Wave Height Prediction Research Articles

Fuzzy-based ensemble methodology for accurate long-term prediction and interpretation of extreme significant wave height events

Providing an accurate prediction of Significant Wave Height (SWH), and specially of extreme SWH events, is crucial for coastal engineering activities and holds major implications in several sectors as offshore renewable energy. With the aim of overcoming the challenge of skewness and imbalance associated with the prediction of these extreme SWH events, a fuzzy-based cascade ensemble of regression models is proposed. This methodology allows to remarkably improve the predictive performance on the extreme SWH values, by using different models specialised in different ranges on the target domain. The method’s explainability is enhanced by analysing the contribution of each model, aiding in identifying those predictor variables more characteristic for the detection of extreme SWH events. The methodology has been validated tackling a long-term SWH prediction problem, considering two case studies over the southwest coast of the United States of America. Both reanalysis data, providing information on various meteorological factors, and SWH measurements, obtained from the nearby stations and the station under examination, have been considered. The goodness of the proposed approach has been validated by comparing its performance against several machine learning and deep learning regression techniques, leading to the conclusion that fuzzy ensemble models perform much better in the prediction of extreme events, at the cost of a slight deterioration in the rest of the samples. The study contributes to advancing the SWH prediction field, specially, to understanding the behaviour behind extreme SWH events, critical for various sectors reliant on oceanic conditions.

Using Machine Learning Techniques to Predict Significant Wave Height Compared with Parametric Methods

Prediction of Sea Wave parameters is an important issue as it is the main design factor for maritime structures. Previously, researchers have used many parametric and numerical approaches, which may be complex in application, take a long time in preparation and sometimes require a bathymetric survey. Recently, soft computing techniques such as Fuzzy Inference Systems, Genetic Algorithm, Machine Learning, etc. have been used to predict sea wave parameters in many marine areas around the world. The ease of application, high accuracy and low computational time of these techniques make them a very good choice in many engineering applications. This study focuses on prediction of significant wave height (Hs) by applying one of the most advanced Machine Learning techniques known as Support Vector Machine (SVM). SVM models are built on the basis of different Kernel functions (Linear, Sigmoid, Radial Basis Function, and Polynomial) which transform the input data into an n-dimensional space where a hyperplane can be generated to partition the data. The results of SVM models are analyzed, evaluated and then compared with the results of commonly used parametric models (P-M, SPM, and CEM). This study shows that the P-M model has reliable and satisfactory results among all parametric models, as its statistical errors are close to those of SVM models (RBF and Polynomial), while all of them are identical in their correlation factors (0.999). Moreover, the parametric models (SPM and CEM) are more accurate in their results than the SVM models (Linear and Sigmoid). Also, this study confirms that the SVM models (RBF and polynomial) are the most accurate models overall, as they have the best generalization error among all models. Finally, it can be concluded that SVM models (RBF and Polynomial) are a promising technique in the sea wave height prediction and can be used as an economic and accurate alternative solution to other prediction models.

RIME-CNN-BiLSTM: A novel optimized hybrid enhanced model for significant wave height prediction in the Gulf of Mexico

Accurate prediction of SWH in the ocean is critical to the development of ocean energy technologies. However, existing forecasting models have limitations in accuracy and reliability, which directly affect the efficiency of ocean energy utilization. To address this problem, this paper proposes a new ocean SWH prediction model, RIME-CNN-BiLSTM, for predicting 1, 6, 12, and 24 h SWH at three buoy observing stations in the Gulf of Mexico. The model combines the RIME algorithm, CNN, and BiLSTM to comprehensively capture multiple parameters that affect wave heights, such as sea breeze, waves, barometric pressure, and temperature. The parameters of the CNN-BiLSTM model are optimized by the RIME algorithm, which significantly improves the prediction accuracy and generalization ability. Compared with the traditional model, RIME-CNN-BiLSTM captures the nonlinear features more accurately, has better prediction ability for outliers, and shows stronger generalization performance in different sea areas of the Gulf of Mexico. In terms of predicting the wave height in the next 24 h, the improvements are 7.065%, 3.646% and 5.186%, respectively. The results show that the RIME-CNN-BiLSTM model performs well in all prediction time periods, significantly outperforms other benchmark models, and is able to accurately capture nonlinear features and effectively predict outliers.

