A Genetic Algorithm/neural Network Approach to Seismic Attribute Selection For Well Log Prediction Available to Purchase

Neural network prediction of well log data using seismic attributes is an important reservoir characterization technique because it allows extrapolation of log properties throughout a seismic volume. The strength of neural networks in pattern recognition is key in its success for delineating the complex nonlinear relationship between seismic attributes and log properties. This study presents a new method for choosing the neural network seismic attribute inputs using a genetic algorithm approach. The genetic algorithm attribute selection utilizes neural network training results to choose the optimal number and type of seismic attributes for porosity prediction. We applied the genetic algorithm feature selection method to the Stratton Field 3-D seismic data set to produce a porosity volume and predict reservoir continuity and stratigraphy within the C38 reservoir.