Prediction of Mean Overtopping Discharge at Vertical Seawalls Using MLR and GLM Statistical Approaches

Wave overtopping at breakwaters is one of their essential hydraulic characteristics when determining the design crest level. this study concentrates on developing a new practical formula on predicting wave overtopping, by implementing two different statistical models, multiple linear regression model (mlr) and generalized linear regression model (glm). the models consider dependency of overtopping on a wide variety of quantities and yield to simple forms of prediction. such statistical analysis are performed on a set of data called clash (crest level assessment of coastal structures by full scale monitoring, neural network prediction and hazard analysis on permissible wave overtopping); the most complete and available database on overtopping phenomena. proposed equations are compared with most recently extracted as well as successful ones. comprehensive assessments clearly show more accurate predictions in the case of mean overtopping at vertical seawalls.