Development of a Wave Model Component in the First Coupled Global Ensemble Forecast System at NOAA

Abstract We describe the development of the wave component in the first global-scale coupled operational forecast system using the Unified Forecasting System (UFS) at the National Oceanic and Atmospheric Administration (NOAA), part of the US National Weather Service (NWS) operational forecasting suite. The operational implementation of the atmosphere-wave coupled Global Ensemble Forecast System version 12 (GEFSv12) in September 2020 was a critical step in NOAA’s transition to the broader community-based UFS framework. GEFSv12 represents a significant advancement, extending forecast ranges and empowering the NWS to deliver advanced weather predictions with extended lead times for high-impact events. The integration of a coupled wave component with higher spatial and temporal resolution and optimized physics parameterizations notably enhanced forecast skill and predictability, particularly benefiting winter storm predictions of wave heights and peak wave periods. This successful endeavor encountered challenges that were addressed by the simultaneous development of new features that enhanced wave model forecast skill and product quality and facilitated by a multidisciplinary team collaborating with NOAA’s operational forecasting centers. The GEFSv12 upgrade marks a pivotal shift in NOAA’s global forecasting capabilities, setting a new standard in wave prediction. We also describe the coupled GEFSv12-Wave component impacts on NOAA operational forecasts, and ongoing experimental enhancements, which altogether represent a substantial contribution to NOAA’s transition to the fully-coupled UFS framework.

Near real-time significant wave height prediction along the coastline of Queensland using advanced hybrid machine learning models

Near real-time significant wave height prediction along the coastline of Queensland using advanced hybrid machine learning models

Regional significant wave height forecast in the East China Sea based on the Self-Attention ConvLSTM with SWAN model

Accurate prediction of regional significant wave heights is crucial for marine resource development, especially in areas with limited wave observations. This paper proposes a method for predicting regional significant wave heights by integrating the numerical wave model Simulating Wave Nearshore (SWAN) with the spatio-temporal prediction network Self-Attention ConvLSTM. The SWAN model is used to simulate regional significant wave heights in the East China Sea. To improve simulation accuracy, calibration of wind input, whitecapping dissipation, quadruplet wave–wave interactions, and bottom friction parameterization schemes in the model source terms were conducted, resulting in a simulated correlation coefficient of 0.97 with measured significant wave heights. The regional significant wave height training dataset constructed using the SWAN model preserves the intrinsic relationships between waves, wind speed, and wind direction over a recent period. Subsequently, a regional prediction system is built based on the output of the SWAN model, integrating the self-attention mechanism into the spatio-temporal prediction model ConvLSTM to construct SA-ConvLSTM. This model extracts correlated features among regional waves from the training dataset to predict future significant wave heights at different time intervals. The prediction performance of four spatio-temporal forecasting networks was compared to verify the accuracy of the SA-ConvLSTM model. The average errors in predicting regional significant wave heights at 3, 6, and 12 h were 0.07 m, 0.09 m, and 0.09 m, respectively. The R-Square metrics for these three prediction intervals were 0.85, 0.78, and 0.7, respectively.

Research on numerical modeling of two-dimensional freak waves and prediction of freak wave heights based on LSTM deep learning networks

Freak waves have posed a serious threat to the safety of marine structures. Thus, the accurate simulation and prediction of freak waves are crucial for maritime safety. This paper proposes a nonlinear numerical method based on phase modulation. This method achieves precise time and location simulation of two-dimensional freak waves, while preserving the key statistical characteristics of the wave sequence, thereby obtaining more accurate two-dimensional wave height information. Additionally, this paper constructs a Long Short-Term Memory (LSTM) deep neural network integrated with a Sequence-to-Sequence (seq2seq) framework for predicting sequences of freak wave heights. In this study, we conduct an in-depth predictive analysis of the experimental data for sequences of freak wave heights. And this paper provides a comprehensive assessment of the performance of Recurrent Neural Networks (RNNs), Gated Recurrent Units (GRUs), and Long Short-Term Memory (LSTM) networks in the task of freak wave prediction. The experimental results indicate that the seq2seq-LSTM model demonstrates significant performance advantages in predicting the wave heights of freak waves, particularly for long-term predictions. In summary, the numerical simulation method based on phase modulation and the improved seq2seq-LSTM deep learning model are of significant practical value for enhancing the safety of offshore platforms and ships.

