XGB-Overtopping



For the design, safety assessment and rehabilitation of coastal structures reliable predictions of wave overtopping are required. XGB-Overtopping is a prediction tool for the estimation of mean overtopping discharges at various types of coastal structures.

Deltares has developed XGB-Overtopping, a new machine learning tool for the prediction of wave overtopping, which is now freely available for use as a web app. This new tool is the successor to the existing Overtopping Neural Network tool by Deltares.

The Overtopping Neural Network is still available.

Accurate predictions of wave overtopping for coastal  structures such as breakwaters, quay walls and coastal dikes both help optimize cost effectiveness of coastal structures and ensure coastal safety. The new XGB-Overtopping tool makes use of state-of-the-art machine learning techniques and is shown to be more accurate than existing empirical formulas and data-driven methods (Den Bieman et al., 2021).

The predictions based on XGB-Overtopping model can be used for the conceptual design of coastal structure; they may not be used in the final stage, since the results should be verified based on dedicated physical model test for the particular wave conditions and structure geometry of the structure to be built.