OPTIMISATION OF MODELS FOR THE DETERMINATION OF THE CREST OF BARS ON SANDY BEACHES

• Published in: WIT Transactions on Engineering Sciences 2019-01, Vol.125, p.207
• Main Authors: LÓPEZ, ISABEL, VILLACAMPA, YOLANDA, PAGÁN, JOSE IGNACIO, NAVARRO-GONZÁLEZ, FRANCISCO JOSÉ, ARAGONÉS, LUIS
• Format: Article
• Language: English
• Subjects: Beaches; Correlation analysis; Finite element method; Formulations; Galerkin method; Mathematical models; Numerical models; Optimization; Physical properties; Sand bars; Wave height
• ISSN: 1746-4471; 1743-3533
• DOI: 10.2495/CMEM190201

Sand bars are important morphological characteristics of beaches, and changes in their position and height are the main causes of profile variability. The cross-shore movement of the bars can be important for the artificial beach nourishments, because the success of the latter depends on its interaction with the bar position. Therefore, it is important to determine the location of the bars in the profile. The aim of this work is to evaluate the different existing models, and to obtain an optimized model that uses the least possible number of variables and obtains the best results. First of all, a total of 25 variables related to the characteristics of the waves, sediment and physical characteristics of the beach have been studied by means of a correlation analysis. Secondly, we have tried to generate linear models using the backward method, which generates successive models eliminating variables in each of them. These models, however, did not offer good results, with R2 values lower than 0.4. For this reason, different numerical models have been generated using among others the same variables used by different authors in their formulations or models. The numerical models of finite elements use Galerkin’s methodology and show that the most influential variables on the location of the bars crest are: wave height, period and median sediment size. These variables are very similar to those proposed by other authors; however, the formulations proposed by these authors do not offer good results in the area of study, while with the models generated, the errors committed in absolute value are less than 8%. This leads us to the final idea that the influential variables in the bars are the same in any study area, but the degree of influence or relationship with the study parameter depends on the study area.