Height Forecasts Research Articles

Wave height forecast method with uncertainty quantification based on Gaussian process regression

Wave height forecast method with uncertainty quantification based on Gaussian process regression

Application of a Two-Step Space–Time EOF Statistical Postprocessing Algorithm to Mitigate Subseasonal 200-hPa Geopotential Height Forecast Error

Abstract The time-extended empirical orthogonal function (EEOF) patterns of error developed in a companion paper are applied in this study for model data postprocessing. Projecting forecast anomalies from the model seasonal cycle from GEFSv12 outputs onto these EEOF patterns reconstructs the error principal components (PCs) in a manner that can be applied in real time. When these reconstructed error anomalies are compared with the original GEFSv12 200-hPa geopotential height (Z200) reforecast error anomalies, the projected and validation error signals tend to align temporally. When distributed globally, projection and validation error anomalies have statistically significant positive Pearson correlation coefficients with each other at most grid points outside of the tropics. Categorical Heidke skill score (HSS) analysis reaffirms that by lead day 16 of a forecast, the algorithm skillfully predicts systematic errors for locations outside of the tropics. Hemispheric winter demonstrates that the highest magnitude HSS values are in the high latitudes, illustrating the underlying seasonality of Z200 behavior and predictability. On average, wintertime HSS values hover around 20%, with high-latitude locations exceeding mean values of 40%. Comparatively, summertime values generally exceed 10% improvement outside of the tropics. High-latitude storm-track regions, such as the North Atlantic, North Pacific, and South Pacific, contain the most Z200 variance in the globe and the highest HSS values. This algorithm will be applied to real-time forecasts and additional variables in future work, with the end goal of implementation into the NOAA-CPC subseasonal forecasts.

Influence of CyGNSS L2 wind data on tropical cyclone analysis and forecasts in the coupled HAFS/HYCOM system

This study examines the influence of NASA Cyclone Global Navigation Satellite System (CyGNSS) Level 2-derived 10 m (near-surface) wind speed over the ocean on analyses and forecasts within the NOAA operational Hurricane Analysis and Forecast System (HAFS). HAFS is coupled with a regional configuration of the HYCOM ocean model. The primary advantages of data from the CyGNSS constellation of satellites include higher revisit frequency compared to polar-orbiting satellites, and the availability of reliable wind observations over the ocean surface during convective precipitation. CyGNSS data are available early in the life cycle of tropical cyclones (TCs) when aerial reconnaissance observations are not available. We focus on TCs whose forecasts were initialized when the TC was a depression or tropical storm. In the present study, we find first, that assimilation of CyGNSS near-surface winds improves storm track, intensity, and structure statistics in the analysis and early in the forecast, for many cases. Second, we find that assimilation of CyGNSS observations provides additional insights into the evolution of air-sea interaction in intensifying TCs: In effect, the ocean responds in the coupled model to modifications in the initial 10 m wind field, thereby impacting forecasts of intensity, storm structure, and sea surface height, as demonstrated by two case studies. We also discuss some forecasts where assimilating CYGNSS appears to degrade performance for either intensity or structure.

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.

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.

КОМПЛЕКСНАЯ СИСТЕМА ПРОГНОЗИРОВАНИЯ ПАРАМЕТРОВ ВЕТРОВОГО ВОЛНЕНИЯ В МИРОВОМ ОКЕАНЕ И МОРЯХ РОССИИ

The paper describes a system for wind wave forecasting in the World Ocean, which has resulted from the development of the operational forecast technology functioning at the Hydrometcenter of Russia since 2014. The system is built on the linked “ocean-sea-coastal zone” scheme designed for making forecasts over the entire World Ocean and individual Russian seas. The developed model configurations make it possible to compute wave parameters with a horizontal resolution of 10-20 km in oceans and 1-5 km in Russian seas. To detail the forecasts in the coastal zone of the seas, unstructured triangulation grids with a horizontal resolution of 100-1000 m are used in relatively small water areas. The boundary conditions at the open boundaries of the coastal computational domain, which are necessary for calculations, are generated in the model of a corresponding sea. The verification results of the forecasts of the significant wave height over the World Ocean based on satellite altimetry observations show the values of traditional forecast skill scores comparable to those of leading forecast centers.

