Modeling sonic logs in oil wells: a comparison of neural networks ensembles and kernel methods

Oil well logs are frequently used to determine the mineralogy and physical properties of potential reservoir rocks, and the nature of the fluids they contain. Recently we reported an exploratory use of neural network ensembles for modeling these records. We showed that ensembles are clearly superior...

Descripción completa

Detalles Bibliográficos
Autores principales: Granitto, Pablo Miguel, Navone, Hugo Daniel, Verdes, Pablo Fabián, Ceccatto, Hermenegildo Alejandro
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2001
Materias:
Ciencias Informáticas
ensemble methods
kernel methods
petroleum industry
Neural nets
ARTIFICIAL INTELLIGENCE
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/23416
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-23416
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
ensemble methods
kernel methods
petroleum industry
Neural nets
ARTIFICIAL INTELLIGENCE
spellingShingle Ciencias Informáticas
ensemble methods
kernel methods
petroleum industry
Neural nets
ARTIFICIAL INTELLIGENCE
Granitto, Pablo Miguel
Navone, Hugo Daniel
Verdes, Pablo Fabián
Ceccatto, Hermenegildo Alejandro
Modeling sonic logs in oil wells: a comparison of neural networks ensembles and kernel methods
topic_facet Ciencias Informáticas
ensemble methods
kernel methods
petroleum industry
Neural nets
ARTIFICIAL INTELLIGENCE
description Oil well logs are frequently used to determine the mineralogy and physical properties of potential reservoir rocks, and the nature of the fluids they contain. Recently we reported an exploratory use of neural network ensembles for modeling these records. We showed that ensembles are clearly superior to linear multivariate regression as modeling technique, revealing an underlying nonlinear functional dependency between the correlated variables. In this work we use kernel methods to develop nonlinear local models relating Sonic logs (transit time of compressional waves) with other commonly measured properties (Resistivity and Natural Formation Radioactivity Level or Gamma Ray log). The kernel considered is conceptually simple and numerically robust, and allows to obtain the same performance as neural networks ensembles on this task.
format Objeto de conferencia
Objeto de conferencia
author Granitto, Pablo Miguel
Navone, Hugo Daniel
Verdes, Pablo Fabián
Ceccatto, Hermenegildo Alejandro
author_facet Granitto, Pablo Miguel
Navone, Hugo Daniel
Verdes, Pablo Fabián
Ceccatto, Hermenegildo Alejandro
author_sort Granitto, Pablo Miguel
title Modeling sonic logs in oil wells: a comparison of neural networks ensembles and kernel methods
title_short Modeling sonic logs in oil wells: a comparison of neural networks ensembles and kernel methods
title_full Modeling sonic logs in oil wells: a comparison of neural networks ensembles and kernel methods
title_fullStr Modeling sonic logs in oil wells: a comparison of neural networks ensembles and kernel methods
title_full_unstemmed Modeling sonic logs in oil wells: a comparison of neural networks ensembles and kernel methods
title_sort modeling sonic logs in oil wells: a comparison of neural networks ensembles and kernel methods
publishDate 2001
url http://sedici.unlp.edu.ar/handle/10915/23416
work_keys_str_mv AT granittopablomiguel modelingsoniclogsinoilwellsacomparisonofneuralnetworksensemblesandkernelmethods
AT navonehugodaniel modelingsoniclogsinoilwellsacomparisonofneuralnetworksensemblesandkernelmethods
AT verdespablofabian modelingsoniclogsinoilwellsacomparisonofneuralnetworksensemblesandkernelmethods
AT ceccattohermenegildoalejandro modelingsoniclogsinoilwellsacomparisonofneuralnetworksensemblesandkernelmethods
bdutipo_str Repositorios
_version_ 1764820465897963521

Ejemplares similares