Wave Forecasting Research Articles

Evaluation of observation impact on the meteorological forecasts associated with heat wave in 2018 over East Asia using observing system experiments

Heat waves are meteorological disasters that inflict damage on public health and societal systems over extensive areas. The frequency and intensity of heat waves are increasing in many regions worldwide. However, insufficient research has been conducted to reduce forecast errors for heat waves in terms of short-range predictions. In this study, observing system experiments were performed using the Weather Research and Forecasting model and a three-dimensional variational data assimilation (DA), and the effects of observations used for DA on forecast errors for meteorological variables (i.e., upper atmospheric geopotential height, upper temperature, upper wind, and near-surface 2-m temperature) associated with heat wave were analyzed. As the forecast time increased, the 200 and 500 hPa geopotential heights in East Asia and the 2-m temperatures around Korea, Japan, and eastern China tended to be underestimated. All observations used for DA reduced the forecast errors for the meteorological variables associated with heat wave. Upper atmospheric observations (i.e., Advanced Microwave Sounding Unit-A (AMSU-A), aircraft, atmospheric motion vector, and radiosonde) played a more significant role in reducing forecast errors than near-surface observations. Among the upper atmospheric observations, AMSU-A had the greatest impact on reducing underestimation in forecasts for 200 and 500 hPa geopotential heights and the second greatest impact on 2-m temperature. The contraction of Tibetan high area at 200 hPa and Northern Pacific high area at 500 hPa in the experiments without using specific observations, compared to the analysis from the experiment using all observations, caused the deflection of the upper winds clockwise through the geostrophic relationship. Radiosonde observations had the greatest impact on reducing forecast errors of 2-m temperatures. Therefore, upper atmospheric observations are important for reducing errors in heat wave simulations in East Asia. The results of this study could help in designing an optimal observing system that reduces heat wave forecast errors in East Asia.

A deep-learning real-time bias correction method for significant wave height forecasts in the Western North Pacific

Significant wave height (SWH) is one of the most important parameters characterizing ocean waves, and accurate numerical ocean wave forecasting is crucial for coastal protection and shipping. However, due to the randomness and nonlinearity of the wind fields that generate ocean waves and the complex interaction between wave and wind fields, current forecasts of numerical ocean waves have biases. In this study, a spatiotemporal deep-learning method was employed to correct gridded SWH forecasts from the European Centre for Medium-Range Weather Forecasting System Integrated Forecast System Global Model (ECMWF-IFS). This method was built on the trajectory gated recurrent unit deep neural network, and it conducts real-time rolling correction for the 0–240-h SWH forecasts from ECMWF-IFS. The correction model is co-driven by wave and wind fields, providing better results than those based on wave fields alone. A novel pixel-switch loss function was developed. The pixel-switch loss function can dynamically fine-tune the pre-trained correction model, focusing on pixels with large biases in SWH forecasts. According to the seasonal characteristics of SWH, four correction models were constructed separately, for spring, summer, autumn, and winter. The experimental results show that, compared with the original ECMWF SWH predictions, the correction was most effective in spring, when the mean absolute error decreased by 12.972–46.237%. Although winter had the worst performance, the mean absolute error decreased by 13.794–38.953%. The corrected results improved the original ECMWF SWH forecasts under both normal and extreme weather conditions, indicating that our SWH correction model is robust and generalizable.

Wind field and model resolution optimization and testing source terms for the prediction of cyclone induced waves in the Bay of Bengal

The present study examines the impact of wind data resolution on wave climate prediction using the wind-wave model, WAM using different spatial resolutions of wind data such as 1/5°, 1/10°, 1/20°, and 1/40°, obtained from the Weather Research and Forecasting (WRF) model. It focuses on the prediction of extreme waves caused by three cyclones (Phailin, Hudhud, and Vardah) that hit the Bay of Bengal region of the North Indian Ocean in 2013, 2014, and 2016, respectively. These cyclones had a significant impact on the east coast of India and have generated significant wave height (Hs) of more than 10 m. To accurately predict these high-impact waves, it is necessary to have suitable wind resolution and a stable wave model grid resolution. We also investigate the effect of different spatial resolutions (1/5°, 1/10°, 1/20°, and 1/40°) on wave prediction. There is no significant difference in Hs prediction accuracy for wind data and wave model resolutions better than 1/10°. Additionally, the WAM model is tested with Ardhuin's input and dissipation source terms included in the model which doubles the source terms computational time required by the model although providing better predictions in the nearshore locations. An optimal model resolution of 1/10°, along with Ardhuin's source terms, is recommended for better wave prediction.

