Neural network for determining the characteristic points of the bars

López, Isabel; Aragonés, Luís; Villacampa, Yolanda; Serra, José Cristobal

doi:10.1016/j.oceaneng.2017.03.033

Cited by 26 publications

(19 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This difference in the adjustment is also observed in the errors. Thus, the numerical model selected results in an absolute error about three times lower than that of the ANN proposed by López et al [26], which is the one that results in the least error of the different models proposed by other authors ( Table 6).…”

Section: Model Generationmentioning

confidence: 66%

“…To evaluate the performance of each model, the results obtained were compared with the formulations proposed by Hsu [22], Silvester and Hsu [23], Günaydın and Kabdaşlı [24] and Kömürcü et al [25], as well as the artificial neural network (ANN) proposed byLópez et al [26]. The results were compared in terms of R 2 , absolute error (eqn 1) and mean absolute percentage error…”

Section: Model Generationmentioning

confidence: 99%

“…The smallest reduction in error occurs when comparing the M5 model with the ANN, and yet the reduction is 16 m in the distance to the coast and 29 cm in depth. Where: H refers to Hsu [22], S&K to Silvester and Hsu [23], G&K to Günaydın and Kabdaşlı [24], K to Kömürcü et al [25], and ANN to the artificial neural network proposed by López et al [26].…”

Section: Model Generationmentioning

confidence: 99%

See 2 more Smart Citations

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

Self Cite

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: 66%

Section: Model Generationmentioning

confidence: 99%

Section: Model Generationmentioning

confidence: 99%

See 1 more Smart Citation

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are many approaches that have been used to model morphodynamic processes in coastal areas and hold promise to be utilized as surrogate models for dune erosion. For instance, Multivariate Adaptive Regression Splines (MARS) has been applied to simulate scour (Samadi et al, ) and landslides (Conoscenti et al, ); Artificial Neural Networks (ANNs) have been used to predict bar movement (Kömürcü et al, ; López et al, ; Pape et al, ), seasonal beach changes (Hashemi et al, ), and long‐shore sediment transport (Güner et al, ; Kabiri‐Samani et al, ); and Bayesian Networks (BNs) have been employed to predict coastal vulnerability to sea level rise (Gutierrez et al, ), barrier island morphodynamics (Gutierrez et al, ; Plant & Stockdon, ), and to model shoreline change (Beuzen et al, ; Plant et al, ). However, to the best of our knowledge, very few studies have attempted to develop surrogate models for coastal dune erosive processes.…”

Section: Introductionmentioning

confidence: 99%

Combining Numerical and Statistical Models to Predict Storm‐Induced Dune Erosion

et al. 2019

View full text Add to dashboard Cite

Dune erosion is an important aspect to consider when assessing coastal flood risk, as dune elevation loss makes the protected areas more susceptible to flooding. However, most advanced dune erosion numerical models are computationally expensive, which hinders their application in early-warning systems. Based on a combination of probabilistic and process-based numerical modeling, we develop an efficient statistical tool to predict dune erosion during storms. The analysis focuses on Dauphin Island, AL, in the northern Gulf of Mexico, where we combine synthetic sea storms with a calibrated and validated XBeach model to develop and test a range of different surrogate models for their ability to predict barrier island geometric parameters under storm conditions. Surrogate models are developed by combining the oceanographic forcing from 100 optimally sampled sea storm events covering the entire multivariate parameter space (used as XBeach input) and associated changes in the dune system (XBeach output). We test four surrogate models using a k-fold approach for validation. All models perform well in predicting changes in dune elevation, barrier island area, and width but are less accurate in predicting alterations in the cross-shore locations of dune morphological features. Multivariate adaptive regression splines is identified as the best surrogate model based on its fast development and good performance, attaining a modified Mielke index of 0.81 for dune crest height. As demonstrated at Dauphin Island, our approach shows potential to be used in an operational framework to predict dune response (in particular crest elevation change) when water level and wave forecasts are available. Key Points: • Surrogate models of XBeach are developed and tested, showing that multivariate adaptive regression splines exhibits the best performance • Carefully trained statistical and machine-learning models predict changes in barrier island geometric parameters at low computational cost • The highest performance is attained for the most extreme dune impact regimes, allowing fast and accurate dune height change predictions Correspondence to:Here, surrogate models are designed to predict coastal dune erosion by addressing issues related to computational performance and absence of sufficient forcing data. Our main goal is to understand complex morphological interactions through simulation of a wide range of realistic scenarios. To accomplish this, we develop and test surrogate models for XBeach that are trained with simulated, physically consistent oceanographic variables and associated dune response. This includes the following steps: (1) select a subset of synthetic multivariate sea storm events from Wahl et al. (2016) and consider time-dependent evolution of the oceanographic variables, (2) use XBeach to predict morphological response parameters for the selected sea storms, and (3) develop and test a range of different surrogate models to mimic XBeach at low computational cost. The different analysis steps are summarized in Figure 1. In...

show abstract

“…For nonlinear prediction, the more commonly used methods are curve fitting (Motulsky and Ransnas, 1987), gray-box model (Pearson and Pottmann, 2000), homogenization function model (Monteiro et al, 2008), neural network (Deo et al, 2001;Y. Wang et al, 2015;Kim et al, 2016) and so on.…”

Section: Introductionmentioning

confidence: 99%

Hybrid improved empirical mode decomposition and BP neural network model for the prediction of sea surface temperature

Jiang

Conde

et al. 2019

Ocean Sci.

View full text Add to dashboard Cite

Sea surface temperature (SST) is the major factor that affects the ocean-atmosphere interaction, and in turn the accurate prediction of SST is the key to ocean dynamic prediction. In this paper, an SST-predicting method based on empirical mode decomposition (EMD) algorithms and back-propagation neural network (BPNN) is proposed. Two different EMD algorithms have been applied extensively for analyzing time-series SST data and some nonlinear stochastic signals. The ensemble empirical mode decomposition (EEMD) algorithm and complementary ensemble empirical mode decomposition (CEEMD) algorithm are two improved algorithms of EMD, which can effectively handle the mode-mixing problem and decompose the original data into more stationary signals with different frequencies. Each intrinsic mode function (IMF) has been taken as input data to the back-propagation neural network model. The final predicted SST data are obtained by aggregating the predicted data of individual series of IMFs (IMFi). A case study of the monthly mean SST anomaly (SSTA) in the northeastern region of the North Pacific shows that the proposed hybrid CEEMD-BPNN model is much more accurate than the hybrid EEMD-BPNN model, and the prediction accuracy based on a BP neural network is improved by the CEEMD method. Statistical analysis of the case study demonstrates that applying the proposed hybrid CEEMD-BPNN model is effective for the SST prediction. Highlights include the following: Highlights.-An SST-predicting method based on the hybrid EMD algorithms and BP neural network method is proposed in this paper.-SST prediction results based on the hybrid EEMD-BPNN and CEEMD-BPNN models are compared and discussed.-A case study of SST in the North Pacific shows that the proposed hybrid CEEMD-BPNN model can effectively predict the time-series SST.

show abstract

Neural network for determining the characteristic points of the bars

Cited by 26 publications

References 40 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

Combining Numerical and Statistical Models to Predict Storm‐Induced Dune Erosion

Hybrid improved empirical mode decomposition and BP neural network model for the prediction of sea surface temperature

Contact Info

Product

Resources

About