The Fracture Network Modeling in Naturally Fractured Reservoirs Using Artificial Neural Network Based on Image Loges and Core Measurements

Abstract

High gas production from the Dashtak formation of Tabnak hydrocarbon field in Fars province, Iran, indicates the presence of natural fractured reservoir whose production potential is dominated by the structural fracture. In this field among 30 wells distributed over the study area, 57 percent have image logs (17 wells) and 3 are core wells with core length of 112m. Observations of natural fractures in core or image logs typically give limited information on orientation, aperture and intensity. Because of the sparseness of well bore intersections of fractures, data analysis results in incomplete statistical characterization of the fracture population, leaving interwell characterization almost impossible. Using basic fracture mechanics models and a novel core-testing technique, we propose that the fundamental shape of fracture parameter distributions can be predicted, and that there is a characteristic, quantifiable relationship between fracture length, spacing and aperture. A nonlinear simulation and assessment model of reservoir fracturing was established using the artificial neural network (ANN) technology to simulate the structure and function of the neural network (NN) of the human brain with engineering technology. The developed nonlinear modeling and forecasting system was used to assess and forecast the reservoir fracture distribution in Tabnak. The correlation between observed and predicted fracture density for training, validation and test data were 0.92, 0.86 and 0.88 percent respectively. The results of this study provided useful and essential information for scientific researches in these areas and production hydrocarbon rates assessment. W ith this information, fracture distribution model and reservoir productivity can be estimated for the purpose of flow simulation in a fractured reservoir.