Soft computing: tools for intelligent reservoir characterization (IRESC) and optimum well placement (OWP)

Abstract

An integrated methodology has been developed to identify nonlinear relationships and mapping between 3-D seismic data and production log data. This methodology has been applied to a producing field. The method uses conventional techniques such as geostatistical and classical pattern recognition in conjunction with modern techniques such as soft computing (neuro-computing, fuzzy logic, genetic computing, and probabilistic reasoning). An important goal of our research is to use clustering techniques to recognize the optimal location of a new well based on 3-D seismic data and available production-log data. The classification task was accomplished in three ways; (1) k-mean clustering, (2) fuzzy c-means clustering, and (3) neural network clustering to recognize similarity cubes. Relationships between each cluster and production-log data can be recognized around the well bore and the results used to reconstruct and extrapolate production-log data away from the well bore. This advanced technique for analysis and interpretation of 3-D seismic and log data can be used to predict: (1) mapping between production data and seismic data, (2) reservoir connectivity based on multi-attribute analysis, (3) pay zone estimation, and (4) optimum well placement.