Crop health condition monitoring based on the identification of biotic and abiotic stresses by using hierarchical self-organizing classifiers

Hyperspectral signatures can provide abundant information regarding health status of crops; however it is difficult to discriminate between biotic and abiotic stress. The case of simultaneous occurrence of yellow rust disease symptoms and nitrogen stress was investigated by using hyperspectral features. In this study, the technique that was developed used a hybrid classification scheme consisting of Hierarchical Self Organizing Classifiers. Three different architectures were considered: Counterpropagation Artificial Neural Networks, Supervised Kohonen Networks and XY-Fusion. The results of biotic and abiotic stress identification appear to be promising, reaching more than 95% for all three architectures.