Digital core repository coupled with machine learning as a tool to classify and assess petrophysical rock properties

Lade...
Vorschaubild
Dateien
Alperovich_2-u8ijrueg73ur2.pdf
Alperovich_2-u8ijrueg73ur2.pdfGröße: 1.57 MBDownloads: 266
Datum
2020
Autor:innen
Hébert, Vanessa
Porcher, Thierry
Planes, Valentin
Léger, Marie
Rodriguez, Olivier
Youssef, Souhail
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
ArXiv-ID
Internationale Patentnummer
Link zur Lizenz
EU-Projektnummer
DFG-Projektnummer
Angaben zur Forschungsförderung (Freitext)
Projekt
Open Access-Veröffentlichung
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Beitrag zu einem Konferenzband
Publikationsstatus
Published
Erschienen in
SCHEMBRE-MCCABE, Josephina, ed., Holger OTT, ed.. E3S Web of Conferences : The 2019 International Symposium of the Society of Core Analysts (SCA 2019). EDP Sciences, 2020, 01003. E3S Web of Conferences. 146. eISSN 2267-1242. Available under: doi: 10.1051/e3sconf/202014601003
Zusammenfassung

To make efficient use of image-based rock physics workflow, it is necessary to optimize different criteria, among which: quantity, representativeness, size and resolution. Advances in artificial intelligence give insights of databases potential. Deep learning methods not only enable to classify rock images, but could also help to estimate their petrophysical properties. In this study we prepare a set of thousands high-resolution 3D images captured in a set of four reservoir rock samples as a base for learning and training. The Voxilon software computes numerical petrophysical analysis. We identify different descriptors directly from 3D images used as inputs. We use convolutional neural network modelling with supervised training using TensorFlow framework. Using approximately fifteen thousand 2D images to drive the classification network, the test on thousand unseen images shows any error of rock type misclassification. The porosity trend provides good fit between digital benchmark datasets and machine learning tests. In a few minutes, database screening classifies carbonates and sandstones images and associates the porosity values and distribution. This work aims at conveying the potential of deep learning method in reservoir characterization to petroleum research, to illustrate how a smart image-based rock physics database at industrial scale can swiftly give access to rock properties.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
The 2019 International Symposium of the Society of Core Analysts (SCA 2019), 26. Aug. 2019 - 30. Aug. 2019, Pau
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690HÉBERT, Vanessa, Thierry PORCHER, Valentin PLANES, Marie LÉGER, Anna ALPEROVICH, Bastian GOLDLÜCKE, Olivier RODRIGUEZ, Souhail YOUSSEF, 2020. Digital core repository coupled with machine learning as a tool to classify and assess petrophysical rock properties. The 2019 International Symposium of the Society of Core Analysts (SCA 2019). Pau, 26. Aug. 2019 - 30. Aug. 2019. In: SCHEMBRE-MCCABE, Josephina, ed., Holger OTT, ed.. E3S Web of Conferences : The 2019 International Symposium of the Society of Core Analysts (SCA 2019). EDP Sciences, 2020, 01003. E3S Web of Conferences. 146. eISSN 2267-1242. Available under: doi: 10.1051/e3sconf/202014601003
BibTex
@inproceedings{Hebert2020-02-05Digit-48873,
  year={2020},
  doi={10.1051/e3sconf/202014601003},
  title={Digital core repository coupled with machine learning as a tool to classify and assess petrophysical rock properties},
  number={146},
  publisher={EDP Sciences},
  series={E3S Web of Conferences},
  booktitle={E3S Web of Conferences : The 2019 International Symposium of the Society of Core Analysts (SCA 2019)},
  editor={Schembre-McCabe, Josephina and Ott, Holger},
  author={Hébert, Vanessa and Porcher, Thierry and Planes, Valentin and Léger, Marie and Alperovich, Anna and Goldlücke, Bastian and Rodriguez, Olivier and Youssef, Souhail},
  note={Article Number: 01003}
}
RDF
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/48873">
    <dcterms:abstract xml:lang="eng">To make efficient use of image-based rock physics workflow, it is necessary to optimize different criteria, among which: quantity, representativeness, size and resolution. Advances in artificial intelligence give insights of databases potential. Deep learning methods not only enable to classify rock images, but could also help to estimate their petrophysical properties. In this study we prepare a set of thousands high-resolution 3D images captured in a set of four reservoir rock samples as a base for learning and training. The Voxilon software computes numerical petrophysical analysis. We identify different descriptors directly from 3D images used as inputs. We use convolutional neural network modelling with supervised training using TensorFlow framework. Using approximately fifteen thousand 2D images to drive the classification network, the test on thousand unseen images shows any error of rock type misclassification. The porosity trend provides good fit between digital benchmark datasets and machine learning tests. In a few minutes, database screening classifies carbonates and sandstones images and associates the porosity values and distribution. This work aims at conveying the potential of deep learning method in reservoir characterization to petroleum research, to illustrate how a smart image-based rock physics database at industrial scale can swiftly give access to rock properties.</dcterms:abstract>
    <dc:contributor>Léger, Marie</dc:contributor>
    <dc:creator>Rodriguez, Olivier</dc:creator>
    <dc:creator>Planes, Valentin</dc:creator>
    <dc:language>eng</dc:language>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-03-02T09:14:07Z</dcterms:available>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/48873/3/Alperovich_2-u8ijrueg73ur2.pdf"/>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:title>Digital core repository coupled with machine learning as a tool to classify and assess petrophysical rock properties</dcterms:title>
    <dc:creator>Léger, Marie</dc:creator>
    <dc:contributor>Goldlücke, Bastian</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-03-02T09:14:07Z</dc:date>
    <dc:creator>Goldlücke, Bastian</dc:creator>
    <dcterms:issued>2020-02-05</dcterms:issued>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/48873/3/Alperovich_2-u8ijrueg73ur2.pdf"/>
    <dc:creator>Alperovich, Anna</dc:creator>
    <dc:contributor>Hébert, Vanessa</dc:contributor>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Youssef, Souhail</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/48873"/>
    <dc:rights>Attribution 4.0 International</dc:rights>
    <dc:contributor>Alperovich, Anna</dc:contributor>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Hébert, Vanessa</dc:creator>
    <dc:contributor>Rodriguez, Olivier</dc:contributor>
    <dc:creator>Porcher, Thierry</dc:creator>
    <dc:contributor>Planes, Valentin</dc:contributor>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Youssef, Souhail</dc:creator>
    <dc:contributor>Porcher, Thierry</dc:contributor>
    <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by/4.0/"/>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
URL der Originalveröffentl.
Prüfdatum der URL
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Diese Publikation teilen