Longshore sediment transport estimation using a fuzzy inference system

Accurate prediction of longshore sediment transport in the nearshore zone is essential for control of shoreline erosion and beach evolution. In this paper, a hybrid Adaptive-Network-Based Fuzzy Inference System (ANFIS), Fuzzy Inference System (FIS), CERC, Walton–Bruno (WB) and Van Rijn (VR) formulae are used to predict and model longshore sediment transport in the surf zone. The architecture of ANFIS consisted of three inputs (breaking wave height), (breaking angle), (wave period) and one output (longshore sediment transport rate). For statistical comparison of predicted and measured sediment transport, bias, root mean square error and scatter index are used. The longshore sediment transport rate (LSTR) and wave characteristics at a 4 km-long beach on the central west coast of India are used as case studies. The CERC, WB and VR methods are also applied to the same data. Results indicate that the errors of the ANFIS model in predicting wave parameters are less than those of the empirical formulas. The scatter index of the CERC, WB and VR methods in predicting LSTR is 51.9%, 27.9% and 22.5%, respectively, while the scatter index of the ANFIS model in the prediction of LSTR is 17.32%. A comparison of results reveals that the ANFIS model provides higher accuracy and reliability for LSTR estimation than the other techniques.     

Prediction of significant wave height using regressive support vector machines

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 (H_s). 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 H_s. Furthermore, comparisons indicate that the error statistics of SVM model marginally outperforms ANN even with much less computational time required.     

一种基于小波分解和模糊推理神经网络的潮位预测方法

潮位预测严重影响沿海区域,尤其是近海浅水沿岸地区居民的生产生活和涉海活动。谐波分析是长周期潮位预测的传统方法,但无法预测非周期性气象过程发生时的水位变化。与数据处理方法相结合,人工智能的方法通过拟合输入与输出数据的历史数值关系,能够有效预测高度非线性和非平稳的流模式,因而在时间序列数据预测领域得到了广泛的应用。本文结合自适应模糊推理系统（Adaptive Neuro-Fuzzy Inference System, ANFIS）和小波分解方法,利用水位异常和风切变分量作为输入数据,实现了一种综合的多时效潮位预测方法。文中测试了多种输入变量组合和小波-ANFIS（WANFIS）模型,并与人工神经网络（Artificial Neural Network, ANN）、小波-ANN（WANN）和ANFIS模型进行了预测结果对比。通过不同指数的误差分析来看,相比ANN模型,ANFIS模型能够更准确的预测潮位变化,小波分解对ANFIS预测精度有一定的提高,且模型中水位异常和风切变分量数据的加入比单一的潮位数据输入能取得更好的预测结果。     

Sea Level Change Analysis and Models Identification Based on Short Tidal Gauge Measurements in Alexandria,Egypt

Sea level change analysis and models identification are important factors used for coastal engineering applications. Moreover, sea level change modeling is used widely to evaluate and study shoreline and climate changes. This study intends to analyze and model Alexandria, Egypt sea level change by investigating yearly tide gauge data collected in a short duration (2008–2011). The time-frequency method was used to evaluate the meteorological noise frequencies. Two models were used to predict the time series data: Neural Network Autoregressive Moving Average (NNARMA) and Adaptive Neuro-Fuzzy Inference System (ANFIS). The time-frequency analysis and models identification results showed that no extreme events were detected for Alexandria point during the monitoring period. Therefore, the NNARMA and ANFIS models can be used to identify the sea level change. The estimates of the models were compared with the three different statistics, determination coefficient, root mean square errors, and auto-correlation function. Comparison of these results revealed that the NNARMA model performs better than the ANFIS model for the study area.     

