A total entropy model of spatial data uncertainty

Abstract

Uncertainty is inherent in spatial data and spatio-temporal phenomena. Spatial data uncertainty generally refers to error, inexactness, fuzziness and ambiguity. The goals of research on spatial data uncertainty are to investigate how uncertainties arise, or are created and propagated in the spatial data process. Based on information theory, considering the characteristics of randomicity of positional data and fuzziness of attribute data and taking entropy as a measure, this paper proposes the stochastic entropy model of spatial positional data uncertainty and fuzzy entropy model of spatial attribute data uncertainty. Usually, both randomicity and fuzziness exist in spatial data simultaneously, so their co-uncertainty is also investigated and quantified in this paper. A novel spatial data uncertainty measure, total entropy, is presented. Total entropy can be used as a uniform measure to quantify the total spatial data uncertainty caused by stochastic uncertainty and fuzzy uncertainty.