Hybrid framework of deep extreme learning machine (DELM) based on sparrow search algorithm for non-stationary wave prediction

Accurate and trustworthy wave height forecast is essential for the efficient exploitation of wave energy. However, the non-linearity and non-stationarity of waves present a challenge task when using the conventional statistical models in the ocean wave forecasting. Aiming at these problems, this paper proposes a short-term wave height prediction method based on the Variational Mode Decomposition (VMD), Deep Extreme Learning Machine (DELM) and Sparrow Search Algorithm (SSA). Specifically, the original wave height data is initially decomposed into numerous sub-series from high to low frequency by VMD technique. Subsequently, the SSA method is employed to optimize the DELM parameters to enhance the functionality of the basic DELM model. Three wave height datasets located in the North Pacific Ocean are employed as cases in this paper. In comparison with other benchmark models, the RMSE parameters of VMD-SSA-DELM model are reduced by 35.59%–73.33% even at 10-h lead time by analyzing different forecast durations, which demonstrate the proposed model's superiority in short-term wave height prediction.

Extraction of lanceolate imagery for analysis of mangrove extent and shoreline changes

This study aims to determine the area of Topang Island's mangrove forest, an area experiencing extreme line changes and the magnitude of the coastline change rate from 1991 to 2021 on Topang Island, Kepulauan Meranti Regency, Riau Province. The method used in this research is remote sensing and field survey. The data obtained were discussed descriptively. The results found that the calculation of wave height prediction on the coast of Topang Island was included in the low category with an average height of 0.12 meters. The research area is dominated by abrasion, based on visual observations, Topang Island has a type of peat and muddy beach. The area of mangroves on Topang Island from 2001 to 2021 saw a big change, either adding or reducing the area of mangroves. Topang Island experienced the worst abrasion in the eastern part with an average abrasion rate of 6.13 m/year, and accretion in the western part with an average accretion rate of 0.62 m/year.

Applying the multivariate Gaidai reliability method in combination with an efficient deconvolution scheme to prediction of extreme ocean wave heights

Applying the multivariate Gaidai reliability method in combination with an efficient deconvolution scheme to prediction of extreme ocean wave heights

A Slow Failure Particle Swarm Optimization Long Short-Term Memory for Significant Wave Height Prediction

Significant wave height (SWH) prediction is crucial for marine safety and navigation. A slow failure particle swarm optimization for long short-term memory (SFPSO-LSTM) is proposed to enhance SWH prediction accuracy. This study utilizes data from four locations within the EAR5 dataset, covering 1 January to 31 May 2023, including variables like wind components, dewpoint temperature, sea level pressure, and sea surface temperature. These variables predict SWH at 1-h, 3-h, 6-h, and 12-h intervals. SFPSO optimizes the LSTM training process. Evaluated with R2, MAE, RMSE, and MAPE, SFPSO-LSTM outperformed the control group in 13 out of 16 experiments. Specifically, the model achieved an optimal RMSE of 0.059, a reduction of 0.009, an R2 increase to 0.991, an MAE of 0.045, and an MAPE of 0.032. Our results demonstrate that SFPSO-LSTM provides reliable and accurate SWH predictions, underscoring its potential for practical applications in marine and atmospheric sciences.

Towards sustainable coastal management: a hybrid model for vulnerability and risk assessment

This paper presents the development of a Hybrid Model (HM) integrated with a Bayesian Network (BN) for comprehensive coastal vulnerability and risk assessment, with a focus on Konyaaltı Beach, Antalya, Turkey. The HM incorporates critical environmental parameters such as wind, waves, currents, and sediment transport to simulate conditions at vulnerable coastal areas and perform risk assessments for storm effects, flooding, and erosion. The model includes submodules for predicting coastal storms, quantifying sediment transport rates, assessing tsunami inundation severity, and categorizing storms based on beach typologies. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized for significant wave height predictions, enhancing the model's accuracy. The integration of hydrodynamic modeling, Bayesian networks, and ANFIS offers a robust framework for assessing coastal vulnerability and informing sustainable management practices. The study's results highlight the necessity for integrated risk management strategies, including adaptive infrastructure design, zoning and land use regulations, ecosystem-based management, and continuous monitoring and model refinement to enhance coastal resilience against dynamic environmental forces. This research provides valuable insights for mitigating the impacts of hazards on urban developments, contributing to the advancement of sustainable coastal management.

