Acquisition of the Significant Wave Height from CFOSAT SWIM Spectra through a Deep Neural Network and its Impact on Wave Model Assimilation

2021 ◽  
Author(s):  
J. K. Wang ◽  
L. Aouf ◽  
A. Dalphinet ◽  
B.X. Li ◽  
Y. Xu ◽  
...  
Keyword(s):  
Neural Network ◽  
Wave Height ◽  
Significant Wave Height ◽  
Deep Neural Network ◽  
Wave Model ◽  
Significant Wave

Effect of Uni- and Bi-Directional Coupling of Ocean-Met Interaction on Significant Wave Height and Local Wind

2017 ◽  
Author(s):  
Adil Rasheed ◽  
Jakob Kristoffer Süld ◽  
Mandar Tabib
Keyword(s):  
Wave Height ◽  
Significant Wave Height ◽  
Surface Wind ◽  
Wave Model ◽  
Ocean Surface ◽  
Observation Data ◽  
Local Wind ◽  
Near Surface ◽  
Significant Wave ◽  
Bidirectional Coupling

Accurate prediction of near surface wind and wave height are important for many offshore activities like fishing, boating, surfing, installation and maintenance of marine structures. The current work investigates the use of different methodologies to make accurate predictions of significant wave height and local wind. The methodology consists of coupling an atmospheric code HARMONIE and a wave model WAM. Two different kinds of coupling methodologies: unidirectional and bidirectional coupling are tested. While in Unidirectional coupling only the effects of atmosphere on ocean surface are taken into account, in bidirectional coupling the effects of ocean surface on the atmosphere are also accounted for. The predicted values of wave height and local wind at 10m above the ocean surface using both the methodologies are compared against observation data. The results show that during windy conditions, a bidirectional coupling methodology has better prediction capability.

The Reconstruction of Significant Wave Height Time Series by Using a Neural Network Approach

2004 ◽  
Vol 126 (3) ◽  
pp. 213-219 ◽  
Author(s):  
Felice Arena ◽  
Silvia Puca
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Wave Height ◽  
Significant Wave Height ◽  
Error Function ◽  
Neural Network Approach ◽  
Significant Wave ◽  
Time Periods ◽  
Weighted Error ◽  
Storm Model

A Multivariate Neural Network (MNN) algorithm is proposed for the reconstruction of significant wave height time series, without any increase of the error of the MNN output with the number of modelled data. The algorithm uses a weighted error function during the learning phase, to improve the modelling of the higher significant wave height. The ability of the MNN to reconstruct sea storms is tested by applying the equivalent triangular storm model. Finally an application to the NOAA buoys moored off California shows a good performance of the MNN algorithm, both during sea storms and calm time periods.

Uncertainty of Ocean Wave Hindcasts Due to Wind Modeling

1995 ◽  
Vol 117 (4) ◽  
pp. 294-297 ◽  
Author(s):  
J. C. Teixeira ◽  
M. P. Abreu ◽  
C. Guedes Soares
Keyword(s):  
Wind Speed ◽  
Relative Error ◽  
Wave Height ◽  
Significant Wave Height ◽  
Second Generation ◽  
Wave Model ◽  
Ocean Wave ◽  
Wind Fields ◽  
Significant Wave ◽  
Wind Input

Two wind models were developed and their results were compared with data gathered during the Wangara experiment, so as to characterize their uncertainty. One of the models was adopted to generate the wind fields used as input to a second generation wave model. The relative error in the wind speed was considered in order to assess the uncertainties of the predictions or the significant wave height. Different time steps for the wind input were also used to determine their effect on the predicted significant wave height.

scholarly journals Evaluation of Assimilation in the MASNUM Wave Model Based on Jason-3 and CFOSAT

2021 ◽  
Vol 13 (19) ◽  
pp. 3833
Author(s):  
Meng Sun ◽  
Jianting Du ◽  
Yongzeng Yang ◽  
Xunqiang Yin
Keyword(s):  
Wave Height ◽  
Significant Wave Height ◽  
Wave Model ◽  
Ocean Waves ◽  
Validation Data ◽  
Engineering Construction ◽  
Significant Wave ◽  
Offshore Engineering ◽  
The Indian Ocean ◽  
Dynamic Sampling

Accurate numerical simulation of ocean waves is one of the most important measures to ensure shipping safety, offshore engineering construction, etc. The use of wave observations from satellite is an efficient way to correct model results. The goal of this paper is to assess the performance of assimilation in the MASNUM wave model for the Indian Ocean. The assimilation technique is based on Ensemble Adjusted Kalman Filter, with a variable ensemble constructed by the dynamic sampling method rather than ensemble members of wave model. Observations of significant wave height from satellites Jason-3 and CFOSAT are regarded as assimilation data and independent validation data, respectively. The results indicate good performance in terms of absolute mean error for significant wave height. Model error decreases by roughly 20–40% in high-sea conditions.

