Intelligent reservoir characterization (iresc)

Abstract

In this study, a new integrated methodology is developed to identify the nonlinear relationship and mapping between 3D seismic data, production log and is applied to producing field. The method uses conventional techniques such as geostatistical and classical pattern recognition [Aminzadeh, F. et al., (1984/85)] in conjunction with modern techniques such as soft computing (neurocomputing, fuzzy logic, genetic computing, and probabilistic reasoning) [Nikravesh, M. et al., (1998), (1997)]. An important task of our research is to use clustering techniques recognize the optimal location of a new well to be drilled based on 3D seismic data and available production log/data or other viable logs. The classification task is accomplished in three ways; 1) k-means clustering, 2) fuzzy clustering, and 3) neural network clustering to recognize the similarity cubes. Then the relationship between each cluster and production log is recognized around the wellbore and the results are used to reconstruct and extrapolate the production log away from the wellbore. This advanced 3D seismic and log analysis and interpretation can be used to predict; 1) mapping between production data and seismic data, 2) reservoir connectivity based on multiattributes analysis, 3) pay zone estimation, and 4) optimum well placement.