Explore the vast range of titles available.

The present study examines the impact of the Pacific-Japan (PJ) pattern on tropical Indo–Western Pacific Ocean significant wave heights during the boreal summer season (June through August, JJA) for the first time. The PJ pattern is a dominant teleconnection pattern characterized by meridional propagating Rossby waves over the Western North Pacific (WNP) and East Asia. The strong southwesterly monsoon winds prevail over the North Indian Ocean (NIO) during JJA inducing strong wave heights in the mean state. The regression analysis of significant wave height anomalies on the PJ index exhibits strong negative wave height anomalies over the Bay of Bengal (BoB), the tropical WNP region and slightly weaker negative anomalies over the Arabian Sea (AS) due to a reduction in the wind-wave growth. The weakening of wave heights in the BoB and WNP regions during PJ is attributed to the anomalous low-level anticyclonic circulation accompanied by high sea-level pressure anomalies over the BoB and WNP regions. The anomalous anticyclonic circulation opposes the mean south-westerlies and reduces the wave heights over the NIO and WNP. Further, the composite analysis of positive and negative PJ patterns display significant asymmetries in their signature on the wind and wave parameters. Thus, our findings suggest that the WNP region’s climate conditions strongly modulate the NIO’s surface waves.

The Black Sea coasts from the northwest of Turkey through Crimea to Georgia were strongly affected by severe storms in Autumn, 2023. The aim of the work is to compare the performance of different wave model approaches and wind datasets in extreme weather conditions in the Black Sea. The study covers the continuous period from the 1st to the 30th of November including two strong storms with wave heights up to 9–10 m. Wave simulations are performed using WAM and the 2D parametric model for surface wave development suggested in Kudryavtsev et al. (2021a). The wave models are forced by hourly wind fields from four datasets: ECMWF Reanalysis (ERA5), ECMWF Level-4 bias-corrected operational model, NCEP (CFSv2), and the regional WRF-ARW model with 6-hour NCEP/NCAR atmospheric forecast as input. The high-resolution Level-4 wave analysis for the Black Sea produced by CMEMS (also using WAM Cycle 6) is also considered. Simulation results are validated against along-track altimeter measurements of significant wave height, CFOSAT SWIM information on dominant wavelength and wave direction, and in-situ data from an oceanographic platform near Crimea. All models demonstrate their overall good performance, though third-generation wave spectral models give an expectedly higher correlation between simulations and observed data, while the parametric model is less accurate. Some recommendations to combine wind and wave models for the most accurate predictions are further given. As known, the wind speed fields produced by ECMWF are underestimated at winds higher than 15–20 m/s. While the wind correction is crucial when using the parametric model, WAM better reproduces the observed extreme waves without it. As also obtained, WAM simulations forced by NCEP and WRF winds lead to an overestimation of the largest storm waves. Increased resolution of the wind fields does not lead to significant improvement in the quality of wave predictions, which can be explained by the wind accumulation effect during wave development.

As an emerging remote sensing technology, GNSS reflectometry (GNSS-R) has been widely investigated for retrieving ocean parameters including ocean significant wave height (SWH). Ocean SWH consists of contribution from swell and wind waves, which are commonly modeled separately in the field of marine science and engineering to facilitate practical application. In this study, we present a deep convolutional neural network (DCNN) model for retrieving swell and wind wave SWHs. The DCNN model makes use of auxiliary data and effective DDM features extracted in the convolution layer, and it is trained by using the ERA5 data and CYGNSS observations. The proposed DCNN model and seven existing models [i.e., random forest, extremely randomized trees, bagging tree (BT), decision tree, support vector machine (SVM), artificial neural network, and convolutional neural network] were extensively tested using the ERA5 and WaveWatch III (WW3) data. The results show that when ERA5 is used as reference data, the proposed DCNN model performs best among the eight models, with the root mean square errors (RMSEs) of retrieving swell and wind wave SWH being better than 0.394 m and 0.397 m, respectively, and the correlation coefficient ( R ) being 0.90. Compared with the SVM model, RMSEs are improved by 28.82% and 31.92%, respectively. When WW3 is employed as reference, the RMSEs of retrieving swell and wind wave SWH are better than 0.497 m and 0.502 m, respectively, with R of 0.89 and 0.90. Compared with the BT model, RMSEs are improved by 26.74% and 27.41%, respectively. The research also found that the auxiliary variables are important for swell and wind wave SWH retrieval. Furthermore, the retrieval of SWH for swells and wind waves using spaceborne GNSS-R technology is affected by rainfall, resulting in about 6% increase in RMSE. This method provides a new idea for studying global ocean swell and wind waves using CYGNSS data.

