Using the artificial neural networks for prediction and validating solar radiation

Journal of the Egyptian Mathematical Society

Table 3 The statistical data for training and testing of the second method

Cites	Model	η	α	RMSE	MِAPE	MABE	r	R²	Rank
For training
Cairo	1	0.01	0.7	1.056	4.603	0.807	0.9846	0.9998	6
	2	0.01	0.9	1.044	4.623	0.804	0.9849	0.9997	5
	3	0.2	0.7	1.017	4.453	0.772	0.9857	0.9998	4
	4	0.2	0.9	0.999	4.316	0.748	0.9865	0.9998	3
	5	0.3	0.7	0.996	4.260	0.737	0.9869	0.9988	2
	6	0.3	0.9	0.970	4.243	0.713	0.9890	0.9731	1
Borg El-Arab	1	0.01	0.7	1.046	4.976	0.786	0.9888	0.9998	5
	2	0.01	0.9	1.005	4.710	0.750	0.9897	0.9998	3
	3	0.2	0.7	0.947	4.364	0.699	0.9912	0.9998	2
	4	0.2	0.9	0.915	4.215	0.675	0.9931	0.9999	1
	5	0.3	0.7	1.046	4.972	0.791	0.9889	0.9996	5
	6	0.3	0.9	1.013	4.783	0.765	0.9895	0.9997	4
Aswan	1	0.01	0.7	1.426	5.307	1.118	0.9685	0.9998	5
	2	0.01	0.9	1.439	5.383	1.134	0.9683	0.9998	6
	3	0.2	0.7	1.398	5.172	1.082	0.9699	0.9999	3
	4	0.2	0.9	1.419	5.386	1.126	0.9710	0.9998	4
	5	0.3	0.7	1.324	5.204	1.083	0.9723	0.9999	2
	6	0.3	0.9	1.282	5.025	1.034	0.9815	0.9999	1
For testing
Cairo	1	0.01	0.7	2.868	12.937	2.187	0.8816	0.9997	5
	2	0.01	0.9	2.703	12.079	2.051	0.8957	0.9996	3
	3	0.2	0.7	2.754	12.262	2.028	0.8967	0.9998	4
	4	0.2	0.9	3.099	13.833	2.344	0.8951	0.9999	6
	5	0.3	0.7	2.596	11.506	1.952	0.9043	0.9999	2
	6	0.3	0.9	2.245	10.684	1.715	0.9223	0.9999	1
Borg El-Arab	1	0.01	0.7	2.815	13.368	2.161	0.9247	0.9999	5
	2	0.01	0.9	2.839	13.423	2.116	0.9249	0.9999	6
	3	0.2	0.7	2.688	12.806	2.078	0.9321	0.9997	4
	4	0.2	0.9	2.624	12.444	2.018	0.9348	0.9998	2
	5	0.3	0.7	2.674	12.790	2.020	0.9352	0.9998	3
	6	0.3	0.9	2.470	11.466	1.878	0.9476	0.9999	1
Aswan	1	0.01	0.7	1.655	5.892	1.207	0.9490	0.9997	6
	2	0.01	0.9	1.630	5.885	1.194	0.9500	0.9999	5
	3	0.2	0.7	1.559	5.669	1.188	0.9550	0.9999	2
	4	0.2	0.9	1.597	5.962	1.195	0.9513	0.9998	4
	5	0.3	0.7	1.575	5.821	1.210	0.9578	0.9999	3
	6	0.3	0.9	1.439	5.282	1.180	0.9655	0.9999	1