Pattern recognition of geophysical data
Identifieur interne : 001F37 ( PascalFrancis/Corpus ); précédent : 001F36; suivant : 001F38Pattern recognition of geophysical data
Auteurs : Bernd EhretSource :
- Geoderma : (Amsterdam) [ 0016-7061 ] ; 2010.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
A new rock classification method for ground penetrating radar (GPR) data is presented for cases where no additional geological information is available from boreholes. There are non-linear relationships between petrophysical properties of rocks and electromagnetic waves which can be handled using two methods derived from statistical learning theory on pattern recognition. An investigation was carried out looking at proving the feasibility of the method in principle for use on synthetic models as well as measurement data. The different learning methods were also compared. The method is based on multivariate statistical learning algorithms for the discrimination of layer boundaries between different rocks. The discrimination developed works with artificial neural networks (ANN) and support vector machines (SVM). The processing procedure starts with geological models with varying petrophysical rock parameters, which are to be sought in the measurement data. The models are used to generate synthetic radargrams from which rock properties can be derived using wave attributes. The calculated values of the wave attributes are stored in a multivariate data pool. This data pool is used to train the ANN and the SVM. The same wave attributes are derived from the GPR data and also saved in a data pool. This generates two data sets for pattern recognition with which to directly classify rock layers. Wave attributes can therefore be used to derive the non-linear correlative relationships between rock properties and GPR data by the weighted matrices of ANN and SVM. The presented method can be used to match reflections in the GRR data directly with the layer boundaries of rock formations. The classification of a boundary horizon between rock salt and anhydrite is demonstrated on synthetic GPR traces and measurement data from a rock salt mine. The advantage of this method is that rock classification is not a priori dependent on borehole data.
Notice en format standard (ISO 2709)
Pour connaître la documentation sur le format Inist Standard.
| pA |
|
|---|
Format Inist (serveur)
| NO : | PASCAL 11-0147620 INIST |
|---|---|
| ET : | Pattern recognition of geophysical data |
| AU : | EHRET (Bernd); TARQUIS (A. M.); BIRD (N. R. A.); PERRIER (E. M. A.); CRAWFORD (J. W.) |
| AF : | Leibniz Institute for Applied Geophysics, Stilleweg 2/30655 Hannover/Allemagne (1 aut.); Judith and David Coffey Chair, Faculty of Agriculture Food and Natural Resources, University of Sydney/Sydney 2006/Australie (4 aut.); Departamento de Matemática Aplicada, Universidad Politécnica de Madrid/28040 Madrid/Espagne (1 aut.); Department of Soil Science, Rothamsted Research/Harpenden, Herts, AL5 2JQ/Royaume-Uni (2 aut.); Unité de Recherches GEODES UR079, Centre IRD Ile de France/93143 Bondy/France (3 aut.) |
| DT : | Publication en série; Niveau analytique |
| SO : | Geoderma : (Amsterdam); ISSN 0016-7061; Coden GEDMAB; Pays-Bas; Da. 2010; Vol. 160; No. 1; Pp. 111-125; Bibl. 3/4 p. |
| LA : | Anglais |
| EA : | A new rock classification method for ground penetrating radar (GPR) data is presented for cases where no additional geological information is available from boreholes. There are non-linear relationships between petrophysical properties of rocks and electromagnetic waves which can be handled using two methods derived from statistical learning theory on pattern recognition. An investigation was carried out looking at proving the feasibility of the method in principle for use on synthetic models as well as measurement data. The different learning methods were also compared. The method is based on multivariate statistical learning algorithms for the discrimination of layer boundaries between different rocks. The discrimination developed works with artificial neural networks (ANN) and support vector machines (SVM). The processing procedure starts with geological models with varying petrophysical