Application of a fuzzy inference system for the prediction of longshore sediment transport

A fuzzy inference system (FIS) and a hybrid adaptive network-based fuzzy inference system (ANFIS), which combines a fuzzy inference system and a neural network, are used to predict and model longshore sediment transport (LST). The measurement data (field and experimental data) obtained from Kamphuis [1] and Smith et al. [2] were used to develop the model. The FIS and ANFIS models employ five inputs (breaking wave height, breaking wave angle, slope at the breaking point, peak wave period and median grain size) and one output (longshore sediment transport rate). The criteria used to measure the performances of the models include the bias, the root mean square error, the scatter index and the coefficients of determination and correlation. The results indicate that the ANFIS model is superior to the FIS model for predicting LST rates. To verify the ANFIS model, the model was applied to the Karaburun coastal region, which is located along the southwestern coast of the Black Sea. The LST rates obtained from the ANFIS model were compared with the field measurements, the CERC [3] formula, the Kamphuis [1] formula and the numerical model (LITPACK). The percentages of error between the measured rates and the calculated LST rates based on the ANFIS method, the CERC formula (K_sig = 0.39), the calibrated CERC formula (K_sig = 0.08), the Kamphuis [1] formula and the numerical model (LITPACK) are 6.5%, 413.9%, 6.9%, 15.3% and 18.1%, respectively. The comparison of the results suggests that the ANFIS model is superior to the FIS model for predicting LST rates and performs significantly better than the tested empirical formulas and the numerical model.     

Estimation of pile group scour using adaptive neuro-fuzzy approach

An accurate estimation of scour depth around piles is important for coastal and ocean engineers involved in the design of marine structures. Owing to the complexity of the problem, most conventional approaches are often unable to provide sufficiently accurate results. In this paper, an alternative attempt is made herein to develop adaptive neuro-fuzzy inference system (ANFIS) models for predicting scour depth as well as scour width for a group of piles supporting a pier. The ANFIS model provides the system identification and interpretability of the fuzzy models and the learning capability of neural networks in a single system. Two combinations of input data were used in the analyses to predict scour depth: the first input combination involves dimensional parameters such as wave height, wave period, and water depth, while the second combination contains nondimensional numbers including the Reynolds number, the Keulegan–Carpenter number, the Shields parameter and the sediment number. The test results show that ANFIS performs better than the existing empirical formulae. The ANFIS predicts scour depth better when it is trained with the original (dimensional) rather than the nondimensional data. The depth of scour was predicted more accurately than its width. A sensitivity analysis showed that scour depth is governed mainly by the Keulegan–Carpenter number, and wave height has a greater influence on scour depth than the other independent parameters.     

利用WAVEWATCH和SWAN嵌套计算珠江口附近海域的风浪场*

基于CCMP(Cross Calibrated Multi-platform)卫星遥感海面风场数据,通过将WAVEWATCH和SWAN (Simulating WAves Nearshore)模型嵌套的方法,数值模拟了珠江口附近海域的风浪场。将总计10个月的数值模拟的有效波高、波周期和波向分别与相应的观测值进行了定量比较。结果说明,有效波高的平均绝对误差为15.4cm,分散系数SI为0.240,相关系数为0.925;波周期的平均绝对误差为1.9s,分散系数SI为0.433,相关系数为0.636;波向的平均绝对误差为23.9°。计算的波高和波向与观测结果的变化趋势相吻合。由于第三代海浪模式本身的缺陷,导致所计算的波周期偏小。总体说来,本文所采用的数值模式能较好地模拟珠江口附近海域的风浪场。另外,还设计了6个算例以探讨采用不同的计算方法和风场对计算结果精度的影响。结果表明使用本文的数值方法和高精度的CCMP风场确实可以提高计算结果的精度。     

风浪和涌浪分离方法的比较（英文）

海浪通常以风浪和涌浪混合的形式存在,如何进行分离风浪和涌浪一直是海浪理论研究和海洋工程应用中的重要问题。本文利用模型试验和实测资料,对目前提出的一种二维谱风涌浪分离方法（2D法）和三种一维谱风涌浪分离方法（PM法、WH法、JP法）进行了检验,分析发现：2D法给出的结果整体而言最为可靠,与2D法相比,PM法明显高估了风浪成分,WH法低风速时高估了风浪,高风速时跟2D法比较接近,而JP法在整体上高估了风浪成分。通过调整分割频率的比例系数,改进了PM法,改进后的PM法给出的分离结果与2D法最为一致。     

Wave height forecasting in Dayyer, the Persian Gulf

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.     

