A fuzzy logic approach for the estimation of facies from wire-line logs

Abstract

A method based on fuzzy logic inference can be used to identify lithological and depositional facies from wire-line logs. Fuzzy logic is inherently well suited to characterizing vague and imperfectly defined knowledge, a situation encountered in most geological data. It can thus yield models that are simpler and more robust than those based on crisp logic. The method is simple, easy to comprehend, and robust. It also generates several confidence measures that can be used to assess the quality of the analysis. Several enhancements, including static and dynamic constraints, are discussed. The technique is tested here by applying it to predict the depositional facies of a cored well in a marine carbonate environment and comparing the output with the facies derived from core analysis. The two show considerable agreement, which indicates that this method can be an effective means of predicting the facies of uncored wells from their logs. The method has advantages when contrasted with other techniques that rely on multivariate statistics and neural networks. Compared to those techniques, this method is simpler, easier to retrain, more reproducible, noniterative, and more computer efficient.