Estimation of Porosity in Abu Rabah field using Artificial Neural Networks

Abstract

In recent years, artificial intelligence techniques and neural networks in particular, have gained popularity in solving complex nonlinear problems. Permeability, porosity and fluid saturation are three fundamental characteristics of reservoir systems that are typically distributed in a spatially non-uniform and non-linear manner.

In this context, porosity prediction from well log data is well-suited using neural networks and other computer-based techniques.

The present study aims to estimate formation porosity from digital well log data and experimental lab measurements on the core of Abu Rabah field using an artificial neural network (ANN) approach.  Five well log data were used as inputs in the ANN to predict porosity responses: Gamma Ray Log (GR), Deep Resistivity (Rt), Formation Density (DEN), Neutron Porosity (PHIN) and Density Porosity (PHID). Core porosity were used as target data in the ANN to test the prediction. The accuracy of the ANN approach was tested by regression plots of predicted values of porosity with core porosity, and it was higher than 98%. This excellent matching of core data and predicted values reflects the accuracy of the ANN technique and its usability as a fast and accurate method for the prediction of reservoir properties and in reservoir modeling and characterization.