Use of linguistic petrographical descriptions to characterise core porosity: contrasting approaches

There are many classification problems in petroleum reservoir characterisat ion, an example being the recognition of lithofacies from well log data. Da ta classification is not an easy task when the data are not of numerical or igin. This paper compares three approaches to classify porosity into groups (very poor, poor, fair, good) using petrographical characteristics describ ed in linguistic terms. The three techniques used are an expert system appr oach, a supervised clustering approach, and a neural network approach. From the results applied to a core data set in Australia, we found that the tec hniques performed best in decreasing order of their requirement for signifi cant user effort, for a low degree of benefit achieved thereby. (C) 2001 El sevier Science B.V. All rights reserved.