Evaluation of Different Machine Learning Models for Predicting Soil Erosion in Tropical Sloping Lands of Northeast Vietnam

Table 2

Performance metrics of five soil erosion prediction models.

Metrics	FKNN		ANN		SVM		LSSVM		RVM
	Mean	Std	Mean	Std	Mean	Std	Mean	Std	Mean	Std
Training phase
CAR (%)	100.00	0.00	92.72	0.95	96.21	0.71	93.02	0.69	92.22	0.86
AUC	1.00	0.85	0.97	0.00	0.97	0.01	0.94	0.01	0.98	0.00
TPR	1.00	0.00	0.90	0.01	0.95	0.01	0.88	0.01	0.90	0.02
FPR	0.00	0.00	0.05	0.01	0.03	0.01	0.02	0.01	0.05	0.01
FNR	0.00	0.00	0.10	0.01	0.05	0.01	0.12	0.01	0.10	0.02
TNR	1.00	0.00	0.95	0.01	0.97	0.01	0.98	0.01	0.95	0.01
Testing phase
CAR (%)	83.19	6.33	88.33	5.62	85.97	7.62	88.61	5.12	91.94	5.99
AUC	0.91	0.05	0.95	0.03	0.86	0.09	0.91	0.05	0.97	0.03
TPR	0.86	0.09	0.88	0.08	0.89	0.07	0.83	0.09	0.91	0.08
FPR	0.20	0.11	0.11	0.10	0.17	0.13	0.06	0.08	0.07	0.09
FNR	0.14	0.09	0.13	0.08	0.11	0.07	0.17	0.09	0.09	0.08
TNR	0.80	0.11	0.89	0.10	0.83	0.13	0.94	0.08	0.93	0.09