Predicting tsunami-like solitary wave run-up over fringing reefs using the multi-layer perceptron neural network

Yao, Yu; Yang, Xiaoxiao; Lai, Sai Hin; Chin, Ren Jie

doi:10.1007/s11069-021-04597-w

Cited by 17 publications

(10 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The impact of input neurons on the output neurons can be obtained by examining the internal weight matrix value [25]. Following this concept, MIV is introduced to evaluate the importance of input parameters to output in a neural network [26,27]. As illustrated in Figure 5c, the procedures of MIV analysis are as follows: First, a well-trained NN model is established using training dataset P. Subsequently, each input parameter i in P increases and decreases by a small percentage of q (equal to 10% in the present study) to create two new datasets P1 i and P2 i , which are later imported into the trained NN model to produce the simulated outputs A1 i and A2 i (as a sequence).…”

Section: Mean Impact Value Analysis and Kernel Principal Component An...mentioning

confidence: 99%

“…Therefore, preprocessing technologies, such as the clustering method and principal component analysis (PCA), were introduced to narrow down or reduce the sample space before applying an NN [21,24]. One can evaluate the impact degree of input neurons on the output in a network [25], and the critical input parameters can be extracted by mean impact value (MIV) analysis [26,27]. MIV analysis based on a well-trained NN model is theoretically capable of selecting the critical parameters [26].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Calibration Experiments of CFOSAT Wavelength in the Southern South China Sea by Artificial Neural Networks

Liu

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

The wave data measured by CFOSAT (China France Oceanography Satellite) have been validated mainly based on numerical model outputs and altimetry products on a global scale. It is still necessary to further calibrate the data for specific regions, e.g., the southern South China Sea. This study analyses the practicability of calibrating the dominant wavelength by using artificial neural networks and mean impact value analysis based on two sets of buoy data with a 2-year observation period and contemporaneous ERA5 reanalysis data. The artificial neural network modeling experiments are repeated 1000 times randomly by Monte Carlo methods to avoid sampling uncertainty. Both experimental results based on the random sampling method and chronological sampling method are performed. Independent buoy observations are used to validate the calibration model. The results show that although there are obvious differences between the CFOSAT wavelength data and the field observations, the parameters observed by the satellite itself can effectively calibrate the data. In addition to the wavelength, nadir significant wave height, nadir wind speed, and the distance between the calibration point and satellite observation point are the most important parameters for the calibration. Accurate data from other sources, such as ERA5, would be helpful to further improve the calibration results. The variable contributing the most to the calibration effect is the mean wave period, which virtually provides relatively accurate wavelength information for the calibration network. These results verify the possibility of synchronous self-calibration for the CFOSAT wavelength data and provide a reference for the further calibration of the satellite products in other regions.

show abstract

Section: Mean Impact Value Analysis and Kernel Principal Component An...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Calibration Experiments of CFOSAT Wavelength in the Southern South China Sea by Artificial Neural Networks

Liu

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The obtained results showed that both the ANN and RSM are appropriate methods for the prediction of wave run-up. Also, the study of Yao et al 19 conformed a good accuracy of ANN in simulating wave run-up.…”

Section: Introductionmentioning

confidence: 77%

Modeling of wave run-up by applying integrated models of group method of data handling

Mahdavi‐Meymand

Zounemat‐Kermani

Sulisz

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Wave-induced inundation in coastal zones is a serious problem for residents. Accurate prediction of wave run-up height is a complex phenomenon in coastal engineering. In this study, several machine learning (ML) models are developed to simulate wave run-up height. The developed methods are based on optimization techniques employing the group method of data handling (GMDH). The invasive weed optimization (IWO), firefly algorithm (FA), teaching–learning-based optimization (TLBO), harmony search (HS), and differential evolution (DE) meta-heuristic optimization algorithms are embedded with the GMDH to yield better feasible optimization. Preliminary results indicate that the developed ML models are robust tools for modeling the wave run-up height. All ML models’ accuracies are higher than empirical relations. The obtained results show that employing heuristic methods enhances the accuracy of the standard GMDH model. As such, the FA, IWO, DE, TLBO, and HS improve the RMSE criterion of the standard GMDH by the rate of 47.5%, 44.7%, 24.1%, 41.1%, and 34.3%, respectively. The GMDH-FA and GMDH-IWO are recommended for applications in coastal engineering.

show abstract

“…Thresholds and weights of the multiperceptron neural network are cascaded according to a specific order, and the weights and thresholds of the multiperceptron neural network are cascaded according to the order; namely, N chromosomes are generated randomly; implicit and output layer thresholds; input and implicit layer thresholds; implicit and output layer weights; input and implicit layer weights; the fitness function selects the mean square error, and the fitness of the chromosomes is recalculated according to the mean square error function to judge whether the prediction results meet the target requirements and generate new individuals if they do not meet the requirements; the specific operation is to perform variation operation, crossover operation, and replication operation on the individuals that meet the requirements of the fitness value and judge whether the new individuals meet the requirements of the mean square error value function if they meet the requirements [ 21 ]. There are four mutation operations in the evolution of a multilayer perceptron genetic algorithm neural network: adding connections, adding nodes, correcting connection weights, and changing the excitation function response.…”

Section: Product Styling Design Evaluation Methods Based On Multilayer Perceptron Genetic Algorithm Neural Network Algorithmmentioning

confidence: 99%

A Product Styling Design Evaluation Method Based on Multilayer Perceptron Genetic Algorithm Neural Network Algorithm

Wu¹

2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Products no longer exist simply as carriers of useful functions, but more and more consumers are beginning to pay attention to the spiritual aspects of the feelings brought by products. This paper brings machine learning algorithms to the discipline of industrial design and proposes a method to evaluate the design of product shapes using a multilayer perceptron genetic algorithm neural network (GA-MLP-NN) algorithm, quantifying the product shape, using computer-aided design technology to achieve shape optimization, shape, and color scheme generation, and using interactive feedback with users to finally generate a product shape with market demand. In this paper, we use the combinatorial innovation method to arrange and combine the detail elements in the solution library to generate the modeling solution, combine the multilayer perceptron genetic algorithm neural network algorithm with product modeling, and establish the interactive genetic modeling system for the product, use this system to design the product modeling solution, and finally get the product modeling solution satisfied by the target users; using the multilayer perceptron genetic algorithm neural network method to evaluate the product modeling items. The mapping relationship model between morphological feature space and imagery cognitive space was constructed based on multiple linear regression equations, and the multiple regression model for each affective dimension was ideal. The results show that the model performance is reliable. The weights are calculated, and the appropriate people are selected to score and calculate the modeling scheme, and finally, the satisfactory product modeling scheme is obtained.

show abstract

Predicting tsunami-like solitary wave run-up over fringing reefs using the multi-layer perceptron neural network

Cited by 17 publications

References 42 publications

Calibration Experiments of CFOSAT Wavelength in the Southern South China Sea by Artificial Neural Networks

Calibration Experiments of CFOSAT Wavelength in the Southern South China Sea by Artificial Neural Networks

Modeling of wave run-up by applying integrated models of group method of data handling

A Product Styling Design Evaluation Method Based on Multilayer Perceptron Genetic Algorithm Neural Network Algorithm

Contact Info

Product

Resources

About