Evolving Neural Conditional Random Fields for drilling report classification
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.petrol.2019.106846 http://hdl.handle.net/11449/201430 |
Resumo: | Oil and gas prospecting is an important economic activity, besides being expensive and quite complex, thus requiring close monitoring to avoid work accidents and mainly environmental damages. An essential source of information concerns the daily drilling reports that contain operations technical interpretations and additional information from rig sensors. However, only a few works have focused on mining textual information from such reports for providing intelligent-based decision-making mechanisms to aid safety and efficiency concerns in drilling operations. This work proposes a contextual-driven approach based on Recurrent Neural Networks to recognize events in drilling reports that can outperform other related techniques. We also introduce a novel approach based on evolutionary computing to combine partially trained models using cyclical learning rates. Experiments conducted on two unbalanced datasets provided by Petrobras (Petróleo Brasileiro S.A.) show that our model improved Macro-F1 scores over the baseline by more than 47%. Besides, the proposed ensembling technique further enhanced these values by another 3% in the best scenario. Such promising results can shed light over new research directions in the field.1 |
id |
UNSP_cc15e43b03b1a303b83c46eed2c56d53 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/201430 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Evolving Neural Conditional Random Fields for drilling report classificationConditional Random FieldsDrilling reports classificationNatural Language ProcessingOil and gas prospecting is an important economic activity, besides being expensive and quite complex, thus requiring close monitoring to avoid work accidents and mainly environmental damages. An essential source of information concerns the daily drilling reports that contain operations technical interpretations and additional information from rig sensors. However, only a few works have focused on mining textual information from such reports for providing intelligent-based decision-making mechanisms to aid safety and efficiency concerns in drilling operations. This work proposes a contextual-driven approach based on Recurrent Neural Networks to recognize events in drilling reports that can outperform other related techniques. We also introduce a novel approach based on evolutionary computing to combine partially trained models using cyclical learning rates. Experiments conducted on two unbalanced datasets provided by Petrobras (Petróleo Brasileiro S.A.) show that our model improved Macro-F1 scores over the baseline by more than 47%. Besides, the proposed ensembling technique further enhanced these values by another 3% in the best scenario. Such promising results can shed light over new research directions in the field.1Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)PetrobrasConselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)UNESP - São Paulo State University School of SciencesUFSCar - Federal University of São Carlos Department of ComputingCenpes - Petróleo Brasileiro S.A.UNESP - São Paulo State University Inst. of Geosciences and Exact SciencesUNESP - São Paulo State University School of SciencesUNESP - São Paulo State University Inst. of Geosciences and Exact SciencesFAPESP: #2013/07375-0Petrobras: #2014/00545-0FAPESP: #2014/12236-1FAPESP: #2016/19403-6CNPq: #307066/2017-7CNPq: #427968/2018-6Universidade Estadual Paulista (Unesp)Universidade Federal de São Carlos (UFSCar)Cenpes - Petróleo Brasileiro S.A.Ribeiro, Luiz C.F. [UNESP]Afonso, Luis C.S.Colombo, DaniloGuilherme, Ivan R. [UNESP]Papa, João P. [UNESP]2020-12-12T02:32:20Z2020-12-12T02:32:20Z2020-04-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.1016/j.petrol.2019.106846Journal of Petroleum Science and Engineering, v. 187.0920-4105http://hdl.handle.net/11449/20143010.1016/j.petrol.2019.1068462-s2.0-85077044785Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengJournal of Petroleum Science and Engineeringinfo:eu-repo/semantics/openAccess2024-04-23T16:11:01Zoai:repositorio.unesp.br:11449/201430Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-04-23T16:11:01Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Evolving Neural Conditional Random Fields for drilling report classification |
title |
Evolving Neural Conditional Random Fields for drilling report classification |
spellingShingle |
Evolving Neural Conditional Random Fields for drilling report classification Ribeiro, Luiz C.F. [UNESP] Conditional Random Fields Drilling reports classification Natural Language Processing |
title_short |
Evolving Neural Conditional Random Fields for drilling report classification |
title_full |
Evolving Neural Conditional Random Fields for drilling report classification |
title_fullStr |
Evolving Neural Conditional Random Fields for drilling report classification |
title_full_unstemmed |
Evolving Neural Conditional Random Fields for drilling report classification |
title_sort |
Evolving Neural Conditional Random Fields for drilling report classification |
author |
Ribeiro, Luiz C.F. [UNESP] |
author_facet |
Ribeiro, Luiz C.F. [UNESP] Afonso, Luis C.S. Colombo, Danilo Guilherme, Ivan R. [UNESP] Papa, João P. [UNESP] |
author_role |
author |
author2 |
Afonso, Luis C.S. Colombo, Danilo Guilherme, Ivan R. [UNESP] Papa, João P. [UNESP] |
author2_role |
author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) Universidade Federal de São Carlos (UFSCar) Cenpes - Petróleo Brasileiro S.A. |
dc.contributor.author.fl_str_mv |
Ribeiro, Luiz C.F. [UNESP] Afonso, Luis C.S. Colombo, Danilo Guilherme, Ivan R. [UNESP] Papa, João P. [UNESP] |
dc.subject.por.fl_str_mv |
Conditional Random Fields Drilling reports classification Natural Language Processing |
topic |
Conditional Random Fields Drilling reports classification Natural Language Processing |
description |
Oil and gas prospecting is an important economic activity, besides being expensive and quite complex, thus requiring close monitoring to avoid work accidents and mainly environmental damages. An essential source of information concerns the daily drilling reports that contain operations technical interpretations and additional information from rig sensors. However, only a few works have focused on mining textual information from such reports for providing intelligent-based decision-making mechanisms to aid safety and efficiency concerns in drilling operations. This work proposes a contextual-driven approach based on Recurrent Neural Networks to recognize events in drilling reports that can outperform other related techniques. We also introduce a novel approach based on evolutionary computing to combine partially trained models using cyclical learning rates. Experiments conducted on two unbalanced datasets provided by Petrobras (Petróleo Brasileiro S.A.) show that our model improved Macro-F1 scores over the baseline by more than 47%. Besides, the proposed ensembling technique further enhanced these values by another 3% in the best scenario. Such promising results can shed light over new research directions in the field.1 |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-12-12T02:32:20Z 2020-12-12T02:32:20Z 2020-04-01 |
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.petrol.2019.106846 Journal of Petroleum Science and Engineering, v. 187. 0920-4105 http://hdl.handle.net/11449/201430 10.1016/j.petrol.2019.106846 2-s2.0-85077044785 |
url |
http://dx.doi.org/10.1016/j.petrol.2019.106846 http://hdl.handle.net/11449/201430 |
identifier_str_mv |
Journal of Petroleum Science and Engineering, v. 187. 0920-4105 10.1016/j.petrol.2019.106846 2-s2.0-85077044785 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Journal of Petroleum Science and Engineering |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
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_ |
1799965747878821888 |