Derivation of a New Model for Prediction of Wave Overtopping at Rubble Mound Structures

Abstract

Prediction of wave overtopping is a key task in the design and safety assessment of coastal structures. In this study, M5′ model tree as a new soft-computing approach was used to develop a model for the prediction of the wave overtopping rate at rubble mound breakwaters. The main advantages of model trees are that they are easier to deploy and more importantly, they produce understandable formulas. Selected data from the CLASH database were used for training of the model, and the conventional governing parameters were used as the input parameters. The obtained results were also compared with those of previous models. The accuracy of the model was evaluated by statistical measures, and it was shown that the developed model is more accurate than previous models. Furthermore, the model was validated with the prototype overtopping measurements in three sites. Results indicated that the developed model outperforms the previous models in predicting the full scale overtopping rates as well.