Skip to Main Content

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 configurationModelCCR2RMSEMAEHidden neuron no.
MS1 GEP 0.511 0.629 0.194 0.078 – 
FFNN 0.319 0.426 0.385 0.162 
MS2 GEP 0.723 0.766 0.127 0.079 – 
FFNN 0.631 0.679 0.191 0.097 
MS3 GEP 0.759 0.817 0.152 0.085 – 
FFNN 0.813 0.850 0.126 0.062 
MS4 GEP 0.633 0.692 0.119 0.086 – 
FFNN 0.418 0.470 0.372 0.155 
MS5 GEP 0.814 0.874 0.112 0.088 – 
FFNN 0.862 0.885 0.104 0.059 
MS6 GEP 0.763 0.833 0.149 0.123 – 
FFNN 0.799 0.841 0.154 0.066 
Input configurationModelCCR2RMSEMAEHidden neuron no.
MS1 GEP 0.511 0.629 0.194 0.078 – 
FFNN 0.319 0.426 0.385 0.162 
MS2 GEP 0.723 0.766 0.127 0.079 – 
FFNN 0.631 0.679 0.191 0.097 
MS3 GEP 0.759 0.817 0.152 0.085 – 
FFNN 0.813 0.850 0.126 0.062 
MS4 GEP 0.633 0.692 0.119 0.086 – 
FFNN 0.418 0.470 0.372 0.155 
MS5 GEP 0.814 0.874 0.112 0.088 – 
FFNN 0.862 0.885 0.104 0.059 
MS6 GEP 0.763 0.833 0.149 0.123 – 
FFNN 0.799 0.841 0.154 0.066 

Close Modal

or Create an Account

Close Modal
Close Modal