Mapping spatial distribution of land cover classification errors

Abstract

Land cover classification accuracy assessments are frequently limited to an error matrix, which derived from location-independent measures and consequently doesn't provide any information about the spatial distribution of the error. The objective of this work is to present a methodology for mapping the spatial distribution of classification errors based on stochastic simulation and that takes into account the spatial continuity of each land cover class errors. It is proposed to use SIS with varying local means to map the distribution of classification errors and the associated uncertainty. Local means are previously obtain through indicator kriging estimation for each thematic class. The results shown that this methodology based on geostatistical stochastic simulation succeeded to map the spatial distribution of classification errors taking into account the spatial continuity of each land cover class errors.