A method of exploiting spatial information for improving classification rules: application to the construction of polygon-based land cover maps

This article proposes a method of exploiting spatial information to improve classification rules constructed by automated methods such as k-nearest ne ighbour or linear discriminant analysis. The method is intended for polygon -based, land cover type mapping using remote sensing information in a GIS. Our approach differs from contextual allocation methods used in lattice- or pixel-based mapping because it does not rely on spatial dependence models. Instead, the method uses a Bayes-type formula to modify the estimated post erior probabilities of group membership produced by automated classifiers. The method is found to substantially improve classification accuracy estima tes in areas where there is a moderate or greater degree of physiographic v ariation across the map extent.