Making the lithology log by Clustering-Estimation approach in the wells of an oil field in South of Iran

Reservoir lithology determination is one of the main studies used for well correlation and analyzing productive zones of the reservoir. The best way for lithology determination is using core and cutting information. Nevertheless, in most wells these data is not complete and continual, so in these cases usually use well logging for lithology estimation. The purpose of this paper is representing accurate method for lithology estimation of petrophysical well data with Clustering-Estimation approach. This method has been generalized according to one well from one of the oil fields in South of Iran that contains core data. Then this method is generalized in uncored wells. Clustering is used as a way for grouping well data in homogeneous lithology clusters Afterward, percentage of mineral is estimated in each of these clusters. The regression coefficients are calculated 92.93% and 74.99% between real and estimated data respectively for calcite and dolomite in one of the wells. The results with high accuracy show the generalization of this method.