Forecasting Daily Precipitation Using Hybrid Model of Wavelet-Artificial Neural Network and Comparison with Adaptive Neurofuzzy Inference System (Case Study: Verayneh Station, Nahavand)

Table 5

Results and structures of ANFIS model.

Model	Structure	Membership function	EPOCH	RMSE	Test error	𝑅
1	D19	Trimf	20	0.0271	0.0264	0.6464
	D20	Trapmf	20	0.0271	0.0265	0.6326
	D21	Gbellmf	50	0.0268	0.0256	0.7835
	D22	Gaussmf	40	0.0269	0.0257	0.7757
	D23	Gauss2mf	40	0.0289	0.0265	0.6265
	D24	Pimf	40	0.0269	0.0257	0.7757
	D25	Dsigmf	40	0.0270	0.0259	0.7559
	D26	Psigmf	40	0.0270	0.0259	0.7559
2	D27	Trimf	20	0.0271	0.0263	0.6563
	D28	Trapmf	20	0.0272	0.0264	0.6453
	D29	Gbellmf	30	0.0269	0.0256	0.7806
	D30	Gaussmf	30	0.0269	0.0256	0.7826
	D31	Gauss2mf	40	0.0269	0.0257	0.7757
	D32	Pimf	40	0.0269	0.0256	0.7786
	D33	Dsigmf	40	0.0270	0.0256	0.7786
	D34	Psigmf	30	0.0270	0.0259	0.7759