Combining a Neural Network with a Genetic Algorithm and Particle Swarm Optimization for Permeability Estimation of the Reservoir

In this work, it is investigated how artificial neural network evolution with genetic algorithm and particle swarm optimization affects the efficiency and prediction capability of an artificial neural network. This strategy is applied to predict permeability of Mansuri Bangestan reservoir located in Ahwaz, Iran utilizing available geophysical well log data. The gradient-based back-propagation strategy is a local search technique and genetic algorithm and particle swarm optimization are global search one. The proposed algorithm combines the local searching ability of back-propagation strategy with the global searching ability of genetic algorithm and particle swarm optimization. For an evaluation purpose, the performance and generalization capabilities of genetic algorithm-back-propagation and particle swarm optimization-back-propagation are compared with back-propagation technique. The results demonstrate that hybrid genetic algorithm-back-propagation and particle swarm optimization-back-propagation outperforms the gradient descent-based neural network.