This study investigates the contribution of external forcings on global and regional ocean wave height change during 1961–2020. Historical significant wave height (Hs) produced for different CMIP6 external forcings and preindustrial control conditions following the Detection and Attribution Model Intercomparison Project (DAMIP) are employed. The internal variability ranges are compared with different external forcing scenario. Statistically significant linear trends in Hs computed over regional ocean basins are found to be mostly associated with anthropogenic forcings: greenhouse gas‐only (GHG) and aerosol‐only (AER) forcing. For Hs, GHG signals are robustly detected and dominant for most of the global ocean, except over North pacific and South Atlantic, where AER signals are dominant. These results are supported by multi‐model analysis for wind speed. The remarkable increase in Hs over the Arctic (22.3%) and Southern (8.2%) Ocean can be attributed to GHG induced sea‐ice depletion and larger effective fetch along with wind speed increase. Plain Language Summary We quantify the influence of anthropogenic forcings (greenhouse gas‐only and aerosol‐only forcing) and natural forcing to the significant wave height trends during 1961–2020 using CMIP6 individual forcing experiments. It is shown that anthropogenic influence is majorly responsible for the significant wave height changes and natural (solar and volcanic activities) forcings show limited influence. The human‐induced greenhouse gas increases are found to be the dominating factor for most of the global ocean, whereas anthropogenic aerosols are the dominating forcing for a few ocean basins, such as North Pacific and South Atlantic. The multimodel analysis for wind speed corroborates the relative dominance of signals in wave height change. In the polar ocean (Arctic and Southern Ocean), we see exceptional wave height increase compared to other regions. Sea‐ice decline associated with greenhouse gas forcing provides larger fetch for the waves to grow in polar region. Moreover, the contrasting influence of greenhouse gas and aerosol forcing to sea‐ice area and wind speed changes are shown to drive the total wave height changes. Key Points CMIP6/DAMIP simulations show that anthropogenic signals are robustly detected for the significant wave height (Hs) trends during 1961–2020 Greenhouse gases are the major contributor for Hs trends over the global ocean, but aerosols dominance is seen for a few regional basins High increase in Hs over the Polar oceans is due to greenhouse gas induced sea‐ice decline, fetch enlargement and wind speed increase

Wave forecasts, though integral to ocean engineering activities, are often conducted using computationally expensive and time-consuming numerical models with accuracies that are blunted by numerical-model-inherent limitations. Additionally, artificial neural networks, though significantly computationally cheaper, faster, and effective, also experience difficulties with nonlinearities in the wave generation and evolution processes. To solve both problems, this study employs and couples empirical mode decomposition (EMD) and a long short-term memory (LSTM) network in a joint model for significant wave height forecasting, a method widely used in wind speed forecasting, but not yet for wave heights. Following a comparative analysis, the results demonstrate that EMD-LSTM significantly outperforms LSTM at every forecast horizon (3, 6, 12, 24, 48, and 72 h), considerably improving forecasting accuracy, especially for forecasts exceeding 24 h. Additionally, EMD-LSTM responds faster than LSTM to large waves. An error analysis comparing LSTM and EMD-LSTM demonstrates that LSTM errors are more systematic. This study also identifies that LSTM is not able to adequately predict high-frequency significant wave height intrinsic mode functions, which leaves room for further improvements.

Deep learning methods have excellent prospects for application in wave forecasting research. This study employed the convolutional LSTM (ConvLSTM) algorithm to predict the South China Sea (SCS) significant wave height (SWH). Three prediction models were established to investigate the influences of setting different parameters and using multiple training data on the forecasting effects. Compared with the SWH data from the China–France Ocean Satellite (CFOSAT), the SWH of WAVEWATCH III (WWIII) from the pacific islands ocean observing system are accurate enough to be used as training data for the ConvLSTM-based SWH prediction model. Model A was preliminarily established by only using the SWH from WWIII as the training data, and 20 sensitivity experiments were carried out to investigate the influences of different parameter settings on the forecasting effect of Model A. The experimental results showed that Model A has the best forecasting effect when using three years of training data and three hourly input data. With the same parameter settings as the best prediction performance Model A, Model B and C were also established by using more different training data. Model B used the wind shear velocity and SWH as training and input data. When making a 24-h SWH forecast, compared with Model A, the root mean square error (RMSE) of Model B is decreased by 17.6%, the correlation coefficient (CC) is increased by 2.90%, and the mean absolute percentage error (MAPE) is reduced by 12.2%. Model C used the SWH, wind shear velocity, wind and wave direction as training and input data. When making a 24-h SWH forecast, compared with Model A, the RMSE of Model C decreased by 19.0%, the CC increased by 2.65%, and the MAPE decreased by 14.8%. As the performance of the ConvLSTM-based prediction model mainly rely on the SWH training data. All the ConvLSTM-based prediction models show a greater RMSE in the nearshore area than that in the deep area of SCS and also show a greater RMSE during the period of typhoon transit than that without typhoon. Considering the wind shear velocity, wind, and wave direction also used as training data will improve the performance of SWH prediction.