Machine-guided discovery of a real-world rogue wave model.

Big data and large-scale machine learning have had a profound impact on science and engineering, particularly in fields focused on forecasting and prediction. Yet, it is still not clear how we can use the superior pattern-matching abilities of machine learning models for scientific discovery. This is because the goals of machine learning and science are generally not aligned. In addition to being accurate, scientific theories must also be causally consistent with the underlying physical process and allow for human analysis, reasoning, and manipulation to advance the field. In this paper, we present a case study on discovering a symbolic model for oceanic rogue waves from data using causal analysis, deep learning, parsimony-guided model selection, and symbolic regression. We train an artificial neural network on causal features from an extensive dataset of observations from wave buoys, while selecting for predictive performance and causal invariance. We apply symbolic regression to distill this black-box model into a mathematical equation that retains the neural network's predictive capabilities, while allowing for interpretation in the context of existing wave theory. The resulting model reproduces known behavior, generates well-calibrated probabilities, and achieves better predictive scores on unseen data than current theory. This showcases how machine learning can facilitate inductive scientific discovery and paves the way for more accurate rogue wave forecasting.

Long-term assessment of wave conditions and wave energy resource in the Arctic Ocean

It was recently shown that the Arctic has been warming much faster than the rest of the globe during the last decades. This warming has reduced the ice extent significantly, which will strongly impact the wave climate in the Arctic regions, thus affecting the design of marine structures, operations, and energy resources. This study focuses on the higher latitudes, and uses the advanced wave hindcast NORA3, which covers a big part of the North Atlantic and the whole Arctic Ocean, to analyze the spatio–temporal properties of wave height and wave energy flux during the last three decades. The most energetic waves in the Arctic Ocean are observed in the Greenland Sea and the Barents Sea. The study shows that the substantial diminishing of sea ice in the Arctic induces local and regional changes in both mean and extreme wave conditions. In the Arctic Ocean the changes in extreme wave height are more pronounced compared to changes in mean wave conditions. The results also indicate a strong positive trend in the extreme wave heights in the Arctic regions of the Barents Sea, the Kara Sea, the Laptev Sea, the East Siberian Sea, the Chukchi Sea, and the Beaufort Sea.

Short-term prediction of the significant wave height and average wave period based on the variational mode decomposition–temporal convolutional network–long short-term memory (VMD–TCN–LSTM) algorithm

Abstract. The present work proposes a prediction model of significant wave height (SWH) and average wave period (APD) based on variational mode decomposition (VMD), temporal convolutional networks (TCNs), and long short-term memory (LSTM) networks. The wave sequence features were obtained using VMD technology based on the wave data from the National Data Buoy Center. Then the SWH and APD prediction models were established using TCNs, LSTM, and Bayesian hyperparameter optimization. The VMD–TCN–LSTM model was compared with the VMD–LSTM (without TCN cells) and LSTM (without VMD and TCN cells) models. The VMD–TCN–LSTM model has significant superiority and shows robustness and generality in different buoy prediction experiments. In the 3 h wave forecasts, VMD primarily improved the model performance, while the TCN had less of an influence. In the 12, 24, and 48 h wave forecasts, both VMD and TCNs improved the model performance. The contribution of the TCN to the improvement of the prediction result determination coefficient gradually increased as the forecasting length increased. In the 48 h SWH forecasts, the VMD and TCN improved the determination coefficient by 132.5 % and 36.8 %, respectively. In the 48 h APD forecasts, the VMD and TCN improved the determination coefficient by 119.7 % and 40.9 %, respectively.

