Artificial neural network modeling of cross-shore profile on sand beaches: The coast of the province of Valencia (Spain)

Please use this identifier to cite or link to this item: http://hdl.handle.net/10045/79832
Información del item - Informació de l'item - Item information
Title: Artificial neural network modeling of cross-shore profile on sand beaches: The coast of the province of Valencia (Spain)
Authors: López Úbeda, Isabel | Aragonés Pomares, Luis | Villacampa, Yolanda | Compañ, Patricia
Research Group/s: Ingeniería del Transporte, Territorio y Medio Litoral (AORTA) | Ingeniería del Terreno y sus Estructuras (InTerEs) | Modelización Matemática de Sistemas | Informática Industrial e Inteligencia Artificial
Center, Department or Service: Universidad de Alicante. Departamento de Ingeniería Civil | Universidad de Alicante. Departamento de Matemática Aplicada | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial
Keywords: Artificial neural network | Beach nourishment | Beach profile | D50 | Models | Sand beach
Knowledge Area: Ingeniería e Infraestructura de los Transportes | Matemática Aplicada | Ciencia de la Computación e Inteligencia Artificial
Issue Date: 2018
Publisher: Taylor & Francis
Citation: Marine Georesources & Geotechnology. 2018, 36(6): 698-708. doi:10.1080/1064119X.2017.1385666
Abstract: The paper describes the training, validation, testing, and application of models of artificial neural networks (ANN) for computing the cross-shore beach profile of the sand beaches of the province of Valencia (Spain). Sixty ANN models were generated by modifying both the input variables as the number of neurons in the hidden layer. The input variables consist of wave data and sedimentological data. To select and evaluate the performance of the optimal model, the following parameters were used: R2, absolute error, mean absolute percentage error, and percentage relative error. Finally, the results are compared with the numerical model proposed by Aragonés et al. (2016b) for the equilibrium profile in the study area. The results show a mean absolute error of 0.21 m compared to 0.33 m Aragones’ model, significantly improving the results of the numerical model in the bar area around de Valencia Port. In addition, when comparing the results with other methods currently used (Dean’s or Vellinga formulation), the errors of these compared to ANN are of the order of 167 and 1538% higher, respectively.
Sponsor: This research has been partially funded by Universidad de Alicante through the project “Estudio sobre el perfil de equilibrio y la profundidad de cierre en playas de arena” (GRE15-02).
URI: http://hdl.handle.net/10045/79832
ISSN: 1064-119X (Print) | 1521-0618 (Online)
DOI: 10.1080/1064119X.2017.1385666
Language: eng
Type: info:eu-repo/semantics/article
Rights: © 2018 Informa UK Limited
Peer Review: si
Publisher version: https://doi.org/10.1080/1064119X.2017.1385666
Appears in Collections:INV - MMS - Artículos de Revistas
INV - i3a - Artículos de Revistas
INV - AORTA - Artículos de Revistas
INV - INTERES - Artículos de Revistas
INV - Smart Learning - Artículos de Revistas

Files in This Item:
Files in This Item:
File Description SizeFormat 
Thumbnail2018_Lopez_etal_MarineGeoresGeotech_accepted.pdfAccepted Manuscript (acceso abierto)1,91 MBAdobe PDFOpen Preview


Items in RUA are protected by copyright, with all rights reserved, unless otherwise indicated.