Significant Wave Height Prediction Research Articles

SIGNIFICANT WAVE HEIGHT PREDICTION USING TRANSFER LEARNING

Wave prediction needed for maritime construction is generally performed by numerical models. This method, however, requires a high-performance computer and a large cost of computational resources. With the development of neural networks, which can compute at a low cost, the use of neural networks in wave prediction has recently been studied. However, because a large amount of training data is required for neural network tasks using scarce datasets, it is difficult to predict wave conditions accurately. Fan et al. (2020) reported that using LSTM model for prediction of significant wave height (Hs) was higher accuracy than conventional neural network model. Additionally, they recommended using at least 2 years of training data for 6h predictions, that is, an excessively small amount of data is not presumed to predict sufficiently Hs. Therefore, we propose a wave prediction method using transition learning. Transfer Learning is the method of transferring trained knowledge from one model to another. In this study, we investigate whether transfer learning can be used to improve the performance of Hs prediction by transferring the knowledge learned at Sakata port, which has a large amount of training data, to the coast of Yamagata, which has a scarce one.

A novel multivariable hybrid model to improve short and long-term significant wave height prediction

Accurate significant wave height (Hs) prediction is crucial for marine renewable energy development. The hybrid models combining multi-resolution analysis techniques such as empirical mode decomposition and wavelet transform with intelligence algorithm have flourished in Hs forecasting. However, these hybrid models cannot fit multivariable input mode well. In this study, a novel multivariable hybrid model is proposed. The improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and recurrence quantification analysis (RQA) were integrated as the deterministic and stochastic components decomposition (DSD) method. Then three machine learning models was integrated with DSD method as hybrid models, respectively. For more sufficient forecasting information, wind speed (Ws), wind direction (Wd) and Hs were adopted as inputs to construct multivariable hybrid models. The forecasting experiment was benchmarked with those from univariate hybrid models, multivariable single models and univariate single models. Three buoy-measured datasets were utilized for validation. Results revealed the positive effect of wind data on long-term prediction and the improvement to prediction by the DSD method. Benefiting from the advantages of both, multivariable hybrid models outperformed other benchmark models. Among them, the multivariable hybrid model based on long short-term memory (LSTM) network, DSD-LSTM-m, achieved the best forecasting performance.

Significant wave height prediction based on dynamic graph neural network with fusion of ocean characteristics

Significant wave height (SWH) is one of the core parameters for wave and accurate prediction of SWH is of great importance for ocean resource assessment. In this paper, we propose a new multi-characteristic and multi-node SWH prediction model(MCMN). The model considers the lead–lag effect among ocean characteristics and utilizes time lag correlation to automatically learn advanced indication information. For the temporal features, temporal correlations are extracted from high-dimensional spatial features efficiently in parallel using Temporal Convolutional Network(TCN). Additionally, the dependencies between nodes are modeled as the joint result of stable long-term patterns and dynamic short-term patterns. To obtain these dependencies, we introduce a novel dynamic graph neural network. Compared to previous SWH predictions focused solely on individual nodes, this model allows us to more fully explore the spatio-temporal dependencies between the nodes by capturing both long-term and short-term spatio-temporal relationship patterns among the nodes. Experiments were conducted with 120 nodes in the South China Sea and East China Sea, respectively. The results show that the model provides reliable predictions. Finally, we compare with five deep learning models, and the results show that our model has better performance in multi-node and multi-step SWH prediction.

Improved Prediction of Local Significant Wave Height by Considering the Memory of Past Winds

