Identification and Disease Index Inversion of Wheat Stripe Rust and Wheat Leaf Rust Based on Hyperspectral Data at Canopy Level
Table 2
The results of SVM models for disease identification.
Model
Optimal parameters
Sample category
Training set
Testing set
Identification accuracy for each category/%
Overall identification accuracy/%
Identification accuracy for each category/%
Overall identification accuracy/%
Model 1
32
0.125
Healthy wheat Wheat in incubation period of stripe rust Wheat in diseased period of leaf rust Wheat in incubation period of leaf rust Wheat in diseased period of leaf rust
98.33 93.33 97.81 86.67 98.97
97.18
100.00 20.00 93.33 80.00 96.67
78.00
Model 2
16
0.5
Healthy wheat Wheat in incubation period of stripe rust Wheat in diseased period of stripe rust Wheat in incubation period of leaf rust Wheat in diseased period of leaf rust
94.29 100.00 100.00 100.00 100.00
99.67
100.00 86.67 63.33 73.33 86.67
82.00
Model 3
0.25
0.125
Healthy wheat Wheat in incubation period of stripe rust Wheat in diseased period of stripe rust Wheat in incubation period of leaf rust Wheat in diseased period of leaf rust
88.33 82.22 67.15 86.67 88.21
82.89
96.67 40.00 40.00 76.67 90.00
68.67
Note: Model 1 was the SVM model for disease identification built based on the first group of spectral features, Model 2 was the SVM model for disease identification built based on the second group of spectral features, and Model 3 was the SVM model for disease identification built based on the third group of spectral features.