Table 4 The results of evaluating accuracy in training and test dataset.
From: GIS-based non-grain cultivated land susceptibility prediction using data mining methods
Models | Stage | Parameter | ||||
|---|---|---|---|---|---|---|
Sensitivity | Specificity | PPV | NPV | AUC | ||
GBM | Train | 0.89 | 0.85 | 0.86 | 0.89 | 0.95 |
Validation | 0.86 | 0.81 | 0.82 | 0.86 | 0.92 | |
XGB | Train | 0.98 | 0.94 | 0.93 | 0.97 | 0.98 |
Validation | 0.91 | 0.88 | 0.88 | 0.91 | 0.94 | |
PSO-GBM | Train | 0.95 | 0.92 | 0.93 | 0.98 | 0.97 |
Validation | 0.92 | 0.86 | 0.85 | 0.92 | 0.95 | |
PSO-XGB | Train | 0.98 | 0.95 | 0.94 | 0.99 | 0.99 |
Validation | 0.93 | 0.89 | 0.88 | 0.93 | 0.96 | |
