共查询到20条相似文献，搜索用时 312 毫秒
1.
The literature on ocean wave forecasting falls into two categories, physics-based models and statistical methods. Since these two approaches have evolved independently, it is of interest to determine which approach can predict more accurately, and over what time horizons. This paper runs a comparative analysis of a well-known physics-based model for simulating waves near shore, SWAN, and two statistical techniques, time-varying parameter regression and a frequency domain algorithm. Forecasts are run for the significant wave height, over horizons ranging from the current period (i.e., the analysis time) to 15 h. Seven data sets, four from the Pacific Ocean and three from the Gulf of Mexico, are used to evaluate the forecasts. The statistical models do extremely well at short horizons, producing more accurate forecasts in the 1–5 hour range. The SWAN model is superior at longer horizons. The crossover point, at which the forecast error from the two methods converges, is in the area of 6 h. Based on these results, the choice of statistical versus physics-based models will depend on the uses to which the forecasts will be put. Utilities operating wave farms, which need to forecast at very short horizons, may prefer statistical techniques. Navies or shipping companies interested in oceanic conditions over longer horizons will prefer physics-based models. 相似文献
2.
Forecasting ocean wave energy: Tests of time-series models 总被引：1，自引：0，他引：1
Gordon Reikard 《Ocean Engineering》2009,36(5):348-356
This paper evaluates the ability of time-series models to predict the energy from ocean waves. Data sets from four Pacific Ocean sites are analyzed. The energy flux is found to exhibit nonlinear variability. The probability distribution has heavy tails, while the fractal dimension is non-integer. This argues for using nonlinear models. The primary technique used here is a time-varying parameter regression in logs. The time-varying regression is estimated using both a Kalman filter and a sliding window, with various window widths. The sliding window method is found to be preferable. A second approach is to combine neural networks with time-varying regressions, in a hybrid model. Both of these methods are tested on the flux itself. Time-varying regressions are also used to forecast the wave height and wave period separately, and combine the forecasts to predict the flux. Forecasting experiments are run at an hourly frequency over horizons of 1-4 h, and at a daily frequency over 1-3 days. All the models are found to improve relative to a random walk. In the hourly data sets, forecasting the components separately achieves the best results in three out of four cases. In daily data sets, the hybrid and regression models yield similar outcomes. Because of the intrinsic variability of the data, the forecast error is fairly high, comparable to the errors found in other forms of alternative energy, such as wind and solar. 相似文献
3.
《Applied Ocean Research》2007,29(1-2):72-79
The wave observations at three locations off the west coast of India have been analyzed using artificial neural network (ANN) to obtain forecasts of significant wave heights at intervals of 3, 6, 12 and 24 h. The most appropriate training method requiring an input of four observations spread over previous 24 h has been selected after considerable trials. Further, the networks are trained after filling in the missing information. Larger gaps in data are filled in using spatial mapping involving observations at nearby locations, while relatively smaller gaps are accounted for by the statistical technique of multiple regressions in temporal mode. It is found that by doing so the long-interval forecasting is tremendously improved, with corresponding accuracy levels becoming close to those of the short-interval forecasts. If the amount of gaps is restricted to around 2% per year or so it is possible to obtain 12 h ahead forecasts with 0.08 m accuracy on an average and 24 h ahead forecast with a mean accuracy of 0.13 m. However, in harsher environments the prediction accuracy can change. 相似文献
4.
Mehmet Özger 《Ocean Engineering》2010,37(16):1443-1451
Wave heights and periods are the significant inputs for coastal and ocean engineering applications. These applications may require to obtain information about the sea conditions in advance. This study aims to propose a forecasting scheme that enables to make forecasts up to 48 h lead time. The combination of wavelet and fuzzy logic approaches was employed as a forecasting methodology. Wavelet technique was used to separate time series into its spectral bands. Subsequently, these spectral bands were estimated individually by fuzzy logic approach. This combination of techniques is called wavelet fuzzy logic (WFL) approach. In addition to WFL method, fuzzy logic (FL), artificial neural networks (ANN), and autoregressive moving average (ARMA) methods were employed to the same data set for comparison purposes. It is seen that WFL outperforms those methods in all cases. The superiority of the WFL in model performances becomes very clear especially in higher lead times such as 48 h. Significant wave height and average wave period series obtained from buoys located off west coast of US were used to train and test the proposed models. 相似文献
5.
