Aragonés, L.; López, I.; Villacampa, Y.; Serra, J.C., and Saval, J.M., 2015. New methodology for the classification of gravel beaches: Adjusted on Alicante (Spain).
This article focuses on the optimal architecture of the neural network for determining the three characteristic points of the bars (starting, crest and final point). For the definition of the network, precision profiles, sedimentological and wave data were used. A total of 209 profiles taken for 22 years was used. The inputs were analysed and selected considering the variables that influenced the formation of the bars and their movement. For the selection of the optimal model different architectures were studied, generating 50 models for each of them and selecting with better results and with the smaller number of neurons in the hidden layer. To evaluate the performance of the model, various statistical errors were used (absolute error, mean magnitude of relative error and percentage relative error), with an average absolute error of 17.3 m in the distances to the coast and 0.26 m in the depths. The results were compared with equations currently employed (Table 1), which show that the errors generated by the ANN (Artificial Neural Network) are much lower (per example the MAPE committed by the proposed equation for distance to shore of the crest is 47%, while the ANN is made of 29%).
Obtaining depth of closure (DoC) in an accurate manner is a fundamental issue for coastal engineering, since good results for coastal structures and beach nourishment depend mainly on DoC. Currently, there are two methods for obtaining the DoC, mathematical formulations and profile surveys. However, these methods can incur important errors if one does not take into account the characteristics and morphology of the area, or if one does not have a sufficiently long time series. In this work the DoC is obtained from the break in the trend of the sediment with the depth, that is, in general with the increase of the depth a decrease in the size of the sediment takes place. However, at one point this tendency changes and the size increases, and then decreases again. When comparing the point where the minimum sediment size occurs before the increase, it is observed that the error incurred is small compared to other methods. If the Standard Deviation of Depth Change (SDDC) method is considered as the most accurate method, the error incurred by the proposed method is less than 7%. In addition, it can be seen that the dispersion of the sediment method always occurs outside the zone of bar movement. Whereas in the methods of profiles survey (using 2 cm precision profiles), sometimes the DoC is obtained within the active zone of bar movement. In addition, where the relative minimum of the median sediment size is found, and the sizes of 0.063 and 0.125 mm predominate in the composition of the sample. Therefore, this new method allows the precise location of the DoC to be obtained in a fast and simple way. Furthermore, this method has the advantage that it is not affected by the modifications that may be experienced by both the study area and the cross-shore beach profile.
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.