rock parameters, which are to be sought in the measurement data. The models are used to generate synthetic radargrams from which rock properties can be derived using wave attributes. The calculated values of the wave attributes are stored in a multivariate data pool. This data pool is used to train the ANN and the SVM. The same wave attributes are derived from the GPR data and also saved in a data pool. This generates two data sets for pattern recognition with which to directly classify rock layers. Wave attributes can therefore be used to derive the non-linear correlative relationships between rock properties and GPR data by the weighted matrices of ANN and SVM. The presented method can be used to match reflections in the GRR data directly with the layer boundaries of rock formations. The classification of a boundary horizon between rock salt and anhydrite is demonstrated on synthetic GPR traces and measurement data from a rock salt mine. The advantage of this method is that rock classification is not a priori dependent on borehole data. |
| CC : | 002A32; 001E01P03; 226C03 |
| FD : | Reconnaissance forme; Sol; Classification; Radar pénétration sol; Onde électromagnétique; Caractère statistique; Théorie; Modèle; Modélisation; Algorithme apprentissage; Réseau neuronal; Intelligence artificielle; Machine vecteur support |
| ED : | pattern recognition; soils; classification; ground-penetrating radar; electromagnetic waves; Statistical character; theory; models; Modeling; Learning algorithm; neural networks; artificial intelligence; Support vector machine |
| SD : | Suelo; Clasificación; Onda electromagnética; Carácter estadístico; Teoría; Modelo; Modelización; Algoritmo aprendizaje; Red neuronal; Máquina vector soporte |
| LO : | INIST-3607.354000194339950130 |
| ID : | 11-0147620 |
Links to Exploration step
Pascal:11-0147620Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Pattern recognition of geophysical data</title><author><name sortKey="Ehret, Bernd" sort="Ehret, Bernd" uniqKey="Ehret B" first="Bernd" last="Ehret">Bernd Ehret</name><affiliation><inist:fA14 i1="01"><s1>Leibniz Institute for Applied Geophysics, Stilleweg 2</s1><s2>30655 Hannover</s2><s3>DEU</s3><sZ>1 aut.</sZ></inist:fA14></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">11-0147620</idno><date when="2010">2010</date><idno type="stanalyst">PASCAL 11-0147620 INIST</idno><idno type="RBID">Pascal:11-0147620</idno><idno type="wicri:Area/PascalFrancis/Corpus">001F37</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Pattern recognition of geophysical data</title><author><name sortKey="Ehret, Bernd" sort="Ehret, Bernd" uniqKey="Ehret B" first="Bernd" last="Ehret">Bernd Ehret</name><affiliation><inist:fA14 i1="01"><s1>Leibniz Institute for Applied Geophysics, Stilleweg 2</s1><s2>30655 Hannover</s2><s3>DEU</s3><sZ>1 aut.</sZ></inist:fA14></affiliation></author></analytic><series><title level="j" type="main">Geoderma : (Amsterdam)</title><title level="j" type="abbreviated">Geoderma : (Amst.)</title><idno type="ISSN">0016-7061</idno><imprint><date when="2010">2010</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">Geoderma : (Amsterdam)</title><title level="j" type="abbreviated">Geoderma : (Amst.)</title><idno type="ISSN">0016-7061</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Learning algorithm</term><term>Modeling</term><term>Statistical character</term><term>Support vector machine</term><term>artificial intelligence</term><term>classification</term><term>electromagnetic waves</term><term>ground-penetrating radar</term><term>models</term><term>neural networks</term><term>pattern recognition</term><term>soils</term><term>theory</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Reconnaissance forme</term><term>Sol</term><term>Classification</term><term>Radar pénétration sol</term><term>Onde électromagnétique</term><term>Caractère statistique</term><term>Théorie</term><term>Modèle</term><term>Modélisation</term><term>Algorithme apprentissage</term><term>Réseau neuronal</term><term>Intelligence artificielle</term><term>Machine vecteur support</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">A new rock classification method for ground penetrating