Design and evaluation of an efficient high-precision ocean surface wave model with a multiscale grid system (MSG_Wav1.0)

Abstract. Ocean surface waves induced by wind forcing and topographic effects are a crucial physical process at the air–sea interface, which significantly affect typhoon development, ocean mixing, etc. Higher-resolution wave modeling can simulate more accurate wave states but requires a huge number of computational resources, making it difficult for Earth system models to include ocean waves as a fast-response physical process. Given that high-resolution Earth system models are in demand, efficient high-precision wave simulation is necessary and urgent. Based on the wave dispersion relation, we design a new wave modeling framework using a multiscale grid system. It has the fewest number of fine grids and reasonable grid spacing in deep-water areas. We compare the performance of wave simulation using different spatial propagation schemes, reveal the different reasons for wave simulation differences in the westerly zone and the active tropical cyclone region, and quantify the matching of spatial resolutions between wave models and wind forcing. A series of numerical experiments show that this new modeling framework can more precisely simulate wave states in shallow-water areas without losing accuracy in the deep ocean while costing a fraction of the price of traditional simulations with uniform fine-gridding space. With affordable computational expenses, the new ocean surface wave modeling can be implemented into high-resolution Earth system models, which may significantly improve the simulation of the atmospheric planetary boundary layer and upper-ocean mixing.

WAVEx: Stabilized finite elements for spectral wind wave models using FEniCSx

The prediction of the wind wave spectrum of the ocean using numerical models are an important tool for researchers, engineers, and communities living in coastal areas. The governing equation of the wind wave models, the Wave Action Balance Equation, presents unique challenges for implementing reliable numerical models because it is highly advective, highly nonlinear and high dimensional. Historically, most operational models have utilized finite difference methods, others have used finite volume methods but relatively few attempts at using finite element methods. In this work, we seek to fill this gap by investigating several different finite element discretizations of the Wave Action Balance Equation. The methods, which include streamline upwind Petrov–Galerkin (SUPG), least squares, and discontinuous Galerkin, are implemented and convergence properties are examined for some simplified 2-D test cases. Then, a new spectral wind wave model, WAVEx, is formulated and implemented for the full problem setting. WAVEx uses continuous finite elements along with SUPG stabilization in geographic/spectral space that allows for fully unstructured triangular meshes in both geographic and spectral space. For propagation in time, a second order fully implicit finite difference method is used. When source terms are active, a second order operator splitting scheme is used to linearize the problem. In the splitting scheme, propagation is solved using the implicit method and the nonlinear source terms are treated explicitly. Several test cases, including analytic tests and laboratory experiments, are demonstrated and results are compared to analytic solutions, observations, as well as output from another model that is used operationally.

A novel framework for wave power plant site selection and wave forecasting based on GIS, MCDM, and ANN methods: A case study in Hainan Island, Southern China

Wave power plants (WPPs) hold significant promise for sustainable energy generation but face complex challenges in site selection and wave forecasting. To address these challenges, this study presents an integrated methodology that combines geographic information system (GIS), multi-criteria decision making (MCDM) and artificial neural network (ANN) techniques. The primary objective of this research is to identify optimal sites for WPP deployment and enhance the accuracy of wave power density (WPD) forecasting. The study focuses on Hainan Island, the second-largest island in China, and employs both macro-scale and micro-scale site selection methods. It establishes a comprehensive criteria system that encompasses environmental, technical, economic, and social aspects. To improve the objectivity of criteria weighting, a group decision making-analytic hierarchy process (GDM-AHP) approach is applied. The findings reveal that approximately 1.36 % (1427.93 km2) of Hainan Island's area offers suitable conditions for WPP deployment, with concentrations in the southern, northern, and eastern marine regions. Among the 27 identified alternative sites covering 208.76 km2 along the eastern coast, six optimal sites are pinpointed in Wanning, Wenchang, and Qionghai. Furthermore, the optimized ANN outperforms the standard ANN, achieving a mean relative error of 9.0 %. This research contributes to the theoretical understanding of WPP site selection and wave forecasting while offering a practical and adaptable framework for stakeholders involved in renewable energy projects, particularly in coastal areas such as Hainan Island. These results and methodologies have real-world implications for the efficient and effective deployment of wave energy projects, ultimately promoting sustainable energy generation and socioeconomic development.

