Uncertainty assessment in production forecast with an optimal artificial neural network

Dominique Guerillot, J. Bruyelle

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Decisions for field development of oil and gas reservoirs are often based on uncertainties assessment on forecast productions and other variables which are highly impacted by the uncertainties on the reservoir characteristics. Using geostatistical models, it would require thousands of flow simulations of several hours each to consider the geological uncertainties. Each of these simulations would require several hours even with current high power computers. To bypass this restriction due to the computation time, one approach consists to replace the simulator by an approximation of it, also called proxy. This paper focuses on the use of Artificial Neural Networks (ANN) proposing an innovative method to build an optimal ANN.

Original languageEnglish
Title of host publicationSociety of Petroleum Engineers - SPE Middle East Oil and Gas Show and Conference 2017
PublisherSociety of Petroleum Engineers (SPE)
Pages2863-2873
Number of pages11
Volume2017-March
ISBN (Electronic)9781510838871
Publication statusPublished - 1 Jan 2017
EventSPE Middle East Oil and Gas Show and Conference 2017 - Manama, Bahrain
Duration: 6 Mar 20179 Mar 2017

Other

OtherSPE Middle East Oil and Gas Show and Conference 2017
CountryBahrain
CityManama
Period6/3/179/3/17

Fingerprint

Neural networks
Flow simulation
Simulators
Gases
Uncertainty
Oils

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Fuel Technology

Cite this

Guerillot, D., & Bruyelle, J. (2017). Uncertainty assessment in production forecast with an optimal artificial neural network. In Society of Petroleum Engineers - SPE Middle East Oil and Gas Show and Conference 2017 (Vol. 2017-March, pp. 2863-2873). Society of Petroleum Engineers (SPE).

Uncertainty assessment in production forecast with an optimal artificial neural network. / Guerillot, Dominique; Bruyelle, J.

Society of Petroleum Engineers - SPE Middle East Oil and Gas Show and Conference 2017. Vol. 2017-March Society of Petroleum Engineers (SPE), 2017. p. 2863-2873.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Guerillot, D & Bruyelle, J 2017, Uncertainty assessment in production forecast with an optimal artificial neural network. in Society of Petroleum Engineers - SPE Middle East Oil and Gas Show and Conference 2017. vol. 2017-March, Society of Petroleum Engineers (SPE), pp. 2863-2873, SPE Middle East Oil and Gas Show and Conference 2017, Manama, Bahrain, 6/3/17.
Guerillot D, Bruyelle J. Uncertainty assessment in production forecast with an optimal artificial neural network. In Society of Petroleum Engineers - SPE Middle East Oil and Gas Show and Conference 2017. Vol. 2017-March. Society of Petroleum Engineers (SPE). 2017. p. 2863-2873
Guerillot, Dominique ; Bruyelle, J. / Uncertainty assessment in production forecast with an optimal artificial neural network. Society of Petroleum Engineers - SPE Middle East Oil and Gas Show and Conference 2017. Vol. 2017-March Society of Petroleum Engineers (SPE), 2017. pp. 2863-2873
@inproceedings{f71126a83165459b895b373d97f2122a,
title = "Uncertainty assessment in production forecast with an optimal artificial neural network",
abstract = "Decisions for field development of oil and gas reservoirs are often based on uncertainties assessment on forecast productions and other variables which are highly impacted by the uncertainties on the reservoir characteristics. Using geostatistical models, it would require thousands of flow simulations of several hours each to consider the geological uncertainties. Each of these simulations would require several hours even with current high power computers. To bypass this restriction due to the computation time, one approach consists to replace the simulator by an approximation of it, also called proxy. This paper focuses on the use of Artificial Neural Networks (ANN) proposing an innovative method to build an optimal ANN.",
author = "Dominique Guerillot and J. Bruyelle",
year = "2017",
month = "1",
day = "1",
language = "English",
volume = "2017-March",
pages = "2863--2873",
booktitle = "Society of Petroleum Engineers - SPE Middle East Oil and Gas Show and Conference 2017",
publisher = "Society of Petroleum Engineers (SPE)",
address = "United States",

}

TY - GEN

T1 - Uncertainty assessment in production forecast with an optimal artificial neural network

AU - Guerillot, Dominique

AU - Bruyelle, J.

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Decisions for field development of oil and gas reservoirs are often based on uncertainties assessment on forecast productions and other variables which are highly impacted by the uncertainties on the reservoir characteristics. Using geostatistical models, it would require thousands of flow simulations of several hours each to consider the geological uncertainties. Each of these simulations would require several hours even with current high power computers. To bypass this restriction due to the computation time, one approach consists to replace the simulator by an approximation of it, also called proxy. This paper focuses on the use of Artificial Neural Networks (ANN) proposing an innovative method to build an optimal ANN.

AB - Decisions for field development of oil and gas reservoirs are often based on uncertainties assessment on forecast productions and other variables which are highly impacted by the uncertainties on the reservoir characteristics. Using geostatistical models, it would require thousands of flow simulations of several hours each to consider the geological uncertainties. Each of these simulations would require several hours even with current high power computers. To bypass this restriction due to the computation time, one approach consists to replace the simulator by an approximation of it, also called proxy. This paper focuses on the use of Artificial Neural Networks (ANN) proposing an innovative method to build an optimal ANN.

UR - http://www.scopus.com/inward/record.url?scp=85050356587&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050356587&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2017-March

SP - 2863

EP - 2873

BT - Society of Petroleum Engineers - SPE Middle East Oil and Gas Show and Conference 2017

PB - Society of Petroleum Engineers (SPE)

ER -