A Hybrid Model of Conformer and LSTM for Ocean Wave Height Prediction

This study proposes a hybrid model (Conformer-LSTM) based on Conformer and Long Short-Term Memory networks (LSTM) to overcome the limitations of existing techniques and enhance the accuracy and generalizability of wave height predictions. The model combines the advantages of self-attention mechanisms and convolutional neural networks. It captures global dependencies through multi-head self-attention and utilizes convolutional layers to extract local features, thereby enhancing the model’s adaptability to dynamic changes in time series. The LSTM component handles long-term dependencies, optimizing the coherence and stability of predictions. Additionally, an adaptive feature fusion weight network is introduced to further improve the model’s recognition and utilization efficiency of key features. Experimental data come from the National Oceanic and Atmospheric Administration buoy data, covering wave height, wind speed, and other data from key maritime areas. Evaluation metrics include Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R2), ensuring a comprehensive assessment of model performance. The results show that the Conformer-LSTM model outperforms traditional LSTM, CNN, and CNN-LSTM models at multiple sites, confirming its potential in wave height prediction.

Hybrid intelligent models for predicting weekly mean significant wave heights

Accurate predictions of significant wave heights are crucial in the field of marine and ocean engineering. This paper presents two hybrid intelligent models, EN-1 and EN-2, that combine random forest (RF) and extreme learning machine (ELM) methods through direct linear weighting and gene expression programming-based nonlinear weighting methods, respectively, for the prediction of weekly mean significant wave heights. The performances of the EN-1 and EN-2 models were compared with those of 11 reference models. The results showed that the coefficient of determination (R2), mean absolute error (MAE), root mean squared error (RMSE) and mean absolute percentage error (MAPE) of the EN-1 and EN-2 models were 0.9850, 0.0567, 0.0736 and 3.7107%, 0.9940, 0.0335, 0.0487 and 2.2373%, respectively, for the training datasets and 0.9802, 0.0627, 0.0847 and 4.1461%, 0.9754, 0.0707, 0.0966 and 4.2614%, respectively, for the testing datasets, indicating that the EN-1 and EN-2 models have good predictive performance and can be effectively used for the prediction of weekly mean significant wave heights. In addition, a sensitivity analysis was conducted to investigate the influence of the input variables on the model performance.

Forecasting Ocean Waves off the U.S. East Coast Using an Ensemble Learning Approach

Abstract This study introduces an ensemble learning model for the prediction of significant wave height and average wave period in stations along the U.S. Atlantic coast. The model utilizes the stacking method, combining three base learner models—least absolute shrinkage and selection operator (LASSO) regression, support vector machine, and multilayer perceptron—to achieve more precise and robust predictions. To train and evaluate the models, a 20-yr dataset comprising meteorological and wave data was used, enabling forecasts for significant wave height and average wave period at 1-, 3-, 6-, and 12-h intervals. The data collection involved two NOAA buoy stations situated on the U.S. Atlantic coast. The findings demonstrate that the ensemble learning model constructed through the stacking method yields significantly higher accuracy in predicting significant wave height within the specified time intervals. Moreover, the study investigates the influence of swell waves on forecasting significant wave height and average wave period. Notably, the inclusion of swell waves improves the accuracy of the 12-h forecast. Consequently, the developed ensemble model effectively estimates both significant wave height and average wave period. The ensemble model outperforms the individual models in forecasting significant wave height and average wave period. This ensemble learning model serves as a viable alternative to conventional coastal models for predicting wave parameters.

Multi-station collaborative wave height prediction based on multi-feature identification and interpretable analysis

This study proposes a novel deep learning model, the graph convolutional gated recurrent unit (GC-GRU), to address the critical challenge of accurate forecasting of ocean wave heights due to the complex nonlinear spatiotemporal variability of wave dynamics. The proposed model, which integrates the strengths of graph convolutional networks (GCNs) for spatial feature extraction and gated recurrent units (GRUs) for temporal feature extraction, allows for effective capture of complex spatiotemporal patterns in wave height data and is evaluated on a dataset of 666 observation stations in the Gulf of Mexico, forecasting wave heights up to 36 h in advance. Comparative experiments with traditional CNN and GRU models demonstrate the superior predictive performance of the GC-GRU approach. Additionally, we introduce the shapley additive explanation (SHAP) values to provide physical insights into the key physical variables and historical patterns driving the model's predictions. The results show that wind speed and mean wave period are the most influential factors related to wave height variations. It is expected that this work presents a significant advancement in wave height forecasting by introducing the innovative GC-GRU architecture and leveraging SHAP analysis to interpret the model's inner workings. The findings are expected to have important implications for enhancing coastal and maritime operations as well as informing our understanding of complex ocean wave dynamics.

