A fast approach for unsupervised karst feature identification using GPU

Detalhes bibliográficos
Autor(a) principal: Afonso, Luis C.S.
Data de Publicação: 2018
Outros Autores: Basso, Mateus, Kuroda, Michelle C., Vidal, Alexandre C., Papa, João P. [UNESP]
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1016/j.cageo.2018.06.004
http://hdl.handle.net/11449/179968
Resumo: Among the geological features, karst is the one that has received special attention in oil and gas exploration for being a strong indicator of the potential existence of hydrocarbon reservoirs. The integration of automatic pattern recognition methods and Graphics Processing Units (GPU) provides a powerful tool to help geological interpretation of seismic data. In order to provide insightful information for interpreters, this work investigates the usage of GPUs in addition to image segmentation by means of unsupervised classification for the identification of karst features in 3D seismic data. For this purpose, an implementation of the robust Self-Organizing Map for GPUs (SOM/GPU) is provided, and a comparison against a Central Processing Unit (CPU)-based SOM (SOM/CPU) is performed to assess the speeding-up provided by GPU. Experiments have shown promising results for geological interpretation using seismic data.
id UNSP_da84f02c0f0b32d2ff209d5ee4950125
oai_identifier_str oai:repositorio.unesp.br:11449/179968
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling A fast approach for unsupervised karst feature identification using GPUCampos basinGraphics processing unitPaleokarstSelf-organizing mapAmong the geological features, karst is the one that has received special attention in oil and gas exploration for being a strong indicator of the potential existence of hydrocarbon reservoirs. The integration of automatic pattern recognition methods and Graphics Processing Units (GPU) provides a powerful tool to help geological interpretation of seismic data. In order to provide insightful information for interpreters, this work investigates the usage of GPUs in addition to image segmentation by means of unsupervised classification for the identification of karst features in 3D seismic data. For this purpose, an implementation of the robust Self-Organizing Map for GPUs (SOM/GPU) is provided, and a comparison against a Central Processing Unit (CPU)-based SOM (SOM/CPU) is performed to assess the speeding-up provided by GPU. Experiments have shown promising results for geological interpretation using seismic data.StatoilUFSCar - Federal University of São Carlos Department of ComputingUNICAMP - University of Campinas Institute of GeosciencesUNESP - São Paulo State University School of SciencesUNESP - São Paulo State University School of SciencesUniversidade Federal de São Carlos (UFSCar)Universidade Estadual de Campinas (UNICAMP)Universidade Estadual Paulista (Unesp)Afonso, Luis C.S.Basso, MateusKuroda, Michelle C.Vidal, Alexandre C.Papa, João P. [UNESP]2018-12-11T17:37:29Z2018-12-11T17:37:29Z2018-10-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article1-8application/pdfhttp://dx.doi.org/10.1016/j.cageo.2018.06.004Computers and Geosciences, v. 119, p. 1-8.0098-3004http://hdl.handle.net/11449/17996810.1016/j.cageo.2018.06.0042-s2.0-850487615322-s2.0-85048761532.pdfScopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengComputers and Geosciences1,350info:eu-repo/semantics/openAccess2024-04-23T16:11:00Zoai:repositorio.unesp.br:11449/179968Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-04-23T16:11Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv A fast approach for unsupervised karst feature identification using GPU
title A fast approach for unsupervised karst feature identification using GPU
spellingShingle A fast approach for unsupervised karst feature identification using GPU
Afonso, Luis C.S.
Campos basin
Graphics processing unit
Paleokarst
Self-organizing map
title_short A fast approach for unsupervised karst feature identification using GPU
title_full A fast approach for unsupervised karst feature identification using GPU
title_fullStr A fast approach for unsupervised karst feature identification using GPU
title_full_unstemmed A fast approach for unsupervised karst feature identification using GPU
title_sort A fast approach for unsupervised karst feature identification using GPU
author Afonso, Luis C.S.
author_facet Afonso, Luis C.S.
Basso, Mateus
Kuroda, Michelle C.
Vidal, Alexandre C.
Papa, João P. [UNESP]
author_role author
author2 Basso, Mateus
Kuroda, Michelle C.
Vidal, Alexandre C.
Papa, João P. [UNESP]
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Universidade Federal de São Carlos (UFSCar)
Universidade Estadual de Campinas (UNICAMP)
Universidade Estadual Paulista (Unesp)
dc.contributor.author.fl_str_mv Afonso, Luis C.S.
Basso, Mateus
Kuroda, Michelle C.
Vidal, Alexandre C.
Papa, João P. [UNESP]
dc.subject.por.fl_str_mv Campos basin
Graphics processing unit
Paleokarst
Self-organizing map
topic Campos basin
Graphics processing unit
Paleokarst
Self-organizing map
description Among the geological features, karst is the one that has received special attention in oil and gas exploration for being a strong indicator of the potential existence of hydrocarbon reservoirs. The integration of automatic pattern recognition methods and Graphics Processing Units (GPU) provides a powerful tool to help geological interpretation of seismic data. In order to provide insightful information for interpreters, this work investigates the usage of GPUs in addition to image segmentation by means of unsupervised classification for the identification of karst features in 3D seismic data. For this purpose, an implementation of the robust Self-Organizing Map for GPUs (SOM/GPU) is provided, and a comparison against a Central Processing Unit (CPU)-based SOM (SOM/CPU) is performed to assess the speeding-up provided by GPU. Experiments have shown promising results for geological interpretation using seismic data.
publishDate 2018
dc.date.none.fl_str_mv 2018-12-11T17:37:29Z
2018-12-11T17:37:29Z
2018-10-01
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1016/j.cageo.2018.06.004
Computers and Geosciences, v. 119, p. 1-8.
0098-3004
http://hdl.handle.net/11449/179968
10.1016/j.cageo.2018.06.004
2-s2.0-85048761532
2-s2.0-85048761532.pdf
url http://dx.doi.org/10.1016/j.cageo.2018.06.004
http://hdl.handle.net/11449/179968
identifier_str_mv Computers and Geosciences, v. 119, p. 1-8.
0098-3004
10.1016/j.cageo.2018.06.004
2-s2.0-85048761532
2-s2.0-85048761532.pdf
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Computers and Geosciences
1,350
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 1-8
application/pdf
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1799965387393073152

Registros relacionados