Prediction of reservoir permeability using genetic algorithms

The determination of permeability is an example of many geological problems where laboratory-measured data is expensive and limited in quantity. We related permeability values to well logs. We used neural networks trained both with the popular backpropagation algorithm and with a genetic algorithm. The genetic training produced smaller errors and better generalization than backpropagation training on the same network topology. The cost includes,greater average computation time as well as,greater variation in computation time for the genetic training. The genetic training is robust and not sensitive to selection of the crossover and mutation parameters.