AbstractWave and water depth were measured with an instrumented tripod in the Yellow River Delta from 9 December 2014 to 29 April 2015. Concurrent wind data were also collected from a nearby wind station. A high‐precision model for predicting local significant wave height (Hs) with wind speed (vw) is constructed using an improved data‐driven approach. The proposed model realized high accuracy as it solves the problem that the Hs falls too fast during the wind‐decreasing periods. It was tackled by considering the remaining influence of historical vw on the present Hs via incorporating a memory curve of the past wind effect. This innovative approach significantly improves the prediction (R2 from 0.60 to 0.83). The winds in the past 24 hr still left an influence on the waves at the observation site although the influence decreases with time. Physically, it is an implicit but simpler consideration of wind fetch/duration. Further data modeling experiments indicated that the decisive factor for the Hs at the site is the wind speed. Wind directions slightly improve the prediction, indicating that waves are slightly affected by the underwater seabed slope along different wind directions, and northwest winds cause the strongest waves at the site. Adding atmospheric pressure or water depth even reduces the accuracy, which indicated that storm surges and wave deformations under different tide levels have a weak impact on Hs. The proposed local wave model can be easily constructed with available wind and wave data, making it expandable to other regions dominated by wind waves.

Application of Empirical Mode Decomposition and Hodrick Prescot filter for the prediction single step and multistep significant wave height with LSTM

The study discusses the application of the Empirical Model Decomposition (EMD) and Hodrick Prescot (HP) filter for significant wave height prediction. Long Short-Term Memory (LSTM) is applied for sequence predictions in Natural Language Processing (NLP). LSTM can also be modeled to time series forecasting, particularly for cyclic data since LSTM learns from experience to forecast the data. The time series signal is a combination of frequencies or spectra, when the LSTM is applied to the raw signal the prediction is lagged, to reduce the lag in the forecast the noise in the time series signal is filtered. Since, the time series consists of various frequency components, filtering the higher-frequency components is required to reduce the delay in prediction from the LSTM neural network model. The EMD is applied to the original time series wave data to split the signal into several frequencies in time series or Intrinsic Mode Functions (IMFs). Similarly, when the HP filter is applied to the original wave data or time series signal it gives a trend and cycle. The LSTM is applied to the IMFs and HP filter trend time series to predict the EMD-IMFs and Trend respectively. All the predicted IMFs are summed to compare with the original raw time series. The single step and multistep prediction or forecasting is carried out for 1-h interval, 6-h, 12-h, and 24 h interval. With the increase in forecasting interval the error values also increased and changing the lambda parameter of HP filter played a critical step for the multistep prediction. The EMD-LSTM is computationally expensive as it takes higher amount time to predict each IMF compared to HP-LSTM. Finally, the results are compared with between normal LSTM, EMD-LSTM and HP-LSTM.

Multi factors-PredRNN based significant wave height prediction in the Bohai, Yellow, and East China Seas

IntroductionCurrently, deep-learning-based prediction of Significant Wave Height (SWH) is mostly performed for a single location in the ocean or simply relies on a single factor (SF). Such approaches have the disadvantage of lacking spatial correlations or dynamic complexity, leading to an inevitable growth of the prediction error with time.MethodsHere, attempting a solution, we develop a Multi-Factor (MF) data-driven 2D SWH prediction model for the Bohai, Yellow, and East China Seas (BYECS). Our model is developed based on a multi-channel PredRNN algorithm that is an improved deep-learning calculation of the ConvLSTM.ResultsIn our model, the MF of historical SWH, 10 m surface winds, ocean surface currents, bathymetries, and open boundaries are used to predict 2D SWH in the next 1-72h. Our modeled SWHs show the correlation coefficients as 0.98, 0.90, and 0.87 for the next 6h, 24h, and 72h, respectively.DiscussionAccording to the ablation experiments, winds are the dominant factor in the MF model and the memory-decoupling module is the key improvement of the PredRNN compared to the ConvLSTM. Furthermore, when the historical SWH is excluded from the input, the correlation coefficients remain around 0.95 in the 1-72h prediction due to the elimination of the error accumulation. It was worse than the MF-PredRNN with the historical SWH before 10h but better than it after 10h. Overall, for the prediction of SWH in the BYECS, our MF-PredRNN-based 2D SWH prediction model significantly improves the accuracy and extends the effective prediction time length.