This paper presents soft computing approach for estimation of missing wave heights at a particular location on a real-time basis using wave heights at other locations. Six such buoy networks are developed in Eastern Gulf of Mexico using soft computing techniques of Artificial Neural Networks (ANN) and Genetic Programming (GP). Wave heights at five stations are used to estimate wave height at the sixth station. Though ANN is now an established tool in time series analysis, use of GP in the field of time series forecasting/analysis particularly in the area of Ocean Engineering is relatively new and needs to be explored further. Both ANN and GP approach perform well in terms of accuracy of estimation as evident from values of various statistical parameters employed. The GP models work better in case of extreme events. Results of both approaches are also compared with the performance of large-scale continuous wave modeling/forecasting system WAVEWATCH III. The models are also applied on real time basis for 3 months in the year 2007. A software is developed using evolved GP codes (C++) as back end with Visual Basic as the Front End tool for real-time application of wave estimation model. 相似文献
6.
利用欧洲中期天气预报中心和国家海洋环境预报中心的数值预报产品，形成包括理想台风模型的模式初值，用正压原始方程做台风路径预报，经过１９９４年的６个台风的实时预报试验，效果较好。 相似文献
7.
The tremendous increase in offshore operational activities demands improved wave forecasting techniques. With the knowledge of accurate wave conditions, it is possible to carry out the marine activities such as offshore drilling, naval operations, merchant vessel routing, nearshore construction, etc. more efficiently and safely. This paper describes an artificial neural network, namely recurrent neural network with rprop update algorithm and is applied for wave forecasting. Measured ocean waves off Marmugao, west coast of India are used for this study. Here, the recurrent neural network of 3, 6 and 12 hourly wave forecasting yields the correlation coefficients of 0.95, 0.90 and 0.87, respectively. This shows that the wave forecasting using recurrent neural network yields better results than the previous neural network application. 相似文献
8.
Real-time wave forecasting using genetic programming 总被引：4，自引：0，他引：4
The forecasting of ocean waves on real-time or online basis is necessary while carrying out any operational activity in the ocean. In order to obtain forecasts that are station-specific a time-series-based approach like stochastic modeling or artificial neural network was attempted by some investigators in the past. This paper presents an application of a relatively new soft computing tool called genetic programming for this purpose. Genetic programming is an extension of genetic algorithm and it is suited to explore dependency between input and output data sets. The wave rider buoy measurements available at two locations in the Gulf of Mexico are analyzed. The forecasts of significant wave heights are made over lead times of 3, 6, 12 and 24 h. The sample size belonged to a period of 15 years and it included an extensive testing period of 5 years. The forecasts made by the approach of genetic programming indicated that it can be regarded as a promising tool for future applications to ocean predictions. 相似文献
9.
In this paper, first we introduce the wave run-up scale which describes the degree of wave run-up based on observed sea conditions near and on a coastal structure. Then, we introduce a simple method which can be used for daily forecast of wave run-up on a coastal structure. The method derives a multiple linear regression equation between wave run-up scale and offshore wind and wave parameters using long-term photographical observation of wave run-up and offshore wave forecasting model results. The derived regression equation then can be used for forecasting the run-up scale using the offshore wave forecasting model results. To test the implementation of the method, wave run-up scales were observed at four breakwaters in the East Coast of Korea for 9 consecutive months in 2008. The data for the first 6 months were used to derive multiple linear regression equations, which were then validated using the run-up scale data for the remaining 3 months and the corresponding offshore wave forecasting model results. A comparison with an engineering formula for wave run-up is also made. It is found that this method can be used for daily forecast and warning of wave run-up on a coastal structure with reasonable accuracy. 相似文献
10.
