Reliable predictions of wave overtopping are required for the design, safety assessment and rehabilitation of coastal structures. Several design formulae already exist for dikes, rubble mound breakwaters and vertical breakwaters. Nevertheless, suitable prediction methods are often not available for structures with non-standard shapes.
Within the framework of the European project CLASH, a method has been developed to provide a conceptual design tool to estimate wave overtopping discharges for a wide range of coastal structures. A single schematisation is used for all types of coastal structures, where not only dikes, rubble mound breakwaters or vertical breakwaters are defined, but also other non-standard structures are included. Additionally, not only is the effect of the most common parameters (i.e. wave height, wave period and crest freeboard) analysed in this schematisation, but the effect of many other wave/structural characteristics is also considered. The prediction method described is based on the technique of Neural Network modelling. For this purpose a data set obtained from a large number of physical model tests is used. Most of these data were provided by the partners involved in the CLASH project. Moreover, a method has been developed to obtain the confidence intervals around these predictions. The latter is a new essential step since the neural network model results in a tool that acts as a kind of black box for users. Therefore it is important that predictions are expanded with the addition of information regarding their reliability. The Neural Network for predicting wave overtopping will be made available so that it may be used by designers at consultancy and general contracting firms. |