A novel hybrid model based on grey wolf optimizer and group method of data handling for the prediction of monthly mean significant wave heights

Significant wave height prediction is challenging owing to the nonlinear and nonsmooth attributes of wave heights. This study presents a hybrid model coupling group method of data handling (GMDH) with grey wolf optimizer (GWO) for the prediction of significant wave heights. The datasets were assembled from three different observations, Stations 41001, 41002 and 44004 in the Atlantic; the datasets of Stations 41001 and 41002 were used for training, and those of Station 44004 were used for testing. The performance of the GWO-GMDH model was compared with four artificial intelligence models, the GMDH, gene expression programming (GEP), adaptive neuro-fuzzy inference system (ANFIS) and back propagation (BP) neural network models, and one empirical equation derived by Buckingham π-theorem. Both regression plots and statistical indices (e.g., correlation coefficient (R), root mean squared error (RMSE), mean squared error (MSE) and mean absolute percentage error (MAPE)) were adopted to evaluate the performance of the hybrid GWO-GMDH model. The MSE, RMSE, MAPE and R values were 0.041, 0.202, 7.353% and 0.953, respectively, for the training datasets and 0.031, 0.175, 7.598% and 0.941, respectively, for the testing datasets. Compared with the single GMDH model, the statistical indices of the training datasets of the hybrid GWO-GMDH model were almost the same; however, the MSE, RMSE and MAE values decreased by 24.39%, 13.37% and 7.95%, respectively, and the R value increased by 2.28% in the testing datasets. Compared with the GEP, BP, and ANFIS models and empirical equation models, the GWO-GMDH model also shows high accuracy and robustness, especially compared with empirical formulations. In addition, a graphical user interface (GUI) was developed to facilitate the application of practical engineering use.

A training strategy to improve the generalization capability of deep learning-based significant wave height prediction models in offshore China

Accurate forecasting of significant wave height (SWH) is crucial for ensuring the safety of marine navigation. To achieve good accuracy, deep learning models need to be trained separately using SWH data from all forecast locations. However, improving the generalizability of SWH prediction models is vital for practical engineering purposes. This paper proposes a training strategy that utilizes multi-point data fusion by using wave data obtained from different locations to construct a training dataset. To verify the feasibility of training strategy, the artificial neural network (ANN), long short-term memory (LSTM), and temporal convolutional network (TCN) models are used to test in China offshore. The RMSE and MAPE of different models with 2h advance forecasts are almost 0.05 and 4%, indicating that the models have good forecasting performance. Additionally, the models exhibit consistency with the model trained solely by single position data, which demonstrates that the training strategy applies to various models. In addition, in sea areas without wave training data, two locations are randomly selected and used in the pre-trained model to predict SWH. The various models demonstrate favorable forecasting results, further demonstrating that the training strategy proposed in this study can enhance the generalizability of models.

Hourly significant wave height prediction via singular spectrum analysis and wavelet transform based models

Generation of significant wave height (SWH) is considered as a complex and stochastic dynamical process whose prediction is vital for effective marine, ocean engineering, sustainable development and scientific phenomena. Based on literature review, despite numerous research attempts to forecast significant wave height with short prediction time horizons, they are incapable in yielding accurate SWH predictions. To achieve this end wavelet techniques have been intensively employed as data pre-processing tools and, have been incorporated with soft computing based approaches to improve the prediction performance of developed models. However, wavelet algorithm has some limitations such as shift sensitivity, poor directionality and lack of phase information. In addition, this technique suffers from time consuming complicated mathematical procedures. In the present study, as a way of addressing the shortcomings of wavelet tool and enhancing prediction accuracy with extended time horizons, singular spectrum analysis (SSA) is proposed as a decomposition procedure. The prediction accuracy of the three distinct models is contrasted by means of diagnostic metrics, Mean Square Error (MSE), the Nash-Sutcliffe Coefficient of efficiency (CE) and determination of coefficient (R2). With its lowest MSE and highest CE value SSA-Fuzzy model clearly outperformed the stand alone Fuzzy and W-Fuzzy models in predicting hourly SWH for all stations and future time horizons. This implies that SSA technique has the utmost capability to decompose measured data effectively into its deterministic and stochastic components.