南海及邻近海域大气-海浪-海洋耦合精细化数值预报系统研制 总被引：2，自引：1，他引：1
本文主要介绍了南海及邻近海域大气-海浪-海洋耦合精细化数值预报系统的研制概况。预报区域为99°E~135°E,15°S~45°N,包括渤海、黄海、东海和南海及其周边海域。为了给耦合预报模式提供较准确的预报初始场,在预报开始之前,分别进行了海浪模式和海洋模式的前24小时同化后报模拟。海浪模式和海洋模式都采用了集合调整Kalman滤波同化方法,海浪模式同化了Jason-2有效波高数据;海洋模式同化了SST数据、MADT数据和ARGO剖面数据。为了改进海洋温度和盐度的模拟,我们在海洋模式的垂向混合方案中引入波致混合和内波致混合的作用。预报系统的运行主要包括两个阶段,首先海浪模式和海洋模式进行了2014年1月至2015年10月底的同化后报模拟,强迫场源自欧洲气象中心的六小时的再分析数据产品。然后耦合预报系统将同化后报模拟的结果作为初始场进行了14个月的耦合预报。预报产品包括大气产品（气温、风速风向、气压等）、海浪产品（有效波高和波向等）、海流产品（温度、盐度和海流等）。一系列观测资料的检验比较表明该大气-海浪-海洋耦合精细化数值预报系统的预报结果较为可靠,可以为南海及周边海洋资源开发和安全保障提供数据和信息产品服务。 相似文献
11.
Interpolation of wave heights 总被引：1，自引：0，他引：1
Remote sensing of waves often necessitates presentation of data in the form of wave height values grouped over large time intervals. This restricts their use to long-term applications only. This paper describes how such data can be made suitable for short-term usage in the field. Weekly mean significant wave heights were derived from their monthly mean observations with the help of different alternative techniques. These include model-free neural network schemes as well as model-based statistical and numerical methods. Superiority of neural networks was noted when the estimations were compared with corresponding observations. The network was trained using three different training algorithms, viz., error back propagation, conjugate gradient and cascade correlation. The technique of cascade correlation took minimum training time and showed better coefficient of correlation between observations and network output. 相似文献
12.
Increasing wave heights and extreme value projections: The wave climate of the U.S. Pacific Northwest 总被引：1，自引：0，他引：1
Deep-water wave buoy data offshore from the U.S. Pacific Northwest (Oregon and Washington) document that the annual averages of deep-water significant wave heights (SWHs) have increased at a rate of approximately 0.015 m/yr since the mid-1970s, while averages of the five highest SWHs per year have increased at the appreciably greater rate of 0.071 m/yr. Histograms of the hourly-measured SWHs more fully document this shift toward higher values over the decades, demonstrating that both the relatively low waves of the summer and the highest SWHs generated by winter storms have increased. Wave heights associated with higher percentiles in the SWH cumulative distribution function are shown to be increasing at progressively faster rates than those associated with lower percentiles. This property is demonstrated to be a direct result of the probability distributions for annual wave climates having lognormal- or Weibull-like forms in that a moderate increase in the mean SWH produces significantly greater increases in the tail of the distribution. Both the linear regressions of increasing annual averages and the evolving probability distribution of the SWH climate, demonstrating the non-stationarity of the Pacific Northwest wave climate, translate into substantial increases in extreme value projections, important in coastal engineering design and in quantifying coastal hazards. Buoy data have been analyzed to assess this response in the wave climate by employing various time-dependent extreme value models that directly compute the progressive increases in the 25- to 100-year projections. The results depend somewhat on the assumptions made in the statistical procedures, on the numbers of storm-generated SWHs included, and on the threshold value for inclusion in the analyses, but the results are consistent with the linear regressions of annual averages and the observed shifts in the histograms. 相似文献
13.