Early childhood height is a determinant of young adult stature in rural Nepal

BackgroundDoes preschool height predict adult stature in undernourished settings? The extent to which preschool length or height forecasts young adult stature is unclear in chronically undernourished populations.MethodsIn 2006-8, we assessed height in a cohort of 2074 young adults, aged 16–23 years, in rural Nepal who, as preschoolers (≤ 4 year), were measured at baseline and again 16 months later during a vitamin A supplementation trial in 1989-91. We assessed by linear regression the ability of preschool length (L, measured < 24 mo) or height (Ht, 24–59 mo), at each year of age to predict 16–23 year old height, adjusted for month of young adult age, interval duration (in months), caste, preschool weight-for-height z-score and, in young women, time since menarche, marriage status and pregnancy history.ResultsYoung women were a mean of 0.81, 1.11, 0.82, 0.24, 0.44 cm taller (all p < 0.01) and young men, 0.84, 1.18, 0.74, 0.64 and 0.48 cm taller (all p < 0.001) per cm of attained L/Ht at each successive preschool year of age and, overall, were 2.04 and 2.40 cm taller for each unit increase in preschool L/Ht z-score (L/HAZ) (both p < 0.001). Coefficients were generally larger for 16-month follow-up measurements. The percent of young adult height attained by children with normal L/HAZ (>-1) increased from 38–40% mid-infancy to ∼ 69–74% by 6 years of age. By 3–6 years of age heights of stunted children (L/HAZ<-2) were consistently ∼ 4–7% lower in their young adult height versus normal statured children. There was no effect of preschool vitamin A receipt.ConclusionsShorter young children become shorter adults but predictive effects can vary by sex, age assessed, and may be influenced by year or season of measurement.

A parallel machine learning-based approach for tsunami waves forecasting using regression trees

Following a seismic event, tsunami early warning systems (TEWSs) try to provide precise forecasts of the maximum height of incoming waves at designated target points along the coast. This information is crucial to trigger early warnings in areas where the impact of tsunami waves is predicted to be dangerous (or potentially cause destruction), to help the management of the potential impact of a tsunami as well as reduce environmental destruction and losses of human lives. For such a reason, it is crucial that TEWSs produce predictions with short computation time while maintaining a high prediction accuracy. This paper presents a parallel machine learning approach, based on regression trees, to discover tsunami predictive models from simulation data. In order to achieve the results in a short time, the proposed approach relies on the parallelization of the most time consuming tasks and on incremental learning executions, in order to achieve higher performances in terms of execution time, efficiency and scalability. The experimental evaluation, performed on two real tsunami cases occurred in the Western and Eastern Mediterranean basin in 2003 and 2017, shows reasonable advantages in terms of scalability and execution time, which is an important benefit in a urgent-computing scenarios.

Why Do DJF 2023/24 Upper‐Level 200‐hPa Geopotential Height Forecasts Look Different From the Expected El Niño Response?

AbstractWe investigate why the North American Multi‐Model Ensemble (NMME) upper‐level height forecast for December–February (DJF) 2023/24 differs from the expected El Niño response. These atypical height anomalies emerged despite the fact a strong El Niño was forecast. The analysis focuses on diagnosing the NMME forecasts of DJF 2023/24 for SSTs and 200‐hPa heights initialized at the beginning of November 2023 relative to other ensemble mean NMME DJF forecasts dating back to 1982. The results demonstrate that forecasts of the 200‐hPa height anomalies had a large contribution from warming trends in global SSTs. It is the combination of trends and the expected El Niño teleconnection that results in the forecast height anomalies. Increasingly, for forecasts of geopotential height anomalies during the recent El Niño winters, the amplitude of trends is nearly equal to the signal from El Niño and has implications for the climatological base period selection for seasonal forecasts.