An EMD–PSO–LSSVM Hybrid Model for Significant Wave Height Prediction

The accurate prediction of significant wave height (SWH) offers major safety improvements for coastal and ocean engineering applications. However, the significant wave height phenomenon is nonlinear and nonstationary, which makes any prediction work a non-straightforward task. The aim of the research presented in this paper is to improve the predicted significant wave height via a hybrid algorithm. Firstly, an empirical mode decomposition (EMD) is used to preprocess nonlinear data, which are decomposed into several elementary signals. Then, a least squares support vector machine (LSSVM) with nonlinear learning ability is adopted to predict the SWH, and a particle swarm optimization (PSO) automatically performs the parameter selection of the LSSVM modeling. The results show that the EMD–PSO–LSSVM model can compensate for the lag in the prediction timing of the prediction models. Furthermore, the prediction performance of the hybrid model has been greatly improved in the deep-sea area; the prediction accuracy of the coefficient of determination (R2) increases from 0.991, 0.982, and 0.959 to 0.993, 0.987, and 0.965, respectively. The prediction performance results show that the proposed EMD–PSO–LSSVM performs better than the EMD–LSSVM and LSSVM models. Therefore, the EMD–PSO–LSSVM model provides a valuable solution for the prediction of SWH.

Application of nested artificial neural network for the prediction of significant wave height

Significant wave height is the most important parameter in feasibility studies and the design of wave energy converters. In this study, the novel nested artificial neural networks were developed and applied to predict significant wave height at twenty selected locations of the North Sea. A nested artificial neural network applies nonlinear machine learning models as transfer functions in the neurons of networks. Two input parameters comprising wind speed and wind direction were implemented to train the derived models. The results show that the derived nonlinear machine learning models are about 18.39% more accurate than the linear regression technique. The statistical indices confirm that the nested artificial neural network may increases the accuracy of traditional models by up to 34%. Among all applied models, the nested artificial neural network developed based on the integration of particle swarm optimization algorithm and adaptive neuro-fuzzy inference system, with RMSE = 0.525m and R2 = 0.84, provides the most accurate prediction of wave heights. The high accuracy of the results indicates that if computational time is not a very critical factor for users, then the application of nested artificial neural networks may be recommended for the modeling of wave parameters and other complex problems.

Prediction of significant wave height using machine learning and its application to extreme wave analysis

Prediction of significant wave height using machine learning and its application to extreme wave analysis

Significant wave height prediction through artificial intelligent mode decomposition for wave energy management

The prediction of significant wave height (SWH) is crucial for managing wave energy. While many machine learning studies have focused on accurately predicting SWH values within hours in advance, the primary concern should be given to the level of the wave height for real-world applications. In this paper, a classification framework for the time-series of SWH based on Transformer encoder (TF) and empirical mode decomposition (EMD) is developed, which can provide a lead time of 6 to 48 h with the fixed thresholds of 2 m for high level waves and 1.5 m for low level waves. The performance of this approach is compared to that of three mainstream algorithms with and without EMD features. Results from the datasets collected from buoy measurements in the Atlantic Ocean indicate that the optimal mean accuracy at a lead time of 6 h was 99.1% and the average training time was 75 s, demonstrating the accuracy and efficiency of this proposed model. This study provides valuable tools and references for real-world SWH prediction applications.

