Table 5 Concordance coefficients for classification (Kappa) and regression (Lin’s ccc) models for correspondence between observed and predicted outcomes of artificial neural networks (ANN), support-vector machine (SVM), random forest (RF), decision trees (DT), logistic regression (LGR), and linear regression (LNR) machine-learning models used to characterize the effect of leaf wetness and incubation temperature on incidence of Sclerotinia stem rot of canola and dry bean.
Study | Models | Kappa | ccc |
|---|---|---|---|
Canola | ANN | 0.75 | 0.94 |
RF | 0.68 | 0.87 | |
DT | 0.51 | 0.86 | |
LGR | 0.50 | – | |
LNR | – | 0.53 | |
SVM | 0.73 | 0.49 | |
Dry bean | ANN | 0.83 | 0.98 |
RF | 0.70 | 0.95 | |
DT | 0.67 | 0.94 | |
LGR | 0.83 | – | |
LNR | – | 0.86 | |
SVM | 0.80 | 0.80 |