Table 8.

Results of ensembles modeling by combination of 80%/20% and raster resolution of 20 m.

Criteria	ADTree		RF		RS		BA		MB
	T	V	T	V	T	V	T	V	T	V
True positive	81	18	81	19	78	18	81	18	81	18
True negative	82	20	82	20	82	20	82	20	82	20
False positive	8	4	8	3	11	4	8	4	8	4
False negative	7	1	7	2	7	2	7	2	7	2
Sensitivity	0.920	0.947	0.920	0.905	0.918	0.900	0.920	0.900	0.920	0.900
Specificity	0.911	0.833	0.911	0.870	0.882	0.833	0.911	0.833	0.911	0.833
Accuracy	0.916	0.884	0.916	0.886	0.899	0.864	0.916	0.864	0.916	0.864
AUROC	0.967	0.903	0.987	0.937	0.972	0.926	0.974	0.926	0.988	0.934

T, training dataset; V, validation dataset.