IWA Publishing

From 203 patterns of the sharp-crested weir, 132 patterns were selected for training and 71 patterns were reserved for testing. Table 4 summarizes the statistical criteria of all models. From the statistics, the MS5-based GEP and FFNN models have the highest accuracy. Figure 3(b) presents the observed vs. simulated scour depth values.

Table 4

Testing statistics of the GEP and FFNN models for sharp edge overflow

Input configuration	Model	CC	R²	RMSE	MAE	Hidden neuron no.
MS1	GEP	0.511	0.629	0.194	0.078	–
MS1	FFNN	0.319	0.426	0.385	0.162	2
MS2	GEP	0.723	0.766	0.127	0.079	–
MS2	FFNN	0.631	0.679	0.191	0.097	3
MS3	GEP	0.759	0.817	0.152	0.085	–
MS3	FFNN	0.813	0.850	0.126	0.062	5
MS4	GEP	0.633	0.692	0.119	0.086	–
MS4	FFNN	0.418	0.470	0.372	0.155	3
MS5	GEP	0.814	0.874	0.112	0.088	–
MS5	FFNN	0.862	0.885	0.104	0.059	5
MS6	GEP	0.763	0.833	0.149	0.123	–
MS6	FFNN	0.799	0.841	0.154	0.066	3

Input configuration	Model	CC	R²	RMSE	MAE	Hidden neuron no.
MS1	GEP	0.511	0.629	0.194	0.078	–
MS1	FFNN	0.319	0.426	0.385	0.162	2
MS2	GEP	0.723	0.766	0.127	0.079	–
MS2	FFNN	0.631	0.679	0.191	0.097	3
MS3	GEP	0.759	0.817	0.152	0.085	–
MS3	FFNN	0.813	0.850	0.126	0.062	5
MS4	GEP	0.633	0.692	0.119	0.086	–
MS4	FFNN	0.418	0.470	0.372	0.155	3
MS5	GEP	0.814	0.874	0.112	0.088	–
MS5	FFNN	0.862	0.885	0.104	0.059	5
MS6	GEP	0.763	0.833	0.149	0.123	–
MS6	FFNN	0.799	0.841	0.154	0.066	3

View Large

This Feature Is Available To Subscribers Only