Forecast of the Dynamics of a Sandy Beach in Complexed Hydrodynamic Conditions

Changes in the coastal zone under the influence of currents of different nature and wind waves are being investigated. A sandy beach located in the water area of the “Park of the 300th Anniversary of St. Petersburg”, the Neva Bay of the Gulf of Finland of the Baltic Sea, is considered as an object. The beach is actively affected by wind waves and eventually washes away with the intensity of the retreat of the shore of about 4 m per year. For numerical modeling, a set of models is used: SWAN–wind-wave model and COASTOX-UN–a two-dimensional model of currents, sediment transport and bottom reformation. It was developed a model of the Neva Bay and the mouth of the Neva River from the Flood Prevention Facility Complex in the west to the river Neva near the Liteiny Bridge in the east. Based on the reanalysis of wind data, 36 strong storms were selected for a five-year period from 2014 to 2018, for the sequence of which numerical modeling of waves, currents and lithodynamic processes was carried out. It was obtained balances of alluvial and washouts after a ten-years simulated period for beach sectors. To verify the results, satellite images of the modeling area are used, it was found that the model adequately describes the main observed trends in the development of the beach.

A Probabilistic Prediction of Rogue Waves from a WAVEWATCH III Model for the Northeast Pacific

Abstract Rogue waves are stochastic, individual ocean surface waves that are disproportionately large compared to the background sea state. They present considerable risk to mariners and offshore structures especially when encountered in large seas. Current rogue wave forecasts are based on nonlinear processes quantified by the Benjamin Feir index (BFI). However, there is increasing evidence that the BFI has limited predictive power in the real ocean and that rogue waves are largely generated by bandwidth-controlled linear superposition. Recent studies have shown that the bandwidth parameter crest–trough correlation r shows the highest univariate correlation with rogue wave probability. We corroborate this result and demonstrate that r has the highest predictive power for rogue wave probability from the analysis of open ocean and coastal buoys in the northeast Pacific. This work further demonstrates that crest–trough correlation can be forecast by a regional WAVEWATCH III wave model with moderate accuracy. This result leads to the proposal of a novel empirical rogue wave risk assessment probability forecast based on r. Semilogarithmic fits between r and rogue wave probability were applied to generate the rogue wave probability forecast. A sample rogue wave probability forecast is presented for a large storm 21–22 October 2021. Significance Statement Rogue waves pose a considerable threat to ships and offshore structures. The rare and unexpected nature of rogue wave makes predicting them an ongoing and challenging goal. Recent work based on an extensive dataset of waves has suggested that the wave parameter called the crest–trough correlation shows the highest correlation with rogue wave probability. Our work demonstrates that crest–trough correlation can be reasonably well forecast by standard wave models. This suggests that current operational wave models can support rogue wave prediction models based on crest–trough correlation for improved rogue wave risk evaluation.

A deep learning super-resolution model to speed up computations of coastal sea states

In this paper, the potential of a super-resolution technique is presented in the context of coastal wave forecasting. The method uses a neural network to predict a high-resolution spatial estimation of spectral wave parameters from a lower resolution numerical computation. In this particular example, one year of training data is sufficient to achieve satisfying accuracy for practical applications. The error of this method in reproducing the results of a high-resolution spectral model is an order of magnitude lower than the usual accuracy of spectral models. Simultaneously, it reduces the computation time by a factor of up to 50. Moreover, utilizing complementary training data of extreme events allows for a further improvement in accuracy. The study also shows that super-resolution is more accurate, albeit slower, than surrogate models, thus providing a trade-off solution between accuracy and speed. Overall, incorporation of the present approach into wave forecasting systems has the potential to rapidly generate “zoomed-in” areas of interest or to speed up ensemble forecasts without supplementary calculations at higher resolution.

