Analysis of plot-level volume increment models developed from machine learning methods applied to an uneven-aged mixed forest

Table 3 Characteristics of RBF and MLP-based ANNs and associated metrics for model evaluation

Index	Structure	Algorithm	Error function	Hidden activation	R²	RMSE	%RMSE	BIAS	%BIAS
1	MLP 7-12-1	BFGS 11	SOS	Logistic	0.928	0.24	10.81	0.011	0.5394
2	MLP 7-5-1	BFGS 14	SOS	Identity	0.930	0.21	9.451	0.016	0.7316
3	MLP 7-9-1	BFGS 11	SOS	Identity	0.930	0.21	9.451	0.014	0.6685
4	MLP 7-10-1	BFGS 16	SOS	Identity	0.926	0.24	10.810	0.007	0.3391
5	MLP 7-11-1	BFGS 11	SOS	Tanh	0.936	0.19	8.558	0.004	0.2021
6	RBF 7-24-1	RBFT	SOS	Gaussian	0.862	0.29	13.063	0.009	0.3132
7	RBF 7-30-1	RBFT	SOS	Gaussian	0.893	0.25	10.810	0.023	1.0520
8	RBF 7-27-1	RBFT	SOS	Gaussian	0.861	0.28	12.6126	0.039	1.7651
9	RBF 7-30-1	RBFT	SOS	Gaussian	0.858	0.26	11.711	0.006	0.2926
10	RBF 7-29-1	RBFT	SOS	Gaussian	0.901	0.27	12.162	0.018	0.852

ISSN: 1297-966X