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

Abstract

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. ARTICLE HISTORY

A new approach to characterising and predicting crop rotations using national-scale annual crop maps

“…The framework could be augmented to investigate rotational complexity, such as crop or rotation flexibility (Castellazzi et al, 2008) or transitions between rotations. Rotation mapping and predictions could also be refined by introducing crop classification certainty (Serra and Pons, 2016), agronomic rules or expertise (Bachinger and Zander, 2007;Detlefsen and Jensen, 2007;Dogliotti et al, 2003;Schönhart et al, 2011;Sharp et al, 2021;Xiao et al, 2014), or a metric for agricultural land capability and other biophysical covariates (e.g. Goodwin et al, n.d.;Socolar et al, 2021).…”