Learning from data for wind-wave forecasting 总被引：1，自引：0，他引：1
Along with existing numerical process models describing the wind-wave interaction, the relatively recent development in the area of machine learning make the so-called data-driven models more and more popular. This paper presents a number of data-driven models for wind-wave process at the Caspian Sea. The problem associated with these models is to forecast significant wave heights for several hours ahead using buoy measurements. Models are based on artificial neural network (ANN) and instance-based learning (IBL) .To capture the wind-wave relationship at measurement sites, these models use the existing past time data describing the phenomenon in question. Three feed-forward ANN models have been built for time horizon of 1, 3 and 6 h with different inputs. The relevant inputs are selected by analyzing the average mutual information (AMI). The inputs consist of priori knowledge of wind and significant wave height. The other six models are based on IBL method for the same forecast horizons. Weighted k-nearest neighbors (k-NN) and locally weighted regression (LWR) with Gaussian kernel were used. In IBL-based models, forecast is made directly by combining instances from the training data that are close (in the input space) to the new incoming input vector. These methods are applied to two sets of data at the Caspian Sea. Experiments show that the ANNs yield slightly better agreement with the measured data than IBL. ANNs can also predict extreme wave conditions better than the other existing methods. 相似文献
14.
Forecasting of wave parameters is necessary for many marine and coastal operations. Different forecasting methodologies have been developed using the wind and wave characteristics. In this paper, artificial neural network (ANN) as a robust data learning method is used to forecast the wave height for the next 3, 6, 12 and 24 h in the Persian Gulf. To determine the effective parameters, different models with various combinations of input parameters were considered. Parameters such as wind speed, direction and wave height of the previous 3 h, were found to be the best inputs. Furthermore, using the difference between wave and wind directions showed better performance. The results also indicated that if only the wind parameters are used as model inputs the accuracy of the forecasting increases as the time horizon increases up to 6 h. This can be due to the lower influence of previous wave heights on larger lead time forecasting and the existing lag between the wind and wave growth. It was also found that in short lead times, the forecasted wave heights primarily depend on the previous wave heights, while in larger lead times there is a greater dependence on previous wind speeds. 相似文献
15.
To explore new operational forecasting methods of waves, a forecasting model for wave heights at three stations in the Bohai Sea has been developed. This model is based on long short-term memory(LSTM) neural network with sea surface wind and wave heights as training samples. The prediction performance of the model is evaluated,and the error analysis shows that when using the same set of numerically predicted sea surface wind as input, the prediction error produced by the proposed LSTM model at Sta. N01 is 20%, 18% and 23% lower than the conventional numerical wave models in terms of the total root mean square error(RMSE), scatter index(SI) and mean absolute error(MAE), respectively. Particularly, for significant wave height in the range of 3–5 m, the prediction accuracy of the LSTM model is improved the most remarkably, with RMSE, SI and MAE all decreasing by 24%. It is also evident that the numbers of hidden neurons, the numbers of buoys used and the time length of training samples all have impact on the prediction accuracy. However, the prediction does not necessary improve with the increase of number of hidden neurons or number of buoys used. The experiment trained by data with the longest time length is found to perform the best overall compared to other experiments with a shorter time length for training. Overall, long short-term memory neural network was proved to be a very promising method for future development and applications in wave forecasting. 相似文献
16.
Forecasting of ocean wave heights, with warning time of a few hours or days, is necessary in planning many operation-related activities in the ocean. Such information is currently derived by numerically solving the differential equation representing wave energy balance. The solution procedure involved is extremely complex and calls for very large amounts of meteorological and oceanographic data. This paper presents a complementary and simple method to make a point forecast of waves in real time sense based on the current observation of waves at a site. It incorporates the technique of neural networks. The network involved is first trained by different algorithms and then used to forecast waves with lead times varying from 3 to 24 h. The results of different training algorithms are compared with each other. The neural output is further compared with the statistical AR models. 相似文献
17.
