Production performance prediction and field development design tool for coalbed methane reservoirs: A neuro-simulation approach

Vaibhav Rajput, E. D.K. Basel, Turgay Ertekin

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

1 Citation (Scopus)

Abstract

Implementation of numerical simulations for field development optimization can be overly demanding in terms of their time and manpower requirements. To overcome these problems, a methodology has been developed that can be used to predict production performance of a given field and perform field development studies with nominal manpower and computational requirements. Artificial neural networks (ANN) are used for development of expert systems for prediction of instantaneous and cumulative gas and water production, as well as for reservoir property prediction. A commercial reservoir simulator is employed for generation of database for training, validation and testing of these expert systems. Uncertainty in reservoir properties is taken into account by varying the reservoir parameters within an estimated range of values. Analysis of results obtained from trained networks showed error values of less than 3% for prediction of gas and water production profiles (forward networks), while those that are obtained for prediction of reservoir characteristics gave error levels of 15-18% (inverse networks). Forward networks were then used for optimization of field development based upon the criteria of maximizing the net present value (NPV) of a given field. Several case studies were carried out and analyzed.

Original languageEnglish (US)
Title of host publicationApplication of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015
EditorsSukumar Bandopadhyay, Snehamoy Chatterjee, Tathagata Ghosh, Kumar Vaibhav Raj
PublisherSociety for Mining, Metallurgy and Exploration (SME)
Pages930-938
Number of pages9
ISBN (Electronic)9780873354172
StatePublished - Jan 1 2015
Event37th International Symposium on Application of Computers and Operations Research in the Mineral Industry, APCOM 2015 - Fairbanks, United States
Duration: May 23 2015May 27 2015

Publication series

NameApplication of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015

Other

Other37th International Symposium on Application of Computers and Operations Research in the Mineral Industry, APCOM 2015
CountryUnited States
CityFairbanks
Period5/23/155/27/15

Fingerprint

coalbed methane
prediction
Expert systems
simulation
expert system
Gases
Water
gas
Simulators
artificial neural network
simulator
Neural networks
Coal bed methane
Computer simulation
Testing
water
methodology

All Science Journal Classification (ASJC) codes

  • Geochemistry and Petrology
  • Computer Science Applications

Cite this

Rajput, V., Basel, E. D. K., & Ertekin, T. (2015). Production performance prediction and field development design tool for coalbed methane reservoirs: A neuro-simulation approach. In S. Bandopadhyay, S. Chatterjee, T. Ghosh, & K. V. Raj (Eds.), Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015 (pp. 930-938). (Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015). Society for Mining, Metallurgy and Exploration (SME).
Rajput, Vaibhav ; Basel, E. D.K. ; Ertekin, Turgay. / Production performance prediction and field development design tool for coalbed methane reservoirs : A neuro-simulation approach. Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015. editor / Sukumar Bandopadhyay ; Snehamoy Chatterjee ; Tathagata Ghosh ; Kumar Vaibhav Raj. Society for Mining, Metallurgy and Exploration (SME), 2015. pp. 930-938 (Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015).
@inproceedings{1f3ad01c10ef4cfda019f19356658b2e,
title = "Production performance prediction and field development design tool for coalbed methane reservoirs: A neuro-simulation approach",
abstract = "Implementation of numerical simulations for field development optimization can be overly demanding in terms of their time and manpower requirements. To overcome these problems, a methodology has been developed that can be used to predict production performance of a given field and perform field development studies with nominal manpower and computational requirements. Artificial neural networks (ANN) are used for development of expert systems for prediction of instantaneous and cumulative gas and water production, as well as for reservoir property prediction. A commercial reservoir simulator is employed for generation of database for training, validation and testing of these expert systems. Uncertainty in reservoir properties is taken into account by varying the reservoir parameters within an estimated range of values. Analysis of results obtained from trained networks showed error values of less than 3{\%} for prediction of gas and water production profiles (forward networks), while those that are obtained for prediction of reservoir characteristics gave error levels of 15-18{\%} (inverse networks). Forward networks were then used for optimization of field development based upon the criteria of maximizing the net present value (NPV) of a given field. Several case studies were carried out and analyzed.",
author = "Vaibhav Rajput and Basel, {E. D.K.} and Turgay Ertekin",
year = "2015",
month = "1",
day = "1",
language = "English (US)",
series = "Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015",
publisher = "Society for Mining, Metallurgy and Exploration (SME)",
pages = "930--938",
editor = "Sukumar Bandopadhyay and Snehamoy Chatterjee and Tathagata Ghosh and Raj, {Kumar Vaibhav}",
booktitle = "Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015",

