Integrating Soft Computing Classification Technique For Linguistic Data in a Petroleum Engineering Application

There are many classification problems in petroleum reservoir characterization, an example being the recognition of lithofacies from well log data. Data classification is not an easy task when the data are not of numerical origin. This paper compares a number of approaches to classify porosity into groups (e.g. very poor, poor, fair, etc.) using petrographical characteristics, which are often described in linguistic statements in core analysis.