《Ocean Engineering》1999,26(3):191-203
Forecasting of ocean wave heights, with warning time of a few hours or days, is necessary in planning many operation-related activities in the ocean. Such information is currently derived by numerically solving the differential equation representing wave energy balance. The solution procedure involved is extremely complex and calls for very large amounts of meteorological and oceanographic data. This paper presents a complementary and simple method to make a point forecast of waves in real time sense based on the current observation of waves at a site. It incorporates the technique of neural networks. The network involved is first trained by different algorithms and then used to forecast waves with lead times varying from 3 to 24 h. The results of different training algorithms are compared with each other. The neural output is further compared with the statistical AR models. 相似文献
18.
Wave parameters prediction is an important issue in coastal and offshore engineering. In this literature, several models and methods are introduced. In the recent years, the well-known soft computing approaches, such as artificial neural networks, fuzzy and adaptive neuro-fuzzy inference systems and etc., have been known as novel methods to form intelligent systems, these approaches has also been used to predict wave parameters, as well. It is not a long time that support vector machine (SVM) is introduced as a strong machine learning and data mining tool. In this paper, it is used to predict significant wave height (Hs). The data set used in this study comprises wave wind data gathered from deep water locations in Lake Michigan. Current wind speed (u) and those belonging up to six previous hours are given as input variables, while the significant wave height is the output parameter. The SVM results are compared with those of artificial neural networks, multi-layer perceptron (MLP) and radial basis function (RBF) models. The results show that SVM can be successfully used for prediction of Hs. Furthermore, comparisons indicate that the error statistics of SVM model marginally outperforms ANN even with much less computational time required. 相似文献
19.
数值模式与统计模型相耦合的近岸海浪预报方法 总被引：2，自引：2，他引：0
针对数值模式和统计模型预报近岸海浪存在的局限性,构建了数值模式和统计模型相耦合的近岸海浪预报框架,在模式计算格点和近岸预报目标点之间定义一个海浪能量密度谱传递系数,通过经验正交函数分解和卡尔曼滤波方法建立传递系数的统计预报模型并与数值模式进行耦合。经过对近岸波浪观测站1a的预报试验表明:该方法能够提高近岸海浪有效波高预报精度,有效波高的均方根误差降低了约0.16m,平均相对误差降低约9%。进一步试验和分析发现,该方法的预报有效时间小于24h,将海浪能量密度谱经过分解后得到的基本模态反映了近岸波侯的主要特征,海浪能量密度谱传递系数的变化体现了波侯的季节变化特点。 相似文献
20.
《Coastal Engineering》2004,51(4):277-296
A cyclone induced storm surge and flood forecasting system that has been developed for the northern Bay of Bengal is presented. The developed system includes a cyclone forecasting model that uses statistical models for forecasting of the cyclone track and maximum wind speed, and an analytical cyclone model for generation of cyclone wind and pressure fields. A data assimilation system has been developed that allows updating of the cyclone parameters based on air pressure and wind speed observations from surface meteorological stations. The forecasted air pressure and wind fields are used as input in a 2D hydrodynamic model for forecasting storm surge levels and associated flooding. An efficient uncertainty prediction procedure based on Harr's point estimation method has been implemented as part of the forecasting system for prediction of the uncertainties of the forecasted storm surge levels and inundation areas caused by the uncertainties in the cyclone track and wind speed forecasts. The developed system is applied on a severe cyclone that hit Bangladesh in April 1991. The simulated storm surge and associated flooding are highly sensitive to the cyclone data. The cyclone data assimilation system provides a more accurate cyclone track when the cyclone approaches the coastline, which results in a significant improvement of the storm surge and flood predictions. Application of the uncertainty prediction procedure shows that the large uncertainties of the cyclone track and intensity forecasts result in large uncertainties of the forecasted storm surge levels and flood extend. The forecasting system shows very good forecasting capabilities up to 24 h before the actual landfall. 相似文献