In this paper, an integrated procedure was adopted to obtain accurate lithofacies classification to be incorporated with well log interpretations for a precise core permeability modeling. Probabilistic neural networks (PNNs) were employed to model lithofacies sequences as a function of well logging data in order to predict discrete lithofacies distribution at missing intervals. Then, the generalized boosted regression model (GBM) was used as to build a nonlinear relationship between core permeability, well logging data, and lithofacies. The well log interpretations that were considered for lithofacies classification and permeability modeling are neutron porosity, shale volume, and water saturation as a function of depth; however, the measured discrete lithofacies types are sand, shaly sand, and shale. Accurate lithofacies classification was achieved by the PNN as the total percent correct of the predicted discrete lithofacies was 95.81%. In GBM results, root-mean-square prediction error and adjusted R-square have incredible positive values, as there was an excellent matching between the measured and predicted core permeability. Additionally, the GBM model led to overcome the multicollinearity that was available between one pair of the predictors. The efficiency of boosted regression was demonstrated by the prediction matching of core permeability in comparison with the conventional multiple linear regression (MLR). GBM led to much more accurate permeability prediction than the MLR.

An integrated multivariate statistics procedure was adopted for the accurate Lithofacies classification prediction to be incorporated with well log attributes into core permeability modeling. Logistic Boosting Regression and Generalized Linear Modeling were adopted for Lithofacies Classification and core permeability estimation, respectively. Logistic Boosting Regression (LogitBoost) was used to model the lithofacies sequences given well log and core data to predict the discrete lithofacies distribution at missing intervals. In this paper, the permeability modeling and estimation was validated through bootstrapping and cross-validation. The well log interpretations that were considered for lithofacies classification and permeability modelling are neutron porosity, shale volume, and water saturation as a function of depth. The measured discrete lithofacies types include three main lithology types: sand, shaly sand, and shale. LogitBoost was adopted for modelling and prediction the discrete Lithofacies distribution for the entire reservoir depth that was then incorporated into permeability modelling. Next, GLM was applied to create the relationship between core permeability and the explanatory variables of well log and Lithofacies. In GLM results, the accuracy of the entire permeability modelling was assessed by K-fold cross-validation that showed significant reduction in prediction variance. GLM has also led to overcome the multicollinearity that was available between shale volume and water saturation. Bootstrapping was then adopted, as an approval tool to ensure that there is no doubt about the validity and accuracy of the fitted GLM model. Bootstrapping simply re-samples the data into a specific number of times and recalculates the variable given each sample. The bootstrapping was implemented for Adjusted R-squared of the overall GLM approach.