The applicability of ALARO and AROME wind-fields in multi-scale waves forecasting in open sea and coastal areas of the southern Baltic Sea

The main objective of the study was to implement the wave model in two independent systems fed respectively by wind fields with a 4 km resolution in the Baltic-wide area and a 2 km resolution in the shallow coastal regions of the southern Baltic for operational work. The study included the selection the best parameterization, which was carried out using measured data and model data from the verified SWAN-COSMO system. The chosen best parameterization of the model, including the time step, iteration, wind scaling, dispersion coefficients and swell formula, among others, allowed the identification of the optimal system that guarantees the most reliable predictions. The most reliable forecasts reproducing real conditions, both for the model powered by wind fields with a resolution of 4 km and 2 km, were obtained for the configuration characterized by the parameters: 30-min time step, 3 iterations, a wind scaling factor of 32 using DEBIAS equal to 0.89, coefficients related to local dissipation and cumulative of 2.8 × 10–6 and 3.5 × 10–5, respectively, and Ardhiun's swell formula of 1.20. The values of the correlation coefficient with both the measured data and the results of the comparative model for significant wave height and wave period, respectively, were no lower than: 0.95 and 0.73 (Petrobaltic) and 0.96 and 0.90 (Pomeranian Bay). Root mean square error (RMSE) values were <0.23 m and <0.20 s (Petrobaltic) and <0.20 m and <0.74 s (Pomeranian Bay) for significant wave height and mean wave period, respectively. Analysis of the forecast results showed some limitations in using the mesoscale model in coastal areas, and the solution was to use the high-resolution model in this zone. It was shown that the stand-alone high-resolution model (domain: southern Baltic Sea) obtained similar results to the same model system but nested in the mesoscale model (domain: Baltic Sea). In addition, this model showed shorter simulation computation time and represents an independent, less vulnerable to discontinuity in forecast generation (lack of assimilation of boundary and initial conditions from a lower resolution model). A noticeable improvement in the quality of forecasts was shown by the AROME wind-field-powered model, which, due to its high resolution of the computational grid and wind data, maps well the wave dynamics in areas with limited wave exposure (the Vistula Lagoon, the Puck Lagoon) or complex coastline (the Hel Split) and seabed (the shallows of the Pomeranian Gulf and the Słupsk Shoal. The coupled data from the ALARO and AROME models, processed internally at IMWM-NRI, provide continuity and independence from global models and indicate applicability in generating wave forecasts by other Baltic countries.

Wave–Tide Interaction by Typhoon Ampil on Wave and Storm Surge in the Changjiang River Estuary and Its Adjacent Coastal Areas

The study used the SCHISM ocean model combined with the WWM III wind wave model to quantify the interaction between wind waves and tides in the coastal zone of the Changjiang River Estuary and its adjacent areas. The wave and storm surge during Typhoon Ampil, which made landfall in July 2018 in Shanghai, were simulated by using the Climate Forecast System Version 2 (CFSv2) and Medium-Range Weather Forecasts (ECMWF) latest reanalysis (ERA5) wind dataset from 1 July to 31 July. Model results with CFSv2 forcing show better performance in terms of significant wave height and storm surge than those with ERA5 forcing. To investigate the interactions between waves, water levels, currents, and their combined effects on significant wave and surge variations, six numerical sensitivity experiments were designed according to the different coupling methods between SCHISM and WWMIII. The research shows that in coastal areas with water depths of less than 10 m, waves are affected by water levels and currents. The differences in the effect on significant wave height between wave-tide coupling and one-way coupling with water levels and currents are negligible. Wave setup is an important physical term which cannot be ignored during the variations of storm surge caused by Typhoon Ampil. The contributions of wave set up were concentrated in coastal areas with water depths less than 10 m. The peak wave setup occurred in the Changjiang River Estuary, reaching 0.15 m. In Xiangshan Bay and Sanmen Bay, wave radiation stress makes the proportion of wave setup to the total surge reached more than 30%. The consideration of wave-tide interaction can effectively improve the accuracy of numerical wave and storm surge simulations, which can provide more accurate hindcasts of wave and storm surge variations in the Changjiang River Estuary and its adjacent coastal areas.

Wave hindcast under tropical cyclone conditions in the South China Sea: sensitivity to wind fields

Wave hindcast under tropical cyclone conditions in the South China Sea: sensitivity to wind fields

Cross-sectional Ct distributions from qPCR tests can provide an early warning signal for the spread of COVID-19 in communities.

