Skip to main content

Table 1 Validation results of the profile and presence/pseudo-absence models based on threshold-dependent criteria

From: Evolution of seasonal land surface temperature trend in pond-breeding newt (Neurergus derjugini) in western Iran and eastern Iraq

Model

Overall accuracy

Kappa

Sensitivity

Specificity

Bioclim

0.87

0.75

0.75

1.00

Domain

0.94

0.88

0.88

1.00

One-class SVM

0.93

0.87

0.87

1.00

BPANN

0.95

0.91

1.00

0.97

MaxEnt

0.97

0.92

1.00

0.95

MaxLIk

0.97

0.94

0.98

0.95

CART

0.97

0.94

0.95

0.98

Rough set

0.84

0.68

0.69

0.98

Two-class SVM

0.95

0.91

1.00

0.91

  1. Overall accuracy: overall accuracy is the rate of correctly classified cells; Kappa: normalizes the overall accuracy by the accuracy that might have occurred by chance alone; sensitivity: the probability that the model will correctly classify a presence; specificity: specificity is the probability that the model will correctly classify pseudo-absence