Generation and quantitative evaluation of interpretable maps in precision agriculture
Résumé
In this paper, an algorithm for the generation of interpretable maps yielding management zones in agriculture is presented. The key points are the definition of numerical zoning quality criteria that are used to guide a global optimization procedure based on quantile values. This makes it an alternative to classical zoning procedures based on local criteria, such as segmentation-based ones. The algorithm is applied to real yield data from precision agriculture.
Origine : Fichiers éditeurs autorisés sur une archive ouverte