Characterization of Sealing and Partially Communicating Faults in Dual-Porosity Gas Reservoirs Using Artificial Neural Network

Open Access
Toktabolat, Zhazar
Graduate Program:
Petroleum and Natural Gas Engineering
Master of Science
Document Type:
Master Thesis
Date of Defense:
May 09, 2012
Committee Members:
  • Turgay Ertekin, Thesis Advisor
  • Sealing and Partially Communicating Faults
  • Dual-Porosity Gas Reservoir
  • Artificial Neural Network
When unconventional hydrocarbon sources are added to the potential resources, the expansion of petroleum industry becomes a vast opportunity. The transient pressure analysis of gas wells in low permeability naturally fractured (tight gas and shale gas) reservoirs have gained wide interest among reservoir modelers, and various formation evaluation methods have been developed. In this work, the combination of analytical model and numerical reservoir simulator are used to generate and simulate a large number of hypothetical reservoirs which encompass wide range of dual porosity tight systems. The framework of this study is to convert observed measurements of reservoir data into characteristic information about the system that we are interested in. Artificial neural network (ANN) technology is utilized in mapping/interpolating the non-linear complex relationship between observed measurements and reservoir characteristics. The proposed ANN methodology is applied towards analyzing the pressure transient measurements collected from isotropic and anisotropic faulted dual-porosity gas reservoirs, as an inverse solution to formation characteristics, such as the permeability and porosity of the fracture and matrix systems, distance to the fault, orientation of the fault with respect to the principal flow directions, and sealing capacity of the fault are predicted using the reservoir fluid, rock, and bottom-hole pressure as the principal inputs. The main focus of this study is to develop a suitable network to obtain accurate prediction about desired reservoir characteristics of dual-porosity tight gas systems with a fault, and demonstrate the efficient processing power of ANN on this class of reservoir problems.