Skip to main content

View full-text article in PMC

. 2018 Nov 5;18(11):3777. doi: 10.3390/s18113777

Table 3.

Model performance using training dataset and ADTree algorithm.

Raster Resolution (m)	10				20
Sample Size (%)	60%/40%	70%/30%	80%/20%	90%/10%	60%/40%	70%/30%	80%/20%	90%/10%
Statistic Measures	60%/40%	70%/30%	80%/20%	90%/10%	60%/40%	70%/30%	80%/20%	90%/10%
TP	60	77	85	91	55	72	81	89
TN	47	81	76	89	48	78	82	92
FP	7	0	4	9	12	9	8	11
FN	20	4	13	11	19	3	7	8
SST %	0.750	0.951	0.867	0.892	0.743	0.960	0.920	0.918
SPF %	0.870	1.000	0.950	0.908	0.800	0.897	0.911	0.893
ACC %	0.799	0.975	0.904	0.900	0.769	0.926	0.916	0.905
Kappa	0.597	0.950	0.809	0.800	0.537	0.851	0.831	0.810
RMSE	0.351	0.157	0.291	0.300	0.407	0.239	0.273	0.298