Analysis of intrinsic factors in accurate wave height prediction based on model interpretability

This study addresses the ‘black box issue’ in machine learning by utilizing interpretable model mechanisms for wave forecasting. The Shapley Additive Explanation (SHAP) method is integrated into various deep learning models to evaluate the contributions of different physical features to wave height prediction. By categorizing these features based on their importance levels, the primary factors influencing wave forecasting are thoroughly investigated. The results indicate that variations in feature contribution scores are linked to physical correlations, temporal correlations, model characteristics, and data quality. Remarkably, features directly related to fundamental physical processes, such as significant wave height and average wave period, are essential for accurate predictions. Different models display varying sensitivities to specific features over time, impacting prediction accuracy. This comprehensive analysis leads to an optimized prediction approach, significantly enhancing prediction efficiency and providing a solution for training deep learning models with limited training data.

Prediction of significant wave height using a VMD-LSTM-rolling model in the South Sea of China

Accurate prediction of significant wave height is crucial for ocean engineering. Traditional time series prediction models fail to achieve satisfactory results due to the non-stationarity of significant wave height. Decomposition algorithms are adopted to address the problem of non-stationarity, but the traditional direct decomposition method exists information leakage. In this study, a hybrid VMD-LSTM-rolling model is proposed for non-stationary wave height prediction. In this model, time series are generated by a rolling method, after which each time series is decomposed, trained and predicted, then the predictions of each time series are combined to generate the final prediction of significant wave height. The performance of the LSTM model, the VMD-LSTM-direct model and the VMD-LSTM-rolling model are compared in terms of multi-step prediction. It is found that the error of the VMD-LSTM-direct model and the VMD-LSTM-rolling model is lower than that of the LSTM model. Due to the decomposition of the testing set, the VMD-LSTM-direct model has a slightly higher accuracy than the VMD-LSTM-rolling model. However, given the issue of information leakage, the accuracy of the VMD-LSTM-direct model is considered false. Thus, it has been proved that the VMD-LSTM-rolling model exhibits superiority in predicting significant wave height and can be applied in practice.

Observations of coastal infragravity wave characteristics under swell-dominated conditions

This study analyzed the characteristics of infragravity (hereafter IG) waves under a microtidal and swell-dominated wave climate based on the field observations collected in the nearshore waters (water depth: ∼ 13 m) of southern Sri Lanka. The main focus is on the dependence of nearshore IG waves on the incident short wave parameters, with particular attention to the influence of the short wave spectral shape on the IG wave characteristics. The observation results indicate that IG waves are primarily locally excited by incident swell wave energy, and accurate prediction of the IG wave height can be achieved using the parameter HS2Tm−1,0, which represents the short wave energy flux. Bound IG wave energy is much smaller than the free IG wave under conventional sea states but becomes significant under high-energy swell sea states.Higher levels of IG wave energy are found to be forced under narrower spectral shapes and smaller directional spreading short wave conditions, and these conditions typically correspond to stronger coupling strengths in the bound IG wave theory. Compared to the single-peaked spectra wave condition, the forced IG wave energy decreases under the double-peaked spectra wave condition. This is likely mainly because the latter tends to have a broader spectrum and a larger directional spreading. On the other hand, under the narrow-banded spectral short wave conditions, IG wave energy is inclined to be distributed over a lower and smaller frequency range. This is noteworthy because lower-frequency IG waves tend to be more difficult to break. In addition, the bound IG wave energy was found to increase at low tide, but for the intermediate water depths in which the observation site is located in this study, the influence of the small tidal range in the study area on the IG wave energy was not significant.

Wave Height Prediction in Maritime Transportation Using Decomposition Based Learning

Wave Height Prediction in Maritime Transportation Using Decomposition Based Learning