A Local Linear Neurofuzzy Model for the Prediction of Permeability from Well-log Data in Carbonate Reservoirs

In this paper a new approach for the prediction of permeability based on recently developed neurofuzzy interpretation of locally linear models, which have led to the introduction of intuitive incremental learning algorithm called locally linear model tree (LOLIMOT) is presented. The incremental learning algorithm initializes the model with an optimal linear least squares estimation and automatically increases the number of neurons in each epoch. The model is optimized for the number of neurons to avoid overfitting and to provide maximum generalization by considering the error index of validation sets during training. The effectiveness of the methodology is demonstrated with a case study in one of the carbonate reservoirs of Iran. Special core analysis from one well that located in the center of the field provide the data for the learning task. Core permeability and well log data from second well provide the basis for model validation. Numerical simulation results show that the neurofuzzy model is more accurate than the conventional multilinear regression analyses (MRA) for the prediction of permeability.