Técnicas de aprendizado de máquina para previsão de perdas severas em rochas carbonáticas de reservatórios do pré-sal

Giovani Ferreira Machado; Luciana Faletti Almeida; Juan Guillermo Lazo Lazo

doi:10.34117/bjdv7n3-496

Técnicas de aprendizado de máquina para previsão de perdas severas em rochas carbonáticas de reservatórios do pré-sal

Translated title of the contribution: Machine learning techniques for predicting severe losses in carbonate rocks from pre-salt reservoirs

Giovani Ferreira Machado, Luciana Faletti Almeida, Juan Guillermo Lazo Lazo

Universidad del Pacífico

Research output: Contribution to journal › Article in a journal › peer-review

Abstract

This work aims to present binary classification models to assist in determining the occurrence of circulation loss phenomenon in the construction of subsea wells in the Santos Basin’s pre-salt. Prior knowledge about the possibility of the phenomenon occurrence, makes it possible to allocate rigs with the appropriate technology for the well's construction. In this context, classification systems based on machine learning can support decision making. In this work, classifiers are proposed based on classic machine learning algorithms (Pedregosa, F. et al. 2011) and the results are presented using the Area Under the ROC Curve (AUC) as the metric.

Translated title of the contribution	Machine learning techniques for predicting severe losses in carbonate rocks from pre-salt reservoirs
Original language	Portuguese
Pages (from-to)	28061-28074
Number of pages	14
Journal	Brazilian Journal of Development
Volume	7
Issue number	3
DOIs	https://doi.org/10.34117/bjdv7n3-496
State	Published - 1 Mar 2021
Event	Congresso Brasileiro de Automática - Brasil Duration: 11 Jan 2020 → 11 Jan 2020

Keywords

Circulation Loss
Classification
Machine learning
Pre-salt
Drilling

Access to Document

10.34117/bjdv7n3-496

Cite this

@article{2731f59f057445d4b083d4bc67def8dd,

title = "T{\'e}cnicas de aprendizado de m{\'a}quina para previs{\~a}o de perdas severas em rochas carbon{\'a}ticas de reservat{\'o}rios do pr{\'e}-sal",

abstract = "This work aims to present binary classification models to assist in determining the occurrence of circulation loss phenomenon in the construction of subsea wells in the Santos Basin{\textquoteright}s pre-salt. Prior knowledge about the possibility of the phenomenon occurrence, makes it possible to allocate rigs with the appropriate technology for the well's construction. In this context, classification systems based on machine learning can support decision making. In this work, classifiers are proposed based on classic machine learning algorithms (Pedregosa, F. et al. 2011) and the results are presented using the Area Under the ROC Curve (AUC) as the metric.",

keywords = "Circulation Loss, Classification, Machine learning, Pre-salt, Drilling",

author = "Machado, {Giovani Ferreira} and Almeida, {Luciana Faletti} and {Lazo Lazo}, {Juan Guillermo}",

year = "2021",

month = mar,

day = "1",

doi = "10.34117/bjdv7n3-496",

language = "Portugu{\'e}s",

volume = "7",

pages = "28061--28074",

journal = "Brazilian Journal of Development",

issn = "2525-8761",

number = "3",

note = "Congresso Brasileiro de Autom{\'a}tica ; Conference date: 11-01-2020 Through 11-01-2020",

}

TY - JOUR

T1 - Técnicas de aprendizado de máquina para previsão de perdas severas em rochas carbonáticas de reservatórios do pré-sal

AU - Machado, Giovani Ferreira

AU - Almeida, Luciana Faletti

AU - Lazo Lazo, Juan Guillermo

PY - 2021/3/1

Y1 - 2021/3/1

N2 - This work aims to present binary classification models to assist in determining the occurrence of circulation loss phenomenon in the construction of subsea wells in the Santos Basin’s pre-salt. Prior knowledge about the possibility of the phenomenon occurrence, makes it possible to allocate rigs with the appropriate technology for the well's construction. In this context, classification systems based on machine learning can support decision making. In this work, classifiers are proposed based on classic machine learning algorithms (Pedregosa, F. et al. 2011) and the results are presented using the Area Under the ROC Curve (AUC) as the metric.

AB - This work aims to present binary classification models to assist in determining the occurrence of circulation loss phenomenon in the construction of subsea wells in the Santos Basin’s pre-salt. Prior knowledge about the possibility of the phenomenon occurrence, makes it possible to allocate rigs with the appropriate technology for the well's construction. In this context, classification systems based on machine learning can support decision making. In this work, classifiers are proposed based on classic machine learning algorithms (Pedregosa, F. et al. 2011) and the results are presented using the Area Under the ROC Curve (AUC) as the metric.

KW - Circulation Loss

KW - Classification

KW - Machine learning

KW - Pre-salt

KW - Drilling

UR - https://www.mendeley.com/catalogue/578c0070-3a45-3129-8539-7bd50448f2c7/

U2 - 10.34117/bjdv7n3-496

DO - 10.34117/bjdv7n3-496

M3 - Artículo de revista

SN - 2525-8761

VL - 7

SP - 28061

EP - 28074

JO - Brazilian Journal of Development

JF - Brazilian Journal of Development

IS - 3

T2 - Congresso Brasileiro de Automática

Y2 - 11 January 2020 through 11 January 2020

ER -

Técnicas de aprendizado de máquina para previsão de perdas severas em rochas carbonáticas de reservatórios do pré-sal

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Técnicas de aprendizado de máquina para previsão de perdas severas em rochas carbonáticas de reservatórios do pré-sal

Cite this