SARS-CoV-2 PCR testing data has been widely used for COVID-19 surveillance. Existing COVID-19 forecasting models mainly rely on case counts obtained from qPCR results, even though the binary PCR results provide a limited picture of the pandemic trajectory. Most forecasting models have failed to accurately predict the COVID-19 waves before they occur. Recently a model utilizing cross-sectional population cycle threshold (Ct-the number of cycles required for the fluorescent signal to cross the background threshold) values obtained from PCR tests (Ct-based model) was developed to overcome the limitations of using only binary PCR results. In this study, we aimed to improve on COVID-19 forecasting models using features derived from the Ct-based model, to detect epidemic waves earlier than case-based trajectories. PCR data was collected weekly at Northeastern University (NU) between August 2020 and January 2022. Campus and county epidemic trajectories were generated from case counts. A novel forecasting approach was developed by enhancing a recent deep learning model with Ct-based features and applied in Suffolk County and NU campus. For this, cross-sectional Ct values from PCR data were used to generate Ct-based epidemic trajectories, including effective reproductive rate (Rt) and incidence. The improvement in forecasting performance was compared using absolute errors and residual squared errors with respect to actual observed cases at the 7-day and 14-day forecasting horizons. The model was also tested prospectively over the period January 2022 to April 2022. Rt curves estimated from the Ct-based model indicated epidemic waves 12 to 14 days earlier than Rt curves from NU campus and Suffolk County cases, with a correlation of 0.57. Enhancing the forecasting models with Ct-based information significantly decreased absolute error (decrease of 49.4 and 221.5 for the 7 and 14-day forecasting horizons) and residual squared error (40.6 and 217.1 for the 7 and 14-day forecasting horizons) compared to the original model without Ct features. Ct-based epidemic trajectories can herald an earlier signal for impending epidemic waves in the community and forecast transmission peaks. Moreover, COVID-19 forecasting models can be enhanced using these Ct features to improve their forecasting accuracy. In this study, we make the case that public health agencies should publish Ct values along with the binary positive/negative PCR results. Early and accurate forecasting of epidemic waves can inform public health policies and countermeasures which can mitigate spread.

On global wave height climatology and trends from multiplatform altimeter measurements and wave hindcast

Reliable estimates of ocean surface waves and their long-term global trends are fundamentally important for numerous ocean engineering and geophysical applications. Nonetheless, it is scientifically and technically demanding to accurately identify such relatively small trends [O(0.1−1) cm yr−1] from wave data currently available. In 2022, Young and Ribal demonstrated that by changing the calibration method, multiplatform altimeter observations yield noticeable differences in wave height estimates and their trends. In this paper, we use our global wave hindcast as a baseline and confirm that observations calibrated relative to one another (i.e., “altimeter-altimeter” calibration) ultimately outperform traditionally “altimeter-buoy” calibrated data. The former leads to more consistent mean and extreme wave heights across simultaneously operating altimeters and consequently to a more homogeneous evolution of global sea states over the past several decades. The underlying reason is hypothesized to be that temporal inhomogeneities in long-term NDBC buoy records due to changes in buoy hardware and software over time introduce comparable inhomogeneities to long-term altimeter observations when the “altimeter-buoy” calibration is adopted. It is encouraging to observe that the global trends of mean and 90th-percentile wave heights over the period 1992-2019 from our hindcast and re-calibrated altimeter data are very close: approximately 0.3 cm yr−1. Nonetheless, the altimeter-based trend of 99th-percentile wave height, Hs99, is substantially-but-spuriously stronger mainly due to markedly growing availability of altimeter missions over time. Our work clearly demonstrates the power of third generation spectral wave models as diagnostics tools. Given the uncertainties embedded in buoy and satellite observations, wave modeling and global wave hindcasts can indeed guide these measurements. Further analysis of the underlying climate physics driving the interannual variability of ocean waves in wind-sea dominated regions is also presented.

