Categorizing quarry blocks as exploitable and non-exploitable for facing and building stones needs to apply multivariate geostatistical methods such as cokriging or to generate factors which are spatially independent and consequently run kriging estimation. There are various methods for generating spatially independent factors such as principal component analysis. But this method cannot produce factors which are totally independent, so in this study an orthogonalization method, independent component analysis, is introduced as a novel tool in multivariate geostatistics and is used to find spatially independent factors. The theory of a new estimating method, independent component kriging is presented and applied to an andesite quarry located in Ankara, Turkey. One level of the quarry is chosen to be a test area from which 108 rock samples are taken at 20 m regular intervals. The rock samples are tested for some of the mechanical properties of andesite that control the economy of the extraction process. Then the application area is divided into 1544 square blocks and the newly developed estimation method is used for estimating unknown values of variables at unsampled locations. Finally, the blocks are classified as exploitable and non-exploitable regarding TS 10835 standards. (C) 2012 Elsevier Ltd. All rights reserved.