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.

Single-instant spatial wave height forecast using machine learning: An image-to-image translation approach based on generative adversarial networks

An innovative single-instant approach for spatial significant wave height forecast based on a Generative Adversarial Networks (GANs) model is presented. The model's most distinctive feature is its ability to provide spatial wave height forecast with only a single snapshot of wind field input, eliminating the need for continuous wind field sequences while simultaneously maintaining high accuracy and enhanced efficiency. The proposed model architecture comprises an image-to-image translation generator and a patch-style discriminator, working in tandem to forecast high-quality wave height data. The model is trained using a 20-year ECMWF Reanalysis v5 (ERA5) wind and wave dataset. A vast sea area covering 15°-40°N, 105°-130°E in West Pacific is used for this study. The presented model is carefully tested against a 10-year period historical dataset and the results are discussed. The model exhibits outstanding overall performances with Mean Absolute Error (MAE) of 0.16 m, Root Mean Square Error (RMSE) of 0.24 m, and Mean Absolute Percentage Error (MAPE) of 13.4 %. The model proves particularly effective in forecasting extreme wave heights during tropical cyclones, capturing the structure of typhoon-driven waves and providing wave heights with favorable accuracy. It is also proficient at delivering satisfactory statistical wave height forecasts for long-term periods.

Model validation and applications of wave and current forecasts from the Hong Kong Observatory's Operational Marine Forecasting System

The Hong Kong Observatory has been running an Operational Marine Forecasting System (OMFS) adapted from the Regional Ocean Modelling System (ROMS) coupled with the WaveWatch III and SWAN wave models to provide wave, current and sea temperature forecasts up to 144 h twice a day since December 2021. To facilitate users’ interpretation of model forecasts of significant wave height and current speed in coastal predictions and open seas which are of particular significance in high wind situations, model forecasts were validated against moored buoy observations and wave recorder measurements near the shores of Hong Kong and drifting buoy data over the South China Sea, as well as Mercator Ocean model reanalysis in 2022. The validation results showed that the wave forecasts generally agreed well with the buoy observations with coefficient of determination (R2) of around 0.7 and root-mean-square error (RMSE) of less than 0.2 m up to 72 h ahead. The R2 for sea current forecasts ranged between 0.4 and 0.6, and the RMSE was around 8 to 11 cm/s in near shores up to T + 144 forecast hours. Validation against drifting buoy demonstrated that the trend of current forecasts generally agreed well with the measurements. RMSE of surface current forecasts over open seas ranged from 19 cm/s for 24-hour forecast to around 30 cm/s for 144-hour forecast when compared against Mercator Ocean reanalysis. Results from the current downscaling approach could serve as a benchmark reference for HKO to enhance OMFS in the future. In this paper, applications of model forecasts in the provision of marine weather services in Hong Kong are also introduced.

XWaveNet: Enabling uncertainty quantification in short-term ocean wave height forecasts and extreme event prediction

