for the example cited.

UR - http://www.scopus.com/inward/record.url?scp=0032028052&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032028052&partnerID=8YFLogxK

U2 - 10.1109/36.662737

DO - 10.1109/36.662737

M3 - Article

AN - SCOPUS:0032028052

VL - 36

SP - 547

EP - 555

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

IS - 2

ER -