Simulating Meteorological and Water Wave Characteristics of Cyclone Shaheen

The Bay of Bengal and Arabian Sea are annually exposed to severe tropical cyclones, which impose massive infrastructure damages and cause the loss of life in coastal regions. Cyclone Shaheen originally generated in the Bay of Bengal in 2021 and translated a rare east-to-west path toward the Arabian Sea. Although the cyclone’s wind field can be obtained from reanalysis datasets such as ERA5 (fifth generation European Centre for Medium-Range Weather Forecasts), the wind speed cannot be reproduced with realistic details in the regions close to the center of cyclone due to spatial resolution. In this study, to address this problem, the high-resolution advanced Weather Research and Forecasting (WRF) model is used for simulation of Shaheen’s wind field. As a critical part of the study, the sensitivity of the results to the planetary boundary layer (PBL) parameterization in terms of the track, intensity, strength and structure of the cyclone Shaheen is investigated. Five experiments are considered with five PBL schemes: Yonsei University (YSU); Mellor–Yamada–Janjić (MYJ); Mellor–Yamada–Nakanishi–Niino level 2.5 (MYNN); Asymmetric Convective Model version 2 (ACM2); Quasi-Normal Scale Elimination (QNSE). The track, intensity, and strength of the experiments are compared with the wind fields obtained from the Joint Typhoon Warning Centre (JTWC) dataset. The results imply the high dependency of the track, intensity, and strength of the cyclone to the PBL parameterization. Simulated tracks with non-local PBL schemes (YSU and ACM2) outperformed those of the local PBL schemes (MYJ, MYNN, and QNSE), especially during the rapid intensification phase of Shaheen before landfall. The YSU produced highly intensified storm, while the ACM2 results are in better agreement with the JTWC data. The most accurate track was obtained from the ERA5 data; however, this dataset overestimated the spatial size and underestimated the wind speed. The WRF model using either YSU or ACM2 overestimated the wind speed compared to that of the altimeter data. The YSU and ACM2 schemes were able to reproduce the observed increase in wind speed and pressure drop at in situ stations. The wind data from EAR5 and cyclone parametric model were applied to the SWAN model to simulate the wave regime in the Arabian Sea during the time that Shaheen was translating across the region. Janssen formulation for wind input and whitecapping dissipation source terms in combination with both ERA5 and hybrid wind were used and the minimum combined error in the prediction of significant wave height (Hs) and zero up-crossing wave period (Tz) was examined. The maximum significant wave height for hybrid wind is higher than that of ERA5, while the cyclone development was successfully inferred from the wave field of the hybrid data.

Significant wave height prediction based on deep learning in the South China Sea

Significant wave height (SWH) prediction can effectively improve the safety of marine activities and reduce the occurrence of maritime accidents, which is of great significance to national security and the development of the marine economy. In this study, we comprehensively analyzed the SWH prediction performance of the recurrent neural network (RNN), long short-term memory network (LSTM), and gated recurrent unit network (GRU) by considering different input lengths, prediction lengths, and model complexity. The experimental results show that (1) the input length impacts the prediction results of SWH, but it does not mean that the longer the input length, the better the prediction performance. When the input length is 24h, the prediction performance of RNN, LSTM, and GRU models is better. (2) The prediction length influences the SWH prediction results. As the prediction length increases, the prediction performance gradually decreases. Among them, RNN is not suitable for 48h long-term SWH prediction. (3) The more layers of the model, the better the SWH prediction performance is not necessarily. When the number of layers is set to 3 or 4, the model’s prediction performance is better.

Prediction of significant wave height based on EEMD and deep learning

Accurate and reliable wave significant wave height(SWH) prediction is an important task for marine and engineering applications. This study aims to develop a new deep learning algorithm to accurately predict the SWH of deep and distant ocean. In this study, we combine two methods, Ensemble Empirical Mode Decomposition (EEMD) and Long Short-Term Memory (LSTM), to construct an EEMD-LSTM model, and explore the optimal parameters of the model through experiments. A total of 5328 hours of SWH data from November 30, 2020, to July 9, 2021, are used to train and test the model to predict the SWH for the future 1h, 3h, 6h, 12h, and 18h. The results show that the EEMD-LSTM model has the best results compared with other comparative models for short-term and medium- and long-term predictions. The RMSEs are 0.0204, 0.0279, 0.0452, 0.0941, and 0.1949 for the SWH prediction in the future 1, 3, 6, 12, and 18 h. It can be used as a rapid SWH prediction system to ensure navigation safety to a certain extent, which has great practical significance and application value.

