Identification and Disease Index Inversion of Wheat Stripe Rust and Wheat Leaf Rust Based on Hyperspectral Data at Canopy Level

Table 3

The results of NN models for identification of wheat stripe rust and wheat leaf rust.

Model	Sample category	Training set		Testing set
		Identification accuracy; for each category/%	Overall identification; accuracy/%	Identification accuracy; for each category/%	Overall identification; accuracy/%
Model 4	Wheat in diseased period of stripe rust	100.00	100.00	100.00	100.00
	Wheat in diseased period of leaf rust	100.00		100.00
Model 5	Healthy wheat	100.00	100.00	100.00	92.22
	Wheat in incubation period of stripe rust	100.00		93.33
	Wheat in incubation period of leaf rust	100.00		83.33

Note. Model 4 was the NN model built based on the remaining data after deleting the spectra with the disease indices equal to 0 (including the spectra of healthy wheat and the spectra of wheat in the incubation period) from the first group of spectral features, and Model 5 was the KNN model built based on the remaining data after deleting the spectra of wheat in the diseased period from the second group of spectral features.