Using ANFIS and Neural Networks to Predict the Volume Percentage of Matrix and Fluid

Abstract

In the common methods to find percentage of lithology and fluids, well log information, petrophysical tests, and high-skill experts are needed. Therefore, designing a model that is able to evaluate the percentage of lithology using well log data without laboratory information will be very economical. Today, by using artificial neural networks, lithology can be predicted very well from the lowest information and time. Various artificial neuro-fuzzy inference systems and radial basis function and back propagation neural network were implied (about 1,500 accredited data and evaluated lithology and fluid volume percentages were available). In this article, first several kinds of features tested by artificial neuro-fuzzy inference systems model and finally neutron porosity (NPHI), conductive log (CT), resistivity log (RT), density (RHOB), natural gamma (GR), and photo electron (PE) logs were determined as the best logs to predict the percentage of lithology and fluid’s volume. Then these logs were used as input variable for radial basis function and back propagation neural network. In the second optimization, several training functions were implemented to select the best structure by lowest error. Comparison between targets and a network’s output data shows that neural networks are suitable tools for predicting the percentage of lithology and fluid’s volume, consuming less time and reducing cost.