风浪和涌浪分离方法的比较

海浪通常以风浪和涌浪混合的形式存在。文中利用模型试验和实测资料,对目前提出的一种二维谱风涌浪分离方法(2D法)和3种一维谱风涌浪分离方法(PM法、WH法、JP法)进行了检验,分析发现:2D法给出的结果整体而言最为可靠,与2D法相比,PM法明显高估了风浪成分,WH法低风速时高估了风浪,高风速时跟2D法比较接近,而JP法在整体上高估了风浪成分。通过调整分割频率的比例系数,改进了PM法,改进后的PM法给出的分离结果与2D法最为一致。     

海浪对ASCAT散射计反演风场的影响研究

To improve retrieval accuracy, this paper studies wave effects on retrieved wind field from a scatterometer. First, the advanced scatterometer(ASCAT) data and buoy data of the National Data Buoy Center(NDBC) are collocated. Buoy wind speed is converted into neutral wind at 10 m height. Then, ASCAT data are compared with the buoy data for the wind speed and direction. Subsequently, the errors between the ASCAT and the buoy wind as a function of each wave parameter are used to analyze the wave effects. Wave parameters include dominant wave period(dpd), significant wave height(swh), average wave period(apd) and the angle between the dominant wave direction(dwd) and the wind direction. Collocated data are divided into sub-datasets according to the different intervals of each wave parameter. A root mean square error(RMSE) for the wind speed and a mean absolute error(MAE) for the wind direction are calculated from the sub-datasets, which are considered as the function of wave parameters. Finally, optimal wave conditions on wind retrieved from the ASCAT are determined based on the error analyses. The results show the ocean wave parameters have correlative relationships with the RMSE of the retrieved wind speed and the MAE of the retrieved wind direction. The optimal wave conditions are presented in terms of dpd, swh, apd and angle.     

Comparison of wind and wave measurements and models in the Western Mediterranean Sea

We have hindcast the wind and wave conditions in the Mediterranean Sea for two one month periods. Four different meteorological models and three different wave models have been used. The results have been compared with satellite and buoy wind and wave observations.Several conclusions concerning both the instruments and the models have been derived. The quality of both wind and wave results has been assessed. Close to the coasts high resolution, nested wave models are required for sufficient reliability.A wave threshold analysis suggests a sufficient reliability only off the coast, with a substantial decrease for low wave heights.     

Neuro-fuzzy based approach for wave transmission prediction of horizontally interlaced multilayer moored floating pipe breakwater

The ocean wave system in nature is very complicated and physical model studies on floating breakwaters are expensive and time consuming. Till now, there has not been available a simple mathematical model to predict the wave transmission through floating breakwaters by considering all the boundary conditions. This is due to complexity and vagueness associated with many of the governing variables and their effects on the performance of breakwater. In the present paper, Adaptive Neuro-Fuzzy Inference System (ANFIS), an implementation of a representative fuzzy inference system using a back-propagation neural network-like structure, with limited mathematical representation of the system, is developed. An ANFIS is trained on the data set obtained from experimental wave transmission of horizontally interlaced multilayer moored floating pipe breakwater using regular wave flume at Marine Structure Laboratory, National Institute of Technology Karnataka, Surathkal, India. Computer simulations conducted on this data shows the effectiveness of the approach in terms of statistical measures, such as correlation coefficient, root-mean-square error and scatter index. Influence of input parameters is assessed using the principal component analysis. Also results of ANFIS models are compared with that of artificial neural network models.     