Climatology, Variability and Extrema of Ocean Waves: The Web-Based KNMI/ERA-40 Wave Atlas

2006 ◽  
Author(s):  
Andreas Sterl ◽  
Sofia Caires
Keyword(s):  
Wave Height ◽  
Significant Wave Height ◽  
Wave Model ◽  
Ocean Waves ◽  
Wave Period ◽  
Web Based ◽  
Significant Wave ◽  
Wave Parameters ◽  
Wave Heights ◽  
The Web

The European Centre for Medium Range Weather Forecasts (ECMWF) has recently finished ERA-40, a reanalysis covering the period September 1957 to August 2002. One of the products of ERA-40 consists of 6-hourly global fields of wave parameters like significant wave height and wave period. These data have been generated with the Centre’s WAM wave model. From these results the authors have derived climatologies of important wave parameters, including significant wave height, mean wave period, and extreme significant wave heights. Particular emphasis is on the variability of these parameters, both in space and time. Besides for scientists studying climate change, these results are also important for engineers who have to design maritime constructions. This paper describes the ERA-40 data and gives an overview of the results derived. The results are available on a global 1.5° × 1.5° grid. They are accessible from the web-based KNMI/ERA-40 Wave Atlas at http://www.knmi.nl/waveatlas.

scholarly journals Characteristics of high monsoon wind-waves observed at multiple stations in the eastern Arabian Sea

2017 ◽  
Author(s):  
M. M. Amrutha ◽  
V. Sanil Kumar
Keyword(s):  
Wave Height ◽  
Significant Wave Height ◽  
Arabian Sea ◽  
Wind Waves ◽  
Surface Wind ◽  
Wave Model ◽  
Spatial Distance ◽  
Significant Wave ◽  
Eastern Arabian Sea ◽  
Crest Height

Abstract. The growth and decay of surface wind-waves during one-month period in a typical Indian summer monsoon is investigated based on the data collected at 9 to 15 m water depth at 4 locations in the nearshore waters of the eastern Arabian Sea covering a spatial distance of ~ 350 km. The significant wave height varied from 0.7 to 5.5 m during the data collection considered in the analysis. The heights of waves during the measurement period often exceed 3 m. The most extreme wave height is 1.50 to 1.62 times the significant wave height and the most extreme crest height of the wave is 1.23 to 1.35 times the significant wave height of the same 30-minutes record. The average ratio of crest height of the wave to the height of the same wave is 0.58 to 0.67. The height of waves having maximum crest height is smaller than the maximum wave height during 30 minutes period. Measured waves are predominantly swell, but since the majority of wave generation during the monsoon is adjacent to the study area and the wind–wave coupling is strong, wave periods are rarely above 15 s. The numerical wave model could estimate the wave height reasonably well during the wave growth compared to the wave decay period. Hovmöller diagrams show a considerable spatial variability in the wave and wind pattern in the Indian Ocean during the high wave event at the eastern Arabian Sea.

Significant wave height retrieval from Sentinel-1 SAR imagery by convolutional neural network

2020 ◽  
Vol 76 (6) ◽  
pp. 465-477
Author(s):  
Sihan Xue ◽  
Xupu Geng ◽  
Xiao-Hai Yan ◽  
Ting Xie ◽  
Qiuze Yu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Wave Height ◽  
Significant Wave Height ◽  
Significant Wave ◽  
Sar Imagery

Correlation Enhanced Machine Learning Approach based Wave Height Prediction

2018 ◽  
Vol 4 (5) ◽  
pp. 10
Author(s):  
Ruchi Shrivastava ◽  
Dr. Krishna Teerth Chaturvedi
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Wave Height ◽  
Significant Wave Height ◽  
Work Performance ◽  
Feature Reduction ◽  
Learning Approaches ◽  
Significant Wave ◽  
Wave Parameters ◽  
Height Prediction

The prediction of wave height is one of the major problems of coastal engineering and coastal structures. In recent years, advances in the prediction of significant wave height have been considerably developed using flexible calculation techniques. In addition to the traditional prediction of significant wave height, soft computing has explored a new way of predicting significant wave heights. This research was conducted in the direction of forecasting a significant wave height using machine learning approaches. In this paper, a problem of significant wave height prediction problem has been tackled by using wave parameters such as wave spectral density. This prediction of significant wave height helps in wave energy converters as well as in ship navigation system. This research will optimize wave parameters for a fast and efficient wave height prediction. For this Pearson’s, Kendall’s and Spearman’s Correlation Coefficients and Particle Swarm Optimization feature reduction techniques are used. So reduced features are taken into consideration for prediction of wave height using neural network. In this work, performance evaluation metrics such as MSE and RMSE values are decreased and gives better performance of classification that is compared with existing research’s implemented methodology. From the experimental results, it is observed that proposed algorithm gives the better prediction as compared to PSO feature reduction technique. So, it is also concluded that Co-relation enhanced neural network is better as compared to PSO based neural network with increased number of features.

Sign in / Sign up

Export Citation Format

Share Document