Neural-Network-Based Data Assimilation to Improve Numerical Ocean Wave Forecast

Deshmukh, Aditya N.; Deo, M. C.; Bhaskaran, Prasad K.; Nair, T. M. Balakrishnan; Sandhya, K. G.

doi:10.1109/joe.2016.2521222

Cited by 54 publications

(23 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development of artificial intelligence technology, artificial neural network (ANN) models are being applied to SWH prediction [17][18][19]. Deo et al [20] proposed a feedforward network for real-time SWH prediction.…”

Section: Introductionmentioning

confidence: 99%

CLTS-Net: A More Accurate and Universal Method for the Long-Term Prediction of Significant Wave Height

Hao

et al. 2021

JMSE

View full text Add to dashboard Cite

Significant wave height (SWH) prediction plays an important role in marine engineering areas such as fishery, exploration, power generation, and ocean transportation. For long-term forecasting of a specific location, classical numerical model wave height forecasting methods often require detailed climatic data and incur considerable calculation costs, which are often impractical in emergencies. In addition, how to capture and use the dynamic correlation between multiple variables is also a major research challenge for multivariate SWH prediction. To explore a new method for predicting SWH, this paper proposes a deep neural network model for multivariate time series SWH prediction—namely, CLTS-Net. In this study, the sea surface wind and wave height in the ERA5 dataset of the relevant points P1, P2, and P3 from 2011 to 2018 were used as input information to train the model and evaluate the model’s SWH prediction performance. The results show that the correlation coefficients (R) of CLTS-Net are 0.99 and 0.99, respectively, in the 24 h and 48 h SWH forecasts at point P1 along the coast. Compared with the current mainstream artificial intelligence-based SWH solutions, it is much higher than ANN (0.79, 0.70), RNN (0.82, 0.83), LSTM (0.93, 0.91), and Bi-LSTM (0.95, 0.94). Point P3 is located in the deep sea. In the 24 h and 48 h SWH forecasts, the R of CLTS-Net is 0.97 and 0.98, respectively, which are much higher than ANN (0.71, 0.72), RNN (0.85, 0.78), LSTM (0.85, 0.78), and Bi-LSTM (0.93, 0.93). Especially in the 72 h SWH forecast, when other methods have too large errors and have lost their practical application value, the R of CLTS-Net at P1, P2, and P3 can still reach 0.81, 0.71, and 0.98. The results also show that CLTS-Net can capture the short-term and long-term dependencies of data, so as to accurately predict long-term SWH, and has wide applicability in different sea areas.

show abstract

Section: Introductionmentioning

confidence: 99%

CLTS-Net: A More Accurate and Universal Method for the Long-Term Prediction of Significant Wave Height

Hao

et al. 2021

JMSE

View full text Add to dashboard Cite

show abstract

“…According to the meteorological data, Günaydın (2008) predicted monthly mean significant wave heights by using neural network and regression methods. Malekmohamadi et al (2008), Londhe et al (2016), and Deshmukh et al (2016) combined neural network and numerical models to realize the wave height prediction. To solve the time lag and the lack of extreme wave height prediction ability in the neural network, Deka and Prahlada (2012), Dixit and Londhe (2016), and Dixit et al (2015) added the wavelet into the neural network.…”

Section: Introductionmentioning

confidence: 99%

Significant Wave Height Prediction with the CRBM-DBN Model

Zhang

Dai

2019

Journal of Atmospheric and Oceanic Technology

View full text Add to dashboard Cite

In recent years, deep learning technology has been gradually used for time series data prediction in various fields. In this paper, the restricted Boltzmann machine (RBM) in the classical deep belief network (DBN) is substituted with the conditional restricted Boltzmann machine (CRBM) containing temporal information, and the CRBM-DBN model is constructed. Key model parameters, which are determined by the particle swarm optimization (PSO) algorithm, are used to predict the significant wave height. Observed data in 2016, which are from nearshore and offshore buoys (i.e., 42020 and 42001) belonging to the National Data Buoy Center (NDBC), are taken to train the model, and the corresponding data in 2017 are used for testing with lead times of 1–24 h. In addition, we trained the data of 42040 in 2003 and tested the data in 2004 in order to investigate the prediction ability of the CRBM-DBN model for the extreme event. The prediction ability of the model is evaluated by the Nash–Sutcliffe coefficient of efficiency (CE) and root-mean-square error (RMSE). Experiments demonstrate that for the short-term (≤9 h) prediction, the RMSE and CE for the significant wave height prediction are <10 cm and >0.98, respectively. Moreover, the relative error of the short-term prediction for the maximum wave height is less than 26%. The excellent short-term and extreme events forecasting ability of the CRBM-DBN model is vital to ocean engineering applications, especially for designs of ocean structures and vessels.

show abstract

“…The SVM results were compared with the field data and BPNN and CCNN models, and the results indicated that the SVM with a radial basis function kernel provides the best generalization capability and the lowest prediction error. While Malekmohamadi et al [11], Londhe et al [12], and Deshmukh et al [13] combined NN and numerical models to realize the wave height prediction, Sadeghifar et al [14] used recurrent neural networks (RNN) for wave predictions based on the data gathered and the measurement of the sea waves in the Caspian Sea in the north of Iran. Additionally, Elgohery et al [15] used nonlinear regression and SVM methods to predict significant wave height.…”

Section: Introductionmentioning

confidence: 99%

Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction

Elbisy¹,

Osra²

2019

AJNNA

View full text Add to dashboard Cite

The estimation of wave parameters is of great importance in coastal activities such as design studies for harbor, inshore and offshore structures, coastal erosion, sediment transport, and wave energy estimation. For this purpose, several models and approaches have been proposed to predict wave parameters, such as empirical, numerical-based approaches, and soft computing. In this study, the group method of data handling type neural network (GMDH-NN) was presented for significant wave height prediction in an attempt to suggest a new model with superior explanatory power and stability. The GMDH-NN results were compared with the field data and with a multilayer perceptron neural networks (MLPNN) model. The results indicate that the prediction accuracy and avoidance of over-fitting of the GMDH-NN method were superior to those of the MLPNN method. The percentage improvement in the root mean square error and the mean absolute percentage error of the GMDH-NN model over the MLPNN model were 72.92% and 81.02%, respectively. Also, according to the indices, the GMDH-NN model performs the best for predicting the Hs of all of the wave height ranges. That is, the GMDH-NN model is capable of predicting wave heights for different ranges. The results of the analysis suggest that the GMDH-NN-based modeling is effective in predicting significant wave height.

show abstract

Neural-Network-Based Data Assimilation to Improve Numerical Ocean Wave Forecast

Cited by 54 publications

References 20 publications

CLTS-Net: A More Accurate and Universal Method for the Long-Term Prediction of Significant Wave Height

CLTS-Net: A More Accurate and Universal Method for the Long-Term Prediction of Significant Wave Height

Significant Wave Height Prediction with the CRBM-DBN Model

Application of Group Method of Data Handling Type Neural Network for Significant Wave Height Prediction

Contact Info

Product

Resources

About