1
Department of Petroleum and Natural Gas Engineering,Xilinx Inc.
2
Department of Petroleum and Natural Gas Engineering,West Virginia University
Abstract
This paper presents the utilization of a newly developed technique for development of a
proxy model in reservoir simulation studies to be used in uncertainty analysis on a Coalbed Methane
(CBM) reservoir. This technique uses Arti cial Neural Networks (ANN) in order to build a Surrogate
Reservoir Model (SRM). An SRM is a replica of the full- eld reservoir model that mimics the behavior
of the reservoir. A small number of realizations of the reservoir are required to develop the SRM. This
is a key di erence between the SRM technique and other techniques in the literature, such as developing
a Response Surface Model using Experimental Design technique or using Reduced Models. Once trained,
SRMs can make thousands of simulation runs in a matter of seconds. The high speed of the SRM enables
the engineer to exhaustively explore the solution space and perform uncertainty analysis. During the
development process of SRM, Key Performance Indicators (KPIs) are identi ed. KPIs are the reservoir
parameters that have the most in
uence on the desired objective of the simulation study.
Jalali, J. , Gaskari, R. , & Mohaghegh, S. (2010). Coalbed Methane Reservoir Simulation and Uncertainty Analysis with Arti cial Neural Networks. Scientia Iranica, 17(1), -.
MLA
J. Jalali; R. Gaskari; Sh.D. Mohaghegh. "Coalbed Methane Reservoir Simulation and Uncertainty Analysis with Arti cial Neural Networks", Scientia Iranica, 17, 1, 2010, -.
HARVARD
Jalali, J., Gaskari, R., Mohaghegh, S. (2010). 'Coalbed Methane Reservoir Simulation and Uncertainty Analysis with Arti cial Neural Networks', Scientia Iranica, 17(1), pp. -.
CHICAGO
J. Jalali , R. Gaskari and S. Mohaghegh, "Coalbed Methane Reservoir Simulation and Uncertainty Analysis with Arti cial Neural Networks," Scientia Iranica, 17 1 (2010): -,
VANCOUVER
Jalali, J., Gaskari, R., Mohaghegh, S. Coalbed Methane Reservoir Simulation and Uncertainty Analysis with Arti cial Neural Networks. Scientia Iranica, 2010; 17(1): -.
)