radar (GPR) data is presented for cases where no additional geological information is available from boreholes. There are non-linear relationships between petrophysical properties of rocks and electromagnetic waves which can be handled using two methods derived from statistical learning theory on pattern recognition. An investigation was carried out looking at proving the feasibility of the method in principle for use on synthetic models as well as measurement data. The different learning methods were also compared. The method is based on multivariate statistical learning algorithms for the discrimination of layer boundaries between different rocks. The discrimination developed works with artificial neural networks (ANN) and support vector machines (SVM). The processing procedure starts with geological models with varying petrophysical rock parameters, which are to be sought in the measurement data. The models are used to generate synthetic radargrams from which rock properties can be derived using wave attributes. The calculated values of the wave attributes are stored in a multivariate data pool. This data pool is used to train the ANN and the SVM. The same wave attributes are derived from the GPR data and also saved in a data pool. This generates two data sets for pattern recognition with which to directly classify rock layers. Wave attributes can therefore be used to derive the non-linear correlative relationships between rock properties and GPR data by the weighted matrices of ANN and SVM. The presented method can be used to match reflections in the GRR data directly with the layer boundaries of rock formations. The classification of a boundary horizon between rock salt and anhydrite is demonstrated on synthetic GPR traces and measurement data from a rock salt mine. The advantage of this method is that rock classification is not a priori dependent on borehole data.</div></front></TEI><inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>0016-7061</s0></fA01><fA02 i1="01"><s0>GEDMAB</s0></fA02><fA03 i2="1"><s0>Geoderma : (Amst.)</s0></fA03><fA05><s2>160</s2></fA05><fA06><s2>1</s2></fA06><fA08 i1="01" i2="1" l="ENG"><s1>Pattern recognition of geophysical data</s1></fA08><fA09 i1="01" i2="1" l="ENG"><s1>Complexity and Nonlinearity in Soils</s1></fA09><fA11 i1="01" i2="1"><s1>EHRET (Bernd)</s1></fA11><fA12 i1="01" i2="1"><s1>TARQUIS (A. M.)</s1><s9>ed.</s9></fA12><fA12 i1="02" i2="1"><s1>BIRD (N. R. A.)</s1><s9>ed.</s9></fA12><fA12 i1="03" i2="1"><s1>PERRIER (E. M. A.)</s1><s9>ed.</s9></fA12><fA12 i1="04" i2="1"><s1>CRAWFORD (J. W.)</s1><s9>ed.</s9></fA12><fA14 i1="01"><s1>Leibniz Institute for Applied Geophysics, Stilleweg 2</s1><s2>30655 Hannover</s2><s3>DEU</s3><sZ>1 aut.</sZ></fA14><fA15 i1="01"><s1>Judith and David Coffey Chair, Faculty of Agriculture Food and Natural Resources, University of Sydney</s1><s2>Sydney 2006</s2><s3>AUS</s3><sZ>4 aut.</sZ></fA15><fA15 i1="02"><s1>Departamento de Matemática Aplicada, Universidad Politécnica de Madrid</s1><s2>28040 Madrid</s2><s3>ESP</s3><sZ>1 aut.</sZ></fA15><fA15 i1="03"><s1>Department of Soil Science, Rothamsted Research</s1><s2>Harpenden, Herts, AL5 2JQ</s2><s3>GBR</s3><sZ>2 aut.</sZ></fA15><fA15 i1="04"><s1>Unité de Recherches GEODES UR079, Centre IRD Ile de France</s1><s2>93143 Bondy</s2><s3>FRA</s3><sZ>3 aut.</sZ></fA15><fA20><s1>111-125</s1></fA20><fA21><s1>2010</s1></fA21><fA23 i1="01"><s0>ENG</s0></fA23><fA43 i1="01"><s1>INIST</s1><s2>3607</s2><s5>354000194339950130</s5></fA43><fA44><s0>0000</s0><s1>© 2011 INIST-CNRS. All rights reserved.</s1></fA44><fA45><s0>3/4 p.