To aid accurate short-term forecast of wave heights and extreme events prediction from buoy data, a deep learning approach is proposed. Wave heights are forecasted up to 72 h in advance from multivariate meteorological and oceanographic data, followed by quantification of uncertainty in the forecasted values, and estimation of exceedance probabilities for extreme event conditions. Using Monte Carlo dropout technique, network regularization and forecast uncertainty assessment were performed. To forecast wave heights, a stacked long short-term memory (LSTM) model was trained on historical buoy data augmented with positionally encoded features. Per comparative evaluation of different models, across the 72 h forecast horizon, positionally encoded temporal attributes resulted in a mean prediction error and forecast uncertainty of only 3 % and 13.5 %, respectively. Contrarily, without temporal feature augmentation mean error was 5 % and uncertainty, 15 %. Therefore, the former model was ensembled with a Random Forest model for exceedance probability estimation. The hybrid model yielded a 21.4 % better separability between the extreme and normal observations in the test data from a nearby buoy in the northern Gulf of Mexico than individual models. All the four extreme events in the test set were correctly predicted with 97 % mean accuracy. Further evaluation of the deep ensemble model on 5 other spatially diverse buoy datasets from the Gulf of Mexico, Atlantic and Pacific coasts, suggested excellent generalizability for short-term wave forecasts and extreme event prediction, with an average maximum error of just 5.2 % across all the 6 buoy test datasets and the entire forecast horizon.

A transformer-based method for correcting significant wave height numerical forecasting errors

Accurate significant wave height (SWH) forecasting is essential for various marine activities. While traditional numerical and mathematical-statistical methods have made progress, there is still room for improvement. This study introduces a novel transformer-based approach called the 2D-Geoformer to enhance SWH forecasting accuracy. The 2D-Geoformer combines the spatial distribution capturing capabilities of SWH numerical models with the ability of mathematical-statistical methods to identify intrinsic relationships among datasets. Using a comprehensive long time series of SWH numerical hindcast datasets as the numerical forecasting database and ERA5 reanalysis SWH datasets as the observational proxies database, with a focus on a 72-hour forecasting window, the 2D-Geoformer is designed. By training the potential connections between SWH numerical forecasting fields and forecasting errors, we can retrieve SWH forecasting errors for each numerical forecasting case. The corrected forecasting results can be obtained by subtracting the retrieved SWH forecasting errors from the original numerical forecasting fields. During long-term validation periods, this method consistently and effectively corrects numerical forecasting errors for almost every case, resulting in a significant reduction in root mean square error compared to the original numerical forecasting fields. Further analysis reveals that this method is particularly effective for numerical forecasting fields with higher errors compared to those with relatively smaller errors. This integrated approach represents a substantial advancement in SWH forecasting, with the potential to improve the accuracy of operational SWH forecasts. The 2D-Geoformer combines the strengths of numerical models and mathematical-statistical methods, enabling better capture of spatial distributions and intrinsic relationships in the data. The method's effectiveness in correcting numerical forecasting errors, particularly for cases with higher errors, highlights its potential for enhancing SWH forecasting accuracy in operational settings.

Wave Height Forecasting Over Ocean of Things Based on Machine Learning Techniques: An Application for Ocean Renewable Energy Generation

Wave Height Forecasting Over Ocean of Things Based on Machine Learning Techniques: An Application for Ocean Renewable Energy Generation

Significant Wave Height Forecasting Based on EMD-TimesNet Networks

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.

Early Detection of Extreme Storm Tide Events Using Multimodal Data Processing

Sea-level rise is a well-known consequence of climate change. Several studies have estimated the social and economic impact of the increase in extreme flooding. An efficient way to mitigate its consequences is the development of a flood alert and prediction system, based on high-resolution numerical models and robust sensing networks. However, current models use various simplifying assumptions that compromise accuracy to ensure solvability within a reasonable timeframe, hindering more regular and cost-effective forecasts for various locations along the shoreline. To address these issues, this work proposes a hybrid model for multimodal data processing that combines physics-based numerical simulations, data obtained from a network of sensors, and satellite images to provide refined wave and sea-surface height forecasts, with real results obtained in a critical location within the Port of Santos (the largest port in Latin America). Our approach exhibits faster convergence than data-driven models while achieving more accurate predictions. Moreover, the model handles irregularly sampled time series and missing data without the need for complex preprocessing mechanisms or data imputation while keeping low computational costs through a combination of time encoding, recurrent and graph neural networks. Enabling raw sensor data to be easily combined with existing physics-based models opens up new possibilities for accurate extreme storm tide events forecast systems that enhance community safety and aid policymakers in their decision-making processes.