Short-term probabilistic prediction of significant wave height using bayesian model averaging: Case study of chabahar port, Iran

Accurate predictions of significant wave heights are important for a number of maritime applications, such as design of coastal and offshore structures. In the present study, an ensemble approach of Bayesian model averaging (BMA) is used for the prediction of significant wave heights. The BMA is used in conjunction with three machine learning methods: Multivariate Adaptive Regression Spline (MARS), Random Forest (RF) and Gradient Boosted Regression Trees (GBRT). Daily data from three wave monitoring stations located near the Chabahar Bay in the Gulf of Oman are used to evaluate performance of the methods in predicting the significant wave height for the lead times of one, two, three and six days. The machine learning methods are also compared with auto-regressive method. The obtained results indicate that BMA model performs slightly better than the GBRT, MARS, RF and AR methods in some cases especially for the six-day ahead time horizon and all the methods are generally competitive in predicting significant wave heights.

Spatial ocean wave height prediction with CNN mixed-data deep neural networks using random field simulated bathymetry

With climate change impacts like sea level rise and changing storms, proper prediction of significant wave height (SWH) becomes increasingly important for coastal protection and marine disaster prevention. In the coastal areas of the North Sea, the morphodynamically changing ebb-tidal delta (ETD) sandbanks cause non-linear wave propagation. Therefore, consideration of spatial dependencies using bathymetric data is essential for accurate machine learning predictions. We developed a novel two-dimensional mixed-data deep convolutional neural network (CNN) for spatial SWH prediction in the nearshore area of Norderney, Germany. To overcome the problem of limited bathymetry data, dynamic ETD sandbank morphologies were simulated using random fields and used as model input for the first time. The regional mixed-data CNN was also trained and tested with in-situ metocean input data from 2004 to 2017 and SWAN-modeled ground truth wave fields as output. The proposed CNN architecture outperformed other benchmark models on the test data (RMSE = 0.097 m, R2 = 0.977, MAAPE = 6.7%). Further validation on 59 buoy measurements revealed very similar accuracy of the CNN and SWAN. Compared to the commonly used numerical SWAN model, the trained CNN reduced the computational cost by a factor of more than 300000, making it an efficient surrogate predictive model.

Prediction of Significant Wave Heights with Engineered Features from GNSS Reflectometry

Estimating reflector heights at stationary GNSS sites with interferometric reflectometry (IR) is a well-established technique in ocean remote sensing. Additionally, IR offers the possibility to estimate the significant wave height (SWH) with a linear model using the damping coefficient from an inverse modelling applied to GNSS signal-to-noise ratio (SNR) observations. Such a linear model serves as a benchmark in the present study, where an alternative approach for the estimation of both SWH and reflector height is presented that is based on kernel regression and clustering techniques. In this alternative approach, the reflector height is estimated by analyzing local extrema occurring in the interference pattern that is present in GNSS SNR observations. Various predictors are derived from clustering statistics and the estimated reflector heights. These predictors are used for the SWH determination with supervised machine learning. Linear models, bagged regression trees, and artificial neural networks are applied and respective results are compared for various predictor sets. In a second step, damping coefficients obtained from the inverse modelling mentioned above are additionally taken into account as predictors. The usability of the alternative approach is demonstrated. Compared to the benchmark, a significant improvement in terms of accuracy is found for an artificial neural network with predictors from both the alternative and the inverse modelling approach.

A Wave Directionality and a Within-Year Wave Climate Variability Effects on the Long-Term Extreme Significant Wave Heights Prediction in the Adriatic Sea

The extreme significant wave height predictions often neglect within-year wave climate variability and wave directionality. Depending on a geographical region, local wind patterns and year climate variability could have an influence on the long-term prediction of waves. The Adriatic Sea having two dominant wind patterns of different characteristics, Bura and Jugo, is a great example for the case study. The 23-year hindcast wave data used in the presented study is extracted from the WorldWaves database. Based on wind and wave data, annual extreme significant wave heights generated by different wind patterns and for different months are fitted by Gumbel distribution using maximum likelihood estimation. Combined long-term extremes are then predicted by calculating system probability. It was found that considering the wave directionality, and especially the seasonality of wave climate, leads to a larger prediction of extreme significant wave heights. The extreme value prediction considering wave directionality on average yields 4% larger significant wave heights, while considering within-year climate variability leads to, on average, 8% larger extremes compared to the predictions when both effects are neglected.