</s0></fA45><fA47 i1="01" i2="1"><s0>11-0147620</s0></fA47><fA60><s1>P</s1></fA60><fA61><s0>A</s0></fA61><fA64 i1="01" i2="1"><s0>Geoderma : (Amsterdam)</s0></fA64><fA66 i1="01"><s0>NLD</s0></fA66><fC01 i1="01" l="ENG"><s0>A new rock classification method for ground penetrating radar (GPR) data is presented for cases where no additional geological information is available from boreholes. There are non-linear relationships between petrophysical properties of rocks and electromagnetic waves which can be handled using two methods derived from statistical learning theory on pattern recognition. An investigation was carried out looking at proving the feasibility of the method in principle for use on synthetic models as well as measurement data. The different learning methods were also compared. The method is based on multivariate statistical learning algorithms for the discrimination of layer boundaries between different rocks. The discrimination developed works with artificial neural networks (ANN) and support vector machines (SVM). The processing procedure starts with geological models with varying petrophysical rock parameters, which are to be sought in the measurement data. The models are used to generate synthetic radargrams from which rock properties can be derived using wave attributes. The calculated values of the wave attributes are stored in a multivariate data pool. This data pool is used to train the ANN and the SVM. The same wave attributes are derived from the GPR data and also saved in a data pool. This generates two data sets for pattern recognition with which to directly classify rock layers. Wave attributes can therefore be used to derive the non-linear correlative relationships between rock properties and GPR data by the weighted matrices of ANN and SVM. The presented method can be used to match reflections in the GRR data directly with the layer boundaries of rock formations. The classification of a boundary horizon between rock salt and anhydrite is demonstrated on synthetic GPR traces and measurement data from a rock salt mine. The advantage of this method is that rock classification is not a priori dependent on borehole data.</s0></fC01><fC02 i1="01" i2="X"><s0>002A32</s0></fC02><fC02 i1="02" i2="2"><s0>001E01P03</s0></fC02><fC02 i1="03" i2="2"><s0>226C03</s0></fC02><fC03 i1="01" i2="2" l="FRE"><s0>Reconnaissance forme</s0><s5>01</s5></fC03><fC03 i1="01" i2="2" l="ENG"><s0>pattern recognition</s0><s5>01</s5></fC03><fC03 i1="02" i2="2" l="FRE"><s0>Sol</s0><s2>NT</s2><s5>02</s5></fC03><fC03 i1="02" i2="2" l="ENG"><s0>soils</s0><s2>NT</s2><s5>02</s5></fC03><fC03 i1="02" i2="2" l="SPA"><s0>Suelo</s0><s2>NT</s2><s5>02</s5></fC03><fC03 i1="03" i2="2" l="FRE"><s0>Classification</s0><s5>04</s5></fC03><fC03 i1="03" i2="2" l="ENG"><s0>classification</s0><s5>04</s5></fC03><fC03 i1="03" i2="2" l="SPA"><s0>Clasificación</s0><s5>04</s5></fC03><fC03 i1="04" i2="2" l="FRE"><s0>Radar pénétration sol</s0><s5>06</s5></fC03><fC03 i1="04" i2="2" l="ENG"><s0>ground-penetrating radar</s0><s5>06</s5></fC03><fC03 i1="05" i2="2" l="FRE"><s0>Onde électromagnétique</s0><s5>12</s5></fC03><fC03 i1="05" i2="2" l="ENG"><s0>electromagnetic waves</s0><s5>12</s5></fC03><fC03 i1="05" i2="2" l="SPA"><s0>Onda electromagnética</s0><s5>12</s5></fC03><fC03 i1="06" i2="X" l="FRE"><s0>Caractère statistique</s0><s5>14</s5></fC03><fC03 i1="06" i2="X" l="ENG"><s0>Statistical character</s0><s5>14</s5></fC03><fC03 i1="06" i2="X" l="SPA"><s0>Carácter estadístico</s0><s5>14</s5></fC03><fC03 i1="07" i2="2" l="FRE"><s0>Théorie</s0><s5>16</s5></fC03><fC03 i1="07" i2="2" l="ENG"><s0>theory</s0><s5>16</s5></fC03><fC03 i1="07" i2="2" l="SPA"><s0>Teoría</s0><s5>16</s5></fC03><fC03 i1="08" i2="2" l="FRE"><s0>Modèle</s0><s5>19</s5></fC03><fC03 i1="08" i2="2" l="ENG"><s0>models</s0><s5>19</s5></fC03><fC03 i1="08" i2="2" l="SPA"><s0>Modelo</s0><s5>19</s5></fC03><fC03 i1="09" i2="X" l="FRE"><s0>Modélisation</s0><s5>20</s5></fC03><fC03 i1="09" i2="X" l="ENG"><s0>Modeling</s0><s5>20</s5></fC03><fC03 i1="09" i2="X" l="SPA"><s0>Modelización</s0><s5>20</s5></fC03><fC03 i1="10" i2="X" l="FRE"><s0>Algorithme apprentissage</s0><s5>21</s5></fC03><fC03 i1="10" i2="X" l="ENG"><s0>Learning algorithm</s0><s5>21</s5></fC03><fC03 i1="10" i2="X" l="SPA"><s0>Algoritmo aprendizaje</s0><s5>21</s5></fC03><fC03 i1="11" i2="2" l="FRE"><s0>Réseau neuronal</s0><s5>23</s5></fC03><fC03 i1="11" i2="2" l="ENG"><s0>neural networks</s0><s5>23</s5></fC03><fC03 i1="11" i2="2" l="SPA"><s0>Red neuronal</s0><s5>23</s5></fC03><fC03 i1="12" i2="2" l="FRE"><s0>Intelligence artificielle</s0><s5>24</s5></fC03><fC03 i1="12" i2="2" l="ENG"><s0>artificial intelligence</s0><s5>24</s5></fC03><fC03 i1="13" i2="X" l="FRE"><s0>Machine vecteur support</s0><s5>25</s5></fC03><fC03 i1="13" i2="X" l="ENG"><s0>Support vector machine</s0><s5>25</s5></fC03><fC03 i1="13" i2="X" l="SPA"><s0>Máquina vector soporte</s0><s5>25</s5></fC03><fN21><s1>094</s1></fN21></pA></standard><server><NO>PASCAL 11-0147620 INIST</NO><ET>Pattern recognition of geophysical data</ET><AU>EHRET (Bernd); TARQUIS (A. M.); BIRD (N. R. A.); PERRIER (E. M. A.); CRAWFORD (J. W.)