Correction to: Application of fuzzy logic and neural networks for porosity analysis using well log data: an example from the Chanda Oil Field, Northwest Pakistan

Fuzzy logic (FL) and neural network (NNs) methods are commonly applied in a variety of areas the petroleum industry. The area hydrocarbon exploration has seen greatest advancement soft-computing technologies including FL, NNs. In this study, FL NNs have been to log data from Chanda Oil Field, northwest Pakistan, for porosity (PHIT) prediction. input dataset study included four known logs, gamma ray (GR), neutron (NPHI), density (RHOB), sonic (DT) two wells drilled Field. For model, ten numbers bins were selected. closeness fit (Cfit) curves calculated considering most, second most likely curves. weighted average final probability Pi, or solution, was also computed. curve histogram distribution set bin cross plots generated using fuzzy model. Gaussian membership function best well analyzed. models show Cfit fall range 92–100% Chanda-1 Deep-1 with standard deviations 1.268 1.396, respectively. Datta Formation reservoir interval. model trained back propagation (BP) algorithm. reveals Cfit_nn 85–100% 0.012 0.025. results reveal very good match between predicted modeling analyses methods. These techniques can be reduce uncertainty determining PHIT wells. comparison, multiple linear regression (MLR) analysis performed same studied coefficient determination (R2) derived (PHIT_ml) 0.5727 0.7988, 0.6256 0.8527 (PHIT_nn) values MLR (PHIT_mlr) 0.512 0.338, high R2 indicate as reliable prediction compared method. application indicates that these better determine an accuracy rivals other methods, such those based on statistics MLR. corresponding correlation obtained through comparison synthesized real values. comparisons measured parameters different indicated both successful synthesizing logs. This paper reliable, giving realistic combination GR, RHOB, NPHI DT