Novel Ocean Wave Height and Energy Spectrum Forecasting Approaches: An Application of Semi-Analytical and Machine Learning Models

Accurate and reliable wave forecasting is crucial for optimizing the performance of various marine operations, such as offshore energy production, shipping, and fishing. Meanwhile, predicting wave height and wave energy is crucial for achieving sustainability as a renewable energy source, as it enables the harnessing of the power of wave energy efficiently based on the water-energy nexus. Advanced wave forecasting models, such as machine learning models and the semi-analytical approach, have been developed to provide more accurate predictions of ocean waves. In this study, the Sverdrup Munk Bretschneider (SMB) semi-analytical approach, Emotional Artificial Neural Network (EANN) approach, and Wavelet Artificial Neural Network (WANN) approach will be used to estimate ocean wave parameters in the Gulf of Mexico and Aleutian Basin. The accuracy and reliability of these approaches will be evaluated, and the spatial and temporal variability of the wave field will be investigated. The available wave characteristics are used to generate hourly, 12-hourly, and daily datasets. The WANN and SMB model shows good performance in the daily prediction of the significant wave height in both case studies. In the SMB model, specifically on a daily time scale, the Nash–Sutcliffe Efficiency (NSE) and the peak deviation coefficient (DCpeak) were determined to be 0.62 and 0.54 for the Aleutian buoy and 0.64 and 0.55 for the Gulf of Mexico buoy, respectively, for significant wave height. In the context of the WANN model and in the testing phase at the daily time scale, the NSE and DCpeak indices exhibit values of 0.85 and 0.61 for the Aleutian buoy and 0.72 and 0.61 for the Gulf of Mexico buoy, respectively, while the EANN model is a strong tool in hourly wave height prediction (Aleutian buoy (NSEEANN = 0.60 and DCpeakEANN = 0.88), Gulf of Mexico buoy (NSEEANN = 0.80 and DCpeakEANN = 0.82)). In addition, the findings pertaining to the energy spectrum density demonstrate that the EANN model exhibits superior performance in comparison to the WANN and SMB models, particularly with regard to accurately estimating the peak of the spectrum (Aleutian buoy (DCpeakEANN= 0.41), Gulf of Mexico buoy (DCpeakEANN = 0.59)).

Enhancing the accuracy of metocean hindcasts with machine learning models

To improve the quality of wind and wave forecasts post-processing algorithms are developed to bias-correct the variables of interest using machine learning models trained with buoy data. Two types of deep neural networks are developed and studied to improve the accuracy of ERA5 hourly data of 10-m wind speed (wsp) and significant wave height (swh) at two locations with distinct metocean conditions. The algorithms are the multilayer perceptron (MLP) and the long short-term memory (LSTM) neural networks. The latter is built based on a range of previous time steps included in the input, evaluating the optimal value. Several metrics such as bias, scatter index, root mean square error and correlation coefficient are used to evaluate model performances. After extensive examination and experimentation regarding feature selection, filtering windows, and model architecture, the results show better improvements for swh than wsp, and that LSTM outperforms MLP significantly. The original correlation coefficients between ERA5 and observations for swh have been improved and the ERA5 RMSE has been reduced with the LSTM post-processing model.

CMIP6 wave climate simulation in the European North East Atlantic Basin using WaveWatch III

Climate change is expected to have an impact on wind patterns, and therefore the generation of waves. Phase 6 of the Coupled Model Intercomparison Project (CMIP6), provides various realization of outputs integrated global coupled models for different centuries. Wind quality is a cornerstone for wave energy as it is the primary generation driver in any wave model. Therefore, proper quantification of wind wave interactions are key in the evaluation of future wave energy potential. In this study, a wave hindcast for the North-East Atlantic, using the WaveWatchIII model forced by CMIP6 winds is presented. The model uses a grid of 0.25° of spatial resolution, covering a longitude range of -21.0° to 10° (west to east) and a latitude range of 18° to 80° (south to north).The main objective of this work is to assess the quality of historical winds from all the CMIP6 wind data that are available under the first realization criteria (r1i1p1f1) at the time of this study. This leads to understanding limitations and proposing a selection method to choose the optimal wind dataset to force the wave model within the analyzed area.Thus, the optimal CMIP6 historical winds for the North-East Atlantic are used to create a 10 years hindcast(from 2003 to 2012). To further assess the suitability of the selected winds dataset for wave generation, results are compared with the ERA5 wave product. The available CMIP6 models show region-specific variations depending on the Regional Climate models used for their developments. The results show the impact of zonal and, meridional wind intensities, on wave characteristics in different regions over the domain.