</AU><AF>Leibniz Institute for Applied Geophysics, Stilleweg 2/30655 Hannover/Allemagne (1 aut.); Judith and David Coffey Chair, Faculty of Agriculture Food and Natural Resources, University of Sydney/Sydney 2006/Australie (4 aut.); Departamento de Matemática Aplicada, Universidad Politécnica de Madrid/28040 Madrid/Espagne (1 aut.); Department of Soil Science, Rothamsted Research/Harpenden, Herts, AL5 2JQ/Royaume-Uni (2 aut.); Unité de Recherches GEODES UR079, Centre IRD Ile de France/93143 Bondy/France (3 aut.)</AF><DT>Publication en série; Niveau analytique</DT><SO>Geoderma : (Amsterdam); ISSN 0016-7061; Coden GEDMAB; Pays-Bas; Da. 2010; Vol. 160; No. 1; Pp. 111-125; Bibl. 3/4 p.</SO><LA>Anglais</LA><EA>A new rock classification method for ground penetrating radar (GPR) data is presented for cases where no additional geological information is available from boreholes. There are non-linear relationships between petrophysical properties of rocks and electromagnetic waves which can be handled using two methods derived from statistical learning theory on pattern recognition. An investigation was carried out looking at proving the feasibility of the method in principle for use on synthetic models as well as measurement data. The different learning methods were also compared. The method is based on multivariate statistical learning algorithms for the discrimination of layer boundaries between different rocks. The discrimination developed works with artificial neural networks (ANN) and support vector machines (SVM). The processing procedure starts with geological models with varying petrophysical rock parameters, which are to be sought in the measurement data. The models are used to generate synthetic radargrams from which rock properties can be derived using wave attributes. The calculated values of the wave attributes are stored in a multivariate data pool. This data pool is used to train the ANN and the SVM. The same wave attributes are derived from the GPR data and also saved in a data pool. This generates two data sets for pattern recognition with which to directly classify rock layers. Wave attributes can therefore be used to derive the non-linear correlative relationships between rock properties and GPR data by the weighted matrices of ANN and SVM. The presented method can be used to match reflections in the GRR data directly with the layer boundaries of rock formations. The classification of a boundary horizon between rock salt and anhydrite is demonstrated on synthetic GPR traces and measurement data from a rock salt mine. The advantage of this method is that rock classification is not a priori dependent on borehole data.</EA><CC>002A32; 001E01P03; 226C03</CC><FD>Reconnaissance forme; Sol; Classification; Radar pénétration sol; Onde électromagnétique; Caractère statistique; Théorie; Modèle; Modélisation; Algorithme apprentissage; Réseau neuronal; Intelligence artificielle; Machine vecteur support</FD><ED>pattern recognition; soils; classification; ground-penetrating radar; electromagnetic waves; Statistical character; theory; models; Modeling; Learning algorithm; neural networks; artificial intelligence; Support vector machine</ED><SD>Suelo; Clasificación; Onda electromagnética; Carácter estadístico; Teoría; Modelo; Modelización; Algoritmo aprendizaje; Red neuronal; Máquina vector soporte</SD><LO>INIST-3607.354000194339950130</LO><ID>11-0147620</ID></server></inist></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Asie/explor/AustralieFrV1/Data/PascalFrancis/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001F37 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 001F37 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Asie
|area= AustralieFrV1
|flux= PascalFrancis
|étape= Corpus
|type= RBID
|clé= Pascal:11-0147620
|texte= Pattern recognition of geophysical data
}}
| This area was generated with Dilib version V0.6.33. |  |