Prediction of offshore bar-shape parameters resulted by cross-shore sediment transport using neural network

Creative Commons License

KOMURCU M. I., Komur M. A., Akpinar A., Ozolcer I. H., YÜKSEK Ö.

APPLIED OCEAN RESEARCH, vol.40, pp.74-82, 2013 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 40
  • Publication Date: 2013
  • Doi Number: 10.1016/j.apor.2013.01.003
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.74-82
  • Karadeniz Technical University Affiliated: Yes


In order to understand the features of coastal zone and to utilize the coastal areas, it is necessary to determine the sediment movement and the resulting transport. Waves, topographic features, and material properties are known as the most important factors affecting the sediment movement and coastal profiles. In this study, by taking into consideration of wave height and period (H-0, T), bed slope (m) and sediment diameter (d(50)), cross-shore sediment movement was studied in a physical model and various bar-shape parameters of the resultant erosion type profile were determined. Using 80 experimental data which are obtained from physical model studies, a neural network (NN) has been calibrated to predict bar-shape parameters of beach profiles. A sensitivity analysis was firstly carried out to decide data of training and test sets. Four different models, in which the rates of their training and testing set data were 80% and 20%, 70% and 30%, 60% and 40%, 50% and 50% were constituted and their performances were compared. It was determined that the model, in which the rate of its training and testing set data was 80% and 20%, respectively, has the best results. Therefore, a total of 64 experimental data were used as training set and the remainders of the experimental data were used as a testing set for the model. The performance of the NN model was compared with the regression equations developed in a previous study and the equations cited in literature indicating better performance over the equations. (c) 2013 Elsevier Ltd. All rights reserved.