Uncertainty visualization of remote sensing crop maps enriched at parcel scale: a contribution for a more conscious GIS dataset usage

© 2015 The Authors. Published by Taylor & Francis. Uncertainty is an inherent issue in all thematic maps, including those produced from remote sensing (RS) data. Factors such as the characteristics of the imagery used to obtain the map or the classification methods, among others, can contribute to differences in the level of uncertainty. Given that map accuracy is not spatially uniform and that confusion matrices do not resolve the issue, this paper proposes a methodology to visualize the spatial uncertainty of a crop map obtained through RS and enriched at parcel scale. The final map covers an area of 3323 ha represented at a scale of 1:35,000. The estimator used to show the classification uncertainty is ‘purity’, that is, the percentage of each parcel area occupied by the finally assigned category. This value is an indicator of misclassification probability analyzed at parcel scale, which is a more useful measure in real management than are per pixel approaches.