}

Rajput, V, Basel, EDK & Ertekin, T 2015, Production performance prediction and field development design tool for coalbed methane reservoirs: A neuro-simulation approach. in S Bandopadhyay, S Chatterjee, T Ghosh & KV Raj (eds), Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015. Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015, Society for Mining, Metallurgy and Exploration (SME), pp. 930-938, 37th International Symposium on Application of Computers and Operations Research in the Mineral Industry, APCOM 2015, Fairbanks, United States, 5/23/15.

Production performance prediction and field development design tool for coalbed methane reservoirs : A neuro-simulation approach. / Rajput, Vaibhav; Basel, E. D.K.; Ertekin, Turgay.

Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015. ed. / Sukumar Bandopadhyay; Snehamoy Chatterjee; Tathagata Ghosh; Kumar Vaibhav Raj. Society for Mining, Metallurgy and Exploration (SME), 2015. p. 930-938 (Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015).

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

TY - GEN

T1 - Production performance prediction and field development design tool for coalbed methane reservoirs

T2 - A neuro-simulation approach

AU - Rajput, Vaibhav

AU - Basel, E. D.K.

AU - Ertekin, Turgay

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Implementation of numerical simulations for field development optimization can be overly demanding in terms of their time and manpower requirements. To overcome these problems, a methodology has been developed that can be used to predict production performance of a given field and perform field development studies with nominal manpower and computational requirements. Artificial neural networks (ANN) are used for development of expert systems for prediction of instantaneous and cumulative gas and water production, as well as for reservoir property prediction. A commercial reservoir simulator is employed for generation of database for training, validation and testing of these expert systems. Uncertainty in reservoir properties is taken into account by varying the reservoir parameters within an estimated range of values. Analysis of results obtained from trained networks showed error values of less than 3% for prediction of gas and water production profiles (forward networks), while those that are obtained for prediction of reservoir characteristics gave error levels of 15-18% (inverse networks). Forward networks were then used for optimization of field development based upon the criteria of maximizing the net present value (NPV) of a given field. Several case studies were carried out and analyzed.

AB - Implementation of numerical simulations for field development optimization can be overly demanding in terms of their time and manpower requirements. To overcome these problems, a methodology has been developed that can be used to predict production performance of a given field and perform field development studies with nominal manpower and computational requirements. Artificial neural networks (ANN) are used for development of expert systems for prediction of instantaneous and cumulative gas and water production, as well as for reservoir property prediction. A commercial reservoir simulator is employed for generation of database for training, validation and testing of these expert systems. Uncertainty in reservoir properties is taken into account by varying the reservoir parameters within an estimated range of values. Analysis of results obtained from trained networks showed error values of less than 3% for prediction of gas and water production profiles (forward networks), while those that are obtained for prediction of reservoir characteristics gave error levels of 15-18% (inverse networks). Forward networks were then used for optimization of field development based upon the criteria of maximizing the net present value (NPV) of a given field. Several case studies were carried out and analyzed.

UR - http://www.scopus.com/inward/record.url?scp=84954290815&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84954290815&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84954290815

T3 - Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015

SP - 930

EP - 938

BT - Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015

A2 - Bandopadhyay, Sukumar

A2 - Chatterjee, Snehamoy

A2 - Ghosh, Tathagata

A2 - Raj, Kumar Vaibhav

PB - Society for Mining, Metallurgy and Exploration (SME)

ER -

Rajput V, Basel EDK, Ertekin T. Production performance prediction and field development design tool for coalbed methane reservoirs: A neuro-simulation approach. In Bandopadhyay S, Chatterjee S, Ghosh T, Raj KV, editors, Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015. Society for Mining, Metallurgy and Exploration (SME). 2015. p. 930-938. (Application of Computers and Operations Research in the Mineral Industry - Proceedings of the 37th International Symposium, APCOM 2015).