A fusion of Functional Networks and Type-2 Fuzzy Logic for the characterization of oil and gas reservoirs

This paper presents a hybrid model consisting of a fusion of Functional Networks and Type-2 Fuzzy Logic. The model capitalizes on the capability of Functional Networks, using its least square fitting algorithm, to reduce the dimensionality of the input data by selecting the most relevant variables for the prediction of porosity and permeability of oil and gas reservoirs. It also attempts to improve the performance of Type-2 Fuzzy Logic whose complexity is increased and performance degraded with increased dimensionality of input data. The Functional Networks block was used to select the dominant variables from six datasets. The dimensionally-reduced datasets were then divided into training and testing subsets using the stratified sampling approach. Hence, the Type-2 Fuzzy Logic block is trained and tested with the best and dimensionally-reduced variables from the input data. The results showed that the hybrid model performed better in terms of training and testing with higher correlation coefficients, lower root mean square errors and reduced execution times than the original Type-2 Fuzzy Logic system. This work has confirmed the possibility and bright prospect for more hybrid models with better performance indices.