Significant wave height (SWH) is a key parameter for monitoring the state of waves. Accurate and long-term SWH forecasting is significant to maritime shipping and coastal engineering. This study proposes a transformer model based on an attention mechanism to achieve the forecasting of SWHs. The transformer model can capture the contextual information and dependencies between sequences and achieves continuous time series forecasting. Wave scale classification is carried out according to the forecasting results, and the results are compared with gated recurrent unit (GRU) and long short-term memory (LSTM) machine-learning models and the key laboratory of MArine Science and NUmerical Modeling (MASNUM) numerical wave model. The results show that the machine-learning models outperform the MASNUM within 72 h, with the transformer being the best model. For continuous 12 h, 24 h, 36 h, 48 h, 72 h, and 96 h forecasting, the average mean absolute errors (MAEs) of the test sets were, respectively, 0.139 m, 0.186 m, 0.223 m, 0.254 m, 0.302 m, and 0.329 m, and the wave scale classification accuracies were, respectively, 91.1%, 99.4%, 86%, 83.3%, 78.9%, and 77.5%. The experimental results validate that the transformer model can achieve continuous and accurate SWH forecasting, as well as accurate wave scale classification and early warning of waves, providing technical support for wave monitoring.

In recent years, wave energy has gained attention for its sustainability and cleanliness. As one of the most important parameters of wave energy, significant wave height (SWH) is difficult to accurately predict due to complex ocean conditions and the ubiquitous chaotic phenomena in nature. Therefore, this paper proposes an integrated CEEMDAN-LSTM joint model. Traditional computational fluid dynamics (CFD) has a long calculation period and high capital consumption, but artificial intelligence methods have the advantage of high accuracy and fast convergence. CEEMDAN is a commonly used method for digital signal processing in mechanical engineering, but has not yet been used for SWH prediction. It has better performance than the EMD and EEMD and is more suitable for LSTM prediction. In addition, this paper also proposes a novel filter formulation for SWH outliers based on the improved violin-box plot. The final empirical results show that CEEMDAN-LSTM significantly outperforms LSTM for each forecast duration, significantly improving the prediction accuracy. In particular, for a forecast duration of 1 h, CEEMDAN-LSTM has the most significant improvement over LSTM, with 71.91% of RMSE, 68.46% of MAE and 6.80% of NSE, respectively. In summary, our model can improve the real-time scheduling capability for marine engineering maintenance and operations.

Significant Wave Height (SWH) is a crucial parameter in ocean wave dynamics, impacting coastal safety, maritime transportation, and meteorological research. Building upon the TimesNet neural network, a recent advancement in the realm of time series prediction in deep learning, this study proposes an integrated approach combining Empirical Mode Decomposition (EMD) with TimesNet, introducing the EMD-TimesNet model for SWH forecasting. The TimesNet model’s multidimensional spatial mapping guarantees effective historical information extraction, while the EMD approach makes it easier to decompose subsequence characteristics inside the original SWH data. The predicted Root Mean Square Error (RMSE) and Correlation Coefficient (CC) values of the EMD-TimesNet model are 0.0494 m and 0.9936; 0.0982 m and 0.9747; and 0.1573 m and 0.9352 at 1 h, 3 h, and 6 h, respectively. The results indicate that the EMD-TimesNet model outperforms existing models, including the TimesNet, Autoformer, Transformer, and CNN-BiLSTM-Attention models, both in terms of overall evaluation metrics and prediction performance for diverse sea states. This integrated model represents a promising advancement in enhancing the accuracy of SWH predictions.

As a renewable and clean energy source with abundant reserves, the development of wave energy relies on accurate predictions of significant wave height (Hs). The fluctuation of Hs is a non-stationary process influenced by seasonal variations in marine climate conditions, which poses significant challenges for accurate predictions. This study proposes a deep learning method based on buoy datasets collected from four research locations in China’s offshore waters over three years (2021–2023, 3-hourly). The hybrid modal decomposition CEEMDAN-VMD is employed for reducing non-stationarity of the Hs sequence, with peak information incorporated as a data augmentation strategy to enhance the performance of deep learning. A probabilistic deep learning model, QRCNN-BiLSTM, was developed using quantile regression, achieving 12-, 24-, and 36-h interval predictions of Hs based on 12 days of historical data with three input features (Hs and wave velocities only). Furthermore, an optimization algorithm that integrates the proposed innovative enhancement strategies is used to automatically adjust the network parameters, making the model more lightweight. Results demonstrate that under a 0.95 prediction interval nominal confidence (PINC), the prediction interval coverage probability (PICP) reaches 100% for at least 6 days across all datasets, indicating that the developed system exhibits superior performance in short-term wave forecasting.