Neural network based layer picking for unfocused resistivity log parameterization

Lin Zhang; Mary Poulton; Alberto Mezzatesta

doi:10.1190/1.1820767

Neural network based layer picking for unfocused resistivity log parameterization

Lin Zhang, Mary Poulton, Alberto Mezzatesta

Mining and Geological Engineering

Research output: Contribution to conference › Paper › peer-review

1 Scopus citations

Abstract

Layer boundary determination is important for earth model parameterization in inversion methods. Unfocused logging tools can produce responses that are asymmetric with respect to layer boundaries. This means we cannot extract accurate layer boundaries based on breaks in the slope. We have developed a neural network based approach to pick layer boundaries from unfocused log data by correcting for the shifted response. The neural network approach to layer picking provides a general way to solve the problem of layer boundary determination and avoids the need for a multitude of specialized algorithms for specific situations or tools.

Original language	English (US)
DOIs	https://doi.org/10.1190/1.1820767
State	Published - 1999
Event	1999 Society of Exploration Geophysicists Annual Meeting, SEG 1999 - Houston, United States Duration: Oct 31 1999 → Nov 5 1999

Other

Other	1999 Society of Exploration Geophysicists Annual Meeting, SEG 1999
Country/Territory	United States
City	Houston
Period	10/31/99 → 11/5/99

ASJC Scopus subject areas

Geophysics

Access to Document

10.1190/1.1820767

Cite this

@conference{486eec4678e647dfa6bb78ad59966aa7,

title = "Neural network based layer picking for unfocused resistivity log parameterization",

abstract = "Layer boundary determination is important for earth model parameterization in inversion methods. Unfocused logging tools can produce responses that are asymmetric with respect to layer boundaries. This means we cannot extract accurate layer boundaries based on breaks in the slope. We have developed a neural network based approach to pick layer boundaries from unfocused log data by correcting for the shifted response. The neural network approach to layer picking provides a general way to solve the problem of layer boundary determination and avoids the need for a multitude of specialized algorithms for specific situations or tools.",

author = "Lin Zhang and Mary Poulton and Alberto Mezzatesta",

note = "Publisher Copyright: {\textcopyright} 1999 Society of Exploration Geophysicists. All rights reserved.; 1999 Society of Exploration Geophysicists Annual Meeting, SEG 1999 ; Conference date: 31-10-1999 Through 05-11-1999",

year = "1999",

doi = "10.1190/1.1820767",

language = "English (US)",

}

TY - CONF

T1 - Neural network based layer picking for unfocused resistivity log parameterization

AU - Zhang, Lin

AU - Poulton, Mary

AU - Mezzatesta, Alberto

PY - 1999

Y1 - 1999

N2 - Layer boundary determination is important for earth model parameterization in inversion methods. Unfocused logging tools can produce responses that are asymmetric with respect to layer boundaries. This means we cannot extract accurate layer boundaries based on breaks in the slope. We have developed a neural network based approach to pick layer boundaries from unfocused log data by correcting for the shifted response. The neural network approach to layer picking provides a general way to solve the problem of layer boundary determination and avoids the need for a multitude of specialized algorithms for specific situations or tools.

AB - Layer boundary determination is important for earth model parameterization in inversion methods. Unfocused logging tools can produce responses that are asymmetric with respect to layer boundaries. This means we cannot extract accurate layer boundaries based on breaks in the slope. We have developed a neural network based approach to pick layer boundaries from unfocused log data by correcting for the shifted response. The neural network approach to layer picking provides a general way to solve the problem of layer boundary determination and avoids the need for a multitude of specialized algorithms for specific situations or tools.

UR - http://www.scopus.com/inward/record.url?scp=85086688512&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85086688512&partnerID=8YFLogxK

U2 - 10.1190/1.1820767

DO - 10.1190/1.1820767

M3 - Paper

AN - SCOPUS:85086688512

T2 - 1999 Society of Exploration Geophysicists Annual Meeting, SEG 1999

Y2 - 31 October 1999 through 5 November 1999

ER -

Neural network based layer picking for unfocused resistivity log parameterization

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this