In this part, 62 data patterns (65% of all patterns) were used for training and 33 data patterns (35% of the patterns) were used for random testing. Table 3 represents the testing statistics for all nine ski-jump bucket scour depth models (fed with the aforementioned nine input configurations). The table clearly shows that the MB4 model has the highest accuracy. Figure 3(a) displays the observed and simulated scour depth values of GEP and FFNN models (fed with MB4 input configuration) for the testing stage.
Table 3

Testing statistics of the GEP and FFNN models for the ski-jump bucket

Input configurationModelCCR2RMSEMAEHidden neuron no.
MB1 GEP 0.291 0.370 0.071 0.051 – 
FFNN 0.112 0.181 0.084 0.056 2 
MB2 GEP 0.526 0.687 0.041 0.033 – 
FFNN 0.493 0.503 0.057 0.045 3 
MB3 GEP 0.758 0.821 0.032 0.028 – 
FFNN 0.169 0.294 0.091 0.052 3 
MB4 GEP 0.841 0.858 0.034 0.025 – 
FFNN 0.863 0.876 0.032 0.024 5 
MB5 GEP 0.532 0.637 0.046 0.036 – 
FFNN 0.456 0.585 0.059 0.035 5 
MB6 GEP 0.133 0.233 0.072 0.053 – 
FFNN 0.411 0.479 0.063 0.049 3 
MB7 GEP 0.788 0.839 0.038 0.029 – 
FFNN 0.769 0.845 0.038 0.032 3 
MB8 GEP 0.611 0.792 0.047 0.042 – 
FFNN 0.789 0.801 0.039 0.029 5 
MB9 GEP 0.813 0.830 0.039 0.032 – 
FFNN 0.501 0.513 0.072 0.047 7 
Input configurationModelCCR2RMSEMAEHidden neuron no.
MB1 GEP 0.291 0.370 0.071 0.051 – 
FFNN 0.112 0.181 0.084 0.056 2 
MB2 GEP 0.526 0.687 0.041 0.033 – 
FFNN 0.493 0.503 0.057 0.045 3 
MB3 GEP 0.758 0.821 0.032 0.028 – 
FFNN 0.169 0.294 0.091 0.052 3 
MB4 GEP 0.841 0.858 0.034 0.025 – 
FFNN 0.863 0.876 0.032 0.024 5 
MB5 GEP 0.532 0.637 0.046 0.036 – 
FFNN 0.456 0.585 0.059 0.035 5 
MB6 GEP 0.133 0.233 0.072 0.053 – 
FFNN 0.411 0.479 0.063 0.049 3 
MB7 GEP 0.788 0.839 0.038 0.029 – 
FFNN 0.769 0.845 0.038 0.032 3 
MB8 GEP 0.611 0.792 0.047 0.042 – 
FFNN 0.789 0.801 0.039 0.029 5 
MB9 GEP 0.813 0.830 0.039 0.032 – 
FFNN 0.501 0.513 0.072 0.047 7 
View Large
Figure 3
Figure 3. Observed vs. predicted scour depths testing stage of GEP and FFNN models for (a) ski-jump bucket, (b) sharp-crested weir, and (c) inclined slope controlled structure.
View largeDownload slide

Observed vs. predicted scour depths testing stage of GEP and FFNN models for (a) ski-jump bucket, (b) sharp-crested weir, and (c) inclined slope controlled structure.

Figure 3
Figure 3. Observed vs. predicted scour depths testing stage of GEP and FFNN models for (a) ski-jump bucket, (b) sharp-crested weir, and (c) inclined slope controlled structure.
View largeDownload slide

Observed vs. predicted scour depths testing stage of GEP and FFNN models for (a) ski-jump bucket, (b) sharp-crested weir, and (c) inclined slope controlled structure.

Close modal
Close Modal
This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy.
Accept