LAUSR

Since wave overtopping is a very complex phenomenon and is sensitive to hydraulic and structural parameters, hydraulic model tests have been used to estimate the wave overtopping rates at coastal structures. Efforts have also been made toward developing empirical formulas and machine learning models based on a large amount of accumulated data, e.g., the EurOtop formulas and Artificial Neural Network (ANN) models based on the CLASH database. In this study, new machine learning formulas for inclined seawalls are derived by using the Group Method of Data Handling (GMDH) algorithm with the CLASH and new EurOtop datasets. Because the GMDH formulas are more complex than other empirical formulas, an EXCEL calculator is provided so that engineers can easily use the formulas. The GMDH formulas are shown to be more accurate than other empirical formulas and equally accurate as the EurOtop-ANN model. The estimation errors of 95% confidence interval and the range of 95% prediction error are also given. The sensitivity analysis of the derived formulas shows that the parameters that more influence the wave overtopping rate are in the order of crest freeboard, structure slope, wave period, and seabed slope.