Comparison between M5′ model tree and neural networks for prediction of significant wave height in Lake Superior

Prediction of wave height is of great importance in marine and coastal engineering. Soft computing tools such as artificial neural networks (ANNs) are recently used for prediction of significant wave height. However, ANNs are not as transparent as semi-empirical regression-based models. In addition, neural networks approach needs to find network parameters such as number of hidden layers and neurons by trial and error, which is time consuming. Therefore, in this work, model trees as a new soft computing method was invoked for prediction of significant wave height. The main advantage of model trees is that, compared to neural networks, they represent understandable rules. These rules can be readily expressed so that humans can understand them. The data set used for developing model trees comprises of wind and wave data gathered in Lake Superior from 6 April to 10 November 2000 and 19 April to 6 November 2001. M5′ algorithm was employed for building and evaluating model trees. Training and testing data include wind speed (U₁₀) as the input variable and the significant wave height (H_s) as the output variable. Results indicate that error statistics of model trees and feed-forward back propagation (FFBP) ANNs were similar, while model trees was marginally more accurate. In addition, model tree shows that for wind speed above 4.7 m/s, the wave height increases nonlinearly by the wind speed.     

Model tree approach for prediction of pile groups scour due to waves

Scour around piles could endanger the stability of the structures placed on them. Hence, an accurate estimation of the scour depth around piles is very important in coastal and marine engineering. Due to the complex interaction between the wave, seabed and pile group; prediction of the scour depth is not an easy task and the available empirical formulas have limited accuracy. Recently, soft computing methods such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs) have been used for the prediction of the scour depth. However, these methods do not give enough insight about the process and are not as easy to use as the empirical equations. In this study, new formulas are given that are easy to use, accurate and physically sound. Available empirical equations for estimating the pile group scour depth such as those of Sumer et al. (1992) and Bayram and Larson (2000), are less accurate compared to the given equations. These equations are as accurate as other soft computing methods such as ANN and SVM. Moreover, in this study, safety factors are given for different levels of acceptable risks, which can be so useful for engineers.     

全球有效波高和风速的时空变化及相关关系研究

The climatology of significant wave height（SWH） and sea surface wind speed are matters of concern in the fields of both meteorology and oceanography because they are very important parameters for planning offshore structures and ship routings. The TOPEX/Poseidon altimeter, which collected data for about 13 years from September 1992 to October 2005, has measured SWHs and surface wind speeds over most of the world＇s oceans. In this paper, a study of the global spatiotemporal distributions and variations of SWH and sea surface wind speed was conducted using the TOPEX/Poseidon altimeter data set. The range and characteristics of the variations were analyzed quantitatively for the Pacific, Atlantic, and Indian oceans. Areas of rough waves and strong sea surface winds were localized precisely, and the correlation between SWH and sea surface wind speed analyzed.     

A forecasting model for wave heights based on a long short-term memory neural network

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.     

Soft computing approach for real-time estimation of missing wave heights

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.     

Linear genetic programming to scour below submerged pipeline

Genetic programming (GP) has nowadays attracted the attention of researchers in the prediction of hydraulic data. This study presents Linear Genetic Programming (LGP), which is an extension to GP, as an alternative tool in the prediction of scour depth below a pipeline. The data sets of laboratory measurements were collected from published literature and were used to develop LGP models. The proposed LGP models were compared with adaptive neuro-fuzzy inference system (ANFIS) model results. The predictions of LGP were observed to be in good agreement with measured data, and quite better than ANFIS and regression-based equation of scour depth at submerged pipeline.     

Wind-wave variability in a shallow tidal sea—Spectral modelling combined with neural network methods

In this paper the wind-wave variability in the tidal basins of the German Wadden Sea is modelled with combined numerical and neural-network (NN) methods. First, the wave propagation and transformation in the study area are modelled with the state-of-the-art third-generation spectral wave model SWAN. The ability of SWAN to accurately reproduce the phenomena of interest in nonstationary conditions governed by highly variable winds, water levels and currents is shown by comparisons of the modelled and measured mean wave parameters at four stations. The principal component analysis of the SWAN results is then used to reveal the dominating spatial patterns in the data and to reduce their dimensionality, thus enabling an efficient and relatively straightforward NN modelling of mean wave parameters in the whole study area. It is shown that the data produced with the approach developed in this work have statistical properties (discrete probability distributions of the mean wave parameters etc.) very close to the properties of the data obtained with SWAN, thus proving that this approach can be used as a reliable tool for wind wave simulation in coastal areas, complementary to (often computationally demanding) spectral wave models.