A Neural-Fuzzy Network Based on Hermite Polynomials to Predict the Coastal Erosion

Tsekouras, George E.; Rigos, Anastasios; Chatzipavlis, Antonios; Velegrakis, Adonis F.

doi:10.1007/978-3-319-23983-5_19

Cited by 9 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, the proposed new model associated with other similar tools such as the determination of erosion [27] or bar volume [28], becomes not only a tool for bar knowledge, but also an additional method for coastal control and management, which may imply a reduction in both construction and maintenance costs.…”

Section: Model Generationmentioning

confidence: 99%

Optimisation of Models for the Determination of the Crest of Bars on Sandy Beaches

López

Villacampa

Pagán

et al. 2019

Computational Methods and Experimental Measurements XIX

View full text Add to dashboard Cite

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.

show abstract

Section: Model Generationmentioning

confidence: 99%

Optimisation of Models for the Determination of the Crest of Bars on Sandy Beaches

López

Villacampa

Pagán

et al. 2019

Computational Methods and Experimental Measurements XIX

View full text Add to dashboard Cite

show abstract

“…is constrained. By splitting the double inequality in (14), the constrained optimization problem is now given as follows: It can be easily verified that the feasible area of the problem is convex, because it forms the intersection of plane surfaces (i.e. convex sets).…”

Section: N =mentioning

confidence: 99%

“…Although the above approaches show good testing performances, they use high number of nodes and thus, can hardly be applied to high dimensional nonlinear problems. In comparison, Chebyshev polynomial radial basis function and neuralfuzzy networks were developed to perform efficient shoreline extraction from coastal imagery [10] and predict coastal erosion [14].…”

Section: Introductionmentioning

confidence: 99%

Modeling Beach Rotation Using a Novel Legendre Polynomial Feedforward Neural Network Trained by Nonlinear Constrained Optimization

Rigos

Tsekouras

Chatzipavlis

et al. 2016

IFIP Advances in Information and Communication Technology

Self Cite

View full text Add to dashboard Cite

A Legendre polynomial feedforward neural network is proposed to model/predict beach rotation. The study area is the reef-fronted Ammoudara beach, located at the northern coastline of Crete Island (Greece). Specialized experimental devices were deployed to generate a set of input-output data concerning the inshore bathymetry, the wave conditions and the shoreline position. The presence of the fronting beachrock reef (parallel to the shoreline) increases complexity and imposes high non-linear effects. The use of Legendre polynomials enables the network to capture data non-linearities. However, in order to maintain specific functional requirements, the connection weights must be confined within a predetermined domain of values; it turns out that the network's training process constitutes a constrained nonlinear programming problem, solved by the barrier method. The performance of the network is compared to other two neural-based approaches. Simulations show that the proposed network achieves a superior performance, which could be improved if an additional wave parameter (wave direction) was to be included in the input variables.

show abstract

“…A number of studies have found ANNs to be applicable for modeling shoreline position, shore profile, and shore volume change [18][19][20][21][22]. Most studies utilize data collected at one or a few beach sites in a small region [7].…”

Section: Introductionmentioning

confidence: 99%

Application of Artificial Neural Networks to Predict Beach Nourishment Volume Requirements

Bujak

Bogovac

Carević

et al. 2021

JMSE

View full text Add to dashboard Cite

The volume of material required for the construction of new and expansion of existing beach sites is an important parameter for coastal management. This information may play a crucial role when deciding which beach sites to develop. This work examines whether artificial neural networks (ANNs) can predict the spatial variability of nourishment requirements on the Croatian coast. We use survey data of the nourishment volume requirements and gravel diameter from 2016 to 2020, fetch length, beach area and orientation derived from national maps which vary from location to location due to a complex coastal configuration on the East Adriatic coast, and wind, tide, and rainfall data from nearby meteorological/oceanographic stations to train and test ANNs. The results reported here confirm that an ANN can adequately predict the spatial variability of observed nourishment volumes (R and MSE for the test set equal 0.87 and 2.24 × 104, respectively). The contributions of different parameters to the ANN’s predictive ability were examined. Apart from the most obvious parameters like the beach length and the beach areas, the fetch length proved to be the most important input contribution to ANN’s predictive ability, followed by the beach orientation. Fetch length and beach orientation are parameters governing the wind wave height and direction and hence are proxies for forcing.

show abstract

A Neural-Fuzzy Network Based on Hermite Polynomials to Predict the Coastal Erosion

Cited by 9 publications

References 14 publications

Optimisation of Models for the Determination of the Crest of Bars on Sandy Beaches

Optimisation of Models for the Determination of the Crest of Bars on Sandy Beaches

Modeling Beach Rotation Using a Novel Legendre Polynomial Feedforward Neural Network Trained by Nonlinear Constrained Optimization

Application of Artificial Neural Networks to Predict Beach Nourishment Volume Requirements

Contact Info

Product

Resources

About