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

Table 2

Results and structures of WANN model.

Structure	Mother wavelet	Levels	MAE	MSE	𝑅
D1	Haar	2	0.0037	0.00003	0.8863
D2	Haar	3	0.0034	0.00026	0.9392
D3	Haar	4	0.0034	0.00036	0.9321
D4	Haar	5	0.0031	0.00002	0.9502
D5	Haar	6	0.0035	0.00067	0.9001
D6	Haar	7	0.0032	0.00032	0.9404
D7	Db4	2	0.0032	0.00022	0.9482
D8	Db4	3	0.0033	0.00026	0.9343
D9	Db4	4	0.0035	0.00029	0.9016
D10	Db4	5	0.0033	0.00031	0.9333
D11	Db4	6	0.0036	0.00037	0.8915
D12	Db4	7	0.0031	0.00049	0.9413
D13	Sym3	2	0.0039	0.00041	0.8704
D14	Sym3	3	0.0043	0.00045	0.8516
D15	Sym3	4	0.0039	0.00036	0.8711
D16	Sym3	5	0.0035	0.0003	0.8993
D17	Sym3	6	0.0035	0.0004	0.9031
D18	Sym3	7	0.0036	0.00034	0.8918