Search

Abstract: Principal component analysis (PCA) is frequently used in geosciences for information extraction. In many applications, masking PCA has been used to create subsets of samples or sub-areas to enhance the effect of the main objects of interest. In this paper we suggest how the representativeness of samples or pixels can be quantified using a fuzzy membership function based on fuzzy set theory. In this new method, the relative importance of pixels or samples can be taken into account using a multivariate statistical method such as PCA. A Fuzzy Masking PCA is proposed and implemented in GeoDAS GIS on the basis of a spatially weighted PCA (SWPCA). This paper introduces the mathematical treatment of the fuzzy masking PCA and follows a case study of identifying the locations of intrusive bodies from geochemical data in the Gejiu mineral district in Yunnan, China. Power-law functions based on the inverse distance from mapped felsic intrusions are applied as weighting functions in FMPCA. The results indicate that fuzzy mask PCA increases the signal-noise ratio of the component representing igneous intrusions and decreases the influence of sedimentary rocks. The areas delineated as potential areas for new intrusions (including buried intrusions) are valuable guides for Sn mineral prospecting. [Copyright &y& Elsevier]