One of the main objectives within the EU-project CLASH (www.clash-eu.org) was to create a generic prediction method for wave overtopping at coastal structures by means of the Neural Network technique. An extensive and homogeneous database on wave overtopping was set up within CLASH, mainly with the aim to be used for the training process of the Neural Network (NN). A total number of 10,532 tests from 163 independent test series were screened and included in the database. The final database consists of far more information than needed for the training of the NN: 31 parameters are included to describe each overtopping test of which only 17 are used for the NN development. This explains the possible use of the overtopping database on its own. Plotting various parameters of the database together in graphs gives a clear view on the contents of the database. Also the ranges covered by the parameters can be detected in this way. The creation of the database, the analysis of the database, and the possible use of the database on its own are described in this paper.
The EU project CLASH (EVK3-CT-2001-00058) (Jan. 2002 -Dec. 2004, stands for 'Crest Level Assessment of coastal Structures by full scale monitoring, neural network prediction and Hazard analysis on permissible wave overtopping' (www.clash-eu.org). One of the objectives of CLASH is to produce a generally applicable prediction method for wave overtopping at coastal structures based on permissible wave overtopping and hazard analysis. The set up of a homogeneous database on wave overtopping is one of the main tasks within the framework of CLASH and is the main subject of this paper. On the one hand, the database gives a detailed inventory of overtopping tests which have been performed and on the other hand, the database serves as the starting point for a neural network prediction method. At this moment (Dec. 2003), the overtopping database consists of more than 6500 overtopping tests. This paper gives a complete overview of the contents of the database and discusses the methodology.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.