Sandstone Reservoirs Porosity and Water Saturation Estimation Using Functional Network Techniques

Abstract

An accurate determination of porosity and water saturation is vital for evaluating an oil reserve and proposing a development plan for developed sandstone reservoir. The objective of this study is to provide an improved intelligent approach the use of functional networks to estimate porosity and water saturation from well log using real field data in sandstone reservoir where it becomes difficult to acquire reliable well logging data. The proposed methodology makes use of appropriate well logs and core measurements. A portion of the data available was retained for verification of the prediction of water saturation and porosity. This paper presents a novel method for estimating these two important parameters directly from conventional well measurements. The recently proposed Functional Networks technique is applied for rapid and accurate prediction of these parameters, using six and five basic well log measurements as data for estimating porosity and water saturation respectively. Functional network is a generalization of the conventional Feed Forward Neural Networks, which overcome many of the drawbacks of the conventional neural network techniques. The proposed functional network was trained using data gathered from two wells in the Middle East region. Results obtained from this case study of sandstone reservoir using the proposed intelligent technique have shown to be fast and accurate referring to core samples porosity and water saturation values.