Multivariate GRU and LSTM models for wave forecasting and hindcasting in the southern Caspian Sea

Reliable wave forecasts and hindcasts are pivotal elements for a wide range of marine activities, coastal engineering applications, renewable energy and wave climate studies. This study explores capability of recurrent neural networks for wave hindcasting and multi-step wave forecasting in the southern Caspian Sea, a region with a limited observational data. Gated recurrent unit (GRU) and long short-term memory (LSTM) models are fed by buoy records for wave forecasting up to 6 h ahead and ERA5 reanalysis data as the model inputs for wave hindcasting. Special efforts are devoted to improve the accuracy of the models by including some additional features (e.g., wave age and swell) in the input layer. Different error measures are employed to evaluate performance of the models at two stations, Amirabad and Anzali. Using multivariate GRU and LSTM models, suitable wave forecasts and hindcasts are achieved for the locations. Although the model performance deteriorates with extending the forecasting time horizon, the forecasts of significant wave height (Hs) up to 6 h ahead are still satisfactory. The best hindcasting model yields a high linear correlation between hindcasted and measured Hs with R2 = 0.75 for Anzali and R2 = 0.83 for Amirabad. Finally, wave age and significant height of total swell (Hs-swell) can be considered as tentative input variables to improve efficiency of the models.

An integrated methodology for significant wave height forecasting based on multi‐strategy random weighted grey wolf optimizer with swarm intelligence

AbstractWhile wave energy is regarded as one of the prominent renewable energy resources to diversify global low‐carbon generation capacity, operational reliability is the main impediment to the wide deployment of the related technology. Current experience in wave energy systems demonstrates that operation and maintenance costs are dominant in their cost structure due to unplanned maintenance resulting in energy production loss. Accurate and high performance simulation forecasting tools are required to improve the efficiency and safety of wave converters. This paper proposes a new methodology for significant wave height forecasting. It is based on incorporating swarm decomposition (SWD) and multi‐strategy random weighted grey wolf optimizer (MsRwGWO) into a multi‐layer perceptron (MLP) forecasting model. This approach takes advantage of the SWD approach to generate more stable, stationary, and regular patterns of the original signal, while the MsRwGWO optimizes the MLP model parameters efficiently. As such, forecasting accuracy has improved. Real wave datasets from three buoys in the North Atlantic Sea are used to test and validate the forecasting performance of the proposed model. Furthermore, the performance is evaluated through a comparison analysis against deep‐learning based state‐of‐the‐art forecasting models. The results show that the proposed approach significantly enhances the model's accuracy.

Impact of HY‐2B SMR radiance assimilation on CMA global medium‐range weather forecasts

AbstractThe Chinese second ocean dynamic environment satellite Haiyang‐2B (HY‐2B) was successfully launched on October 25, 2018, carrying a scanning microwave radiometer (SMR) to provide information about the ocean and atmosphere. For the first time, this study investigated the impact of radiance data from the HY‐2B SMR in the four‐dimensional variational (4DVar) data assimilation system of the Global Forecast System developed by the China Meteorology Administration (CMA‐GFS). Prior to the radiance assimilation, we evaluated the data quality and developed suitable quality control (QC) procedures for the HY‐2B SMR observations. In addition, the cloud liquid water path (CLWP) and ocean wind speed (OWS) were introduced as new bias correction (BC) predictors to remove the systematic bias originating from the forward operator in the CMA‐GFS 4DVar system. The assimilation effects of SMR observations were evaluated through one‐month cycling experiments. Verification with independent observations and reanalysis data has demonstrated that assimilating SMR clear‐sky radiance can greatly reduce the analysis errors for temperature and humidity, while indirectly improving the quality of wind analysis. Furthermore, significant improvements in geopotential height forecasts were found for days 1–5 in the lower troposphere of the tropical region.