Artificial neural networks for predicting maximum wave runup on rubble mound structures

Erdik T., Savcı M. M., Şen Z.

Expert Systems with Applications, vol.36, no.3 PART 2, pp.6403-6408, 2009 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 36 Issue: 3 PART 2
  • Publication Date: 2009
  • Doi Number: 10.1016/j.eswa.2008.07.049
  • Journal Name: Expert Systems with Applications
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.6403-6408
  • Keywords: Rock slopes, Artificial neural networks, Dimensionless 2% wave runup
  • Istanbul Medipol University Affiliated: Yes


Accurate prediction of maximum wave runup on breakwaters is a vital issue for determining crest level of coastal structures. In practice, traditional regression-based empirical model, recommended by the "Coastal Engineering Manual", as well as the "Manual on the use of rock in hydraulic engineering", is widely used. However, use of these approaches brings additional restrictive assumptions such as linearity, normality (Gaussian distributed variables), variance constancy (homoscedasticity) etc. This paper focuses on the prediction of maximum wave runup elevation through artificial neural networks (ANNs), which has no restrictive assumptions. Out of 261 irregular wave runup data of Van der Meer and Stam, 100 randomly chosen data points are used for training the model. The remaining data are exploited for testing purposes. This study has two objectives: (1) to develop ANN models and search their applicability to estimate maximum wave runup elevation on breakwaters; (2) to compare widely used empirical model with these models. For these purposes, different ANN models are constructed and trained with their own topology. The performance of the ANN models is tested against the same testing data, none of which is employed in the training. It is found that ANN technique gives more accurate results and the extent of accuracy can be affected by the structure of ANNs. © 2008 Elsevier Ltd. All rights reserved.