The Experts below are selected from a list of 17913 Experts worldwide ranked by ideXlab platform

Sancho Salcedosanz - One of the best experts on this subject based on the ideXlab platform.

  • Significant Wave Height and energy flux estimation with a genetic fuzzy system for regression
    Ocean Engineering, 2018
    Co-Authors: Laura Cornejobueno, Pablo Rodriguezmier, Manuel Mucientes, J C Nietoborge, Sancho Salcedosanz
    Abstract:

    Abstract This paper proposes a regression Genetic Fuzzy System (GFS, FRULER) for a problem of sea Wave parameters estimation from neighbor buoys, with application on Wave energy systems. FRULER is a recently proposed, three-staged algorithm that combines an instance selection method for regression, a multigranularity fuzzy discretization of the input variables and an evolutionary algorithm to generate accurate and simple Takagi-Sugeno-Kant (TSK) fuzzy rules. We have applied FRULER to a real problem of Significant Wave Height and energy flux prediction in one buoy of the West Coast of the USA (California), from values of other two neighbor buoys. In the case of the Significant Wave Height, FRULER is able to obtain a robust prediction with only three rules, which in addition are fully interpretable, since they clearly separate swell situations from wind-sea in the prediction. In both cases, the variables used in the Significant Wave prediction are completely different and can be identified as relevant for the specific case (swell or wind-sea). In the case of the energy flux prediction, the interpretation of the rules provided by FRULER is more difficult, since eight rules are necessary to obtain the prediction. Even in this case, several rules can be clearly classified as swell predictors, and the rest of the rules describe local wind situation of Waves. This study shows that the GFSs are useful tools to obtain robust and interpretable predictions in ocean Wave parameter estimation problems.

  • Significant Wave Height and energy flux prediction for marine energy applications a grouping genetic algorithm extreme learning machine approach
    Renewable Energy, 2016
    Co-Authors: Laura Cornejobueno, J C Nietoborge, P Garciadiaz, G Rodriguez, Sancho Salcedosanz
    Abstract:

    This paper proposes a novel hybrid approach for feature selection in two different relevant problems for marine energy applications: Significant Wave Height (Hm0) and Wave energy flux (P) prediction. Specifically, a hybrid Grouping Genetic Algorithm – Extreme Learning Machine approach (GGA-ELM) is proposed, in such a way that the GGA searches for several subsets of features, and the ELM provides the fitness of the algorithm, by means of its accuracy on Hm0 or P prediction. Since the GGA was specifically created for problems involving a number of groups, the proposed algorithm may be used to evolve different groups of features in parallel, which may improve the performance of the predictions obtained. After the feature selection process with the GGA-ELM, the final results are given by an ELM and also by a Support Vector Machine, both working on the best GGA groups obtained. The performance of the proposed system has been tested in a real problem of Hm0 and P prediction at the Western coast of the USA, obtaining good results.

  • accurate estimation of Significant Wave Height with support vector regression algorithms and marine radar images
    Coastal Engineering, 2016
    Co-Authors: Laura Cornejobueno, José Carlos Nieto Borge, Katrin Hessner, Enrique Alexandre, Sancho Salcedosanz
    Abstract:

    Abstract Significant Wave Height ( H s ) is a basic parameter in Wave characterization, important for different problems in marine activities such as the design and management of vessels, marine structures, and Wave energy converters. H s is usually estimated using in-situ sensors, mainly buoys, that record time series of Wave elevation information. In this paper we propose a method for H s estimation based on a Support Vector Regression algorithm over non-coherent X-band marine radar images. Results for three different platforms (Fino 1, Ekofisk and Glas Dowr) at different locations of the North Sea and South Africa are presented, showing that the SVR obtains a better result than the existing standard method in H s prediction, within different sea states observed at each location.

  • a hybrid genetic algorithm extreme learning machine approach for accurate Significant Wave Height reconstruction
    Ocean Modelling, 2015
    Co-Authors: Enrique Alexandre, J C Nietoborge, L Cuadra, G Candilgarcia, M Del Pino, Sancho Salcedosanz
    Abstract:

    Abstract Wave parameters computed from time series measured by buoys (Significant Wave Height Hs, mean Wave period, etc.) play a key role in coastal engineering and in the design and operation of Wave energy converters. Storms or navigation accidents can make measuring buoys break down, leading to missing data gaps. In this paper we tackle the problem of locally reconstructing Hs at out-of-operation buoys by using Wave parameters from nearby buoys, based on the spatial correlation among values at neighboring buoy locations. The novelty of our approach for its potential application to problems in coastal engineering is twofold. On one hand, we propose a genetic algorithm hybridized with an extreme learning machine that selects, among the available Wave parameters from the nearby buoys, a subset F n S P with nSP parameters that minimizes the Hs reconstruction error. On the other hand, we evaluate to what extent the selected parameters in subset F n S P are good enough in assisting other machine learning (ML) regressors (extreme learning machines, support vector machines and gaussian process regression) to reconstruct Hs. The results show that all the ML method explored achieve a good Hs reconstruction in the two different locations studied (Caribbean Sea and West Atlantic).

Guedes C Soares - One of the best experts on this subject based on the ideXlab platform.

  • bivariate distributions of Significant Wave Height and mean Wave period of combined sea states
    Ocean Engineering, 2015
    Co-Authors: C Lucas, Guedes C Soares
    Abstract:

    Abstract This work presents the results of the fit of three bivariate models to twelve years of Significant Wave Height and mean zero-crossing period data of swell, wind sea components, and combined sea states from Australia. The Conditional Modelling Approach defines the joint distribution from a marginal distribution of Significant Wave Height and a set of distributions of mean zero-crossing period conditional on Significant Wave Height. The second model fits the Plackett model to the data, and the last one applies the Box–Cox transformations to the data with the aim of making it approximately normal to fit a bivariate normal distribution to the transformed data. The conditional model with a lognormal distribution for the Significant Wave Height and lognormal distributions for the zero-crossing period gave the best fit for the total sea states and for the wind component. In case of the swell component the conditional model with a Weibull distribution to the Significant Wave Height and a lognormal distribution to the mean zero-crossing period gave a relatively close fit to the data.

  • on the distribution of Significant Wave Height and associated peak periods
    Coastal Engineering, 2015
    Co-Authors: G. Muraleedharan, C Lucas, Guedes C Soares, D Martins, P. G. Kurup
    Abstract:

    Abstract This study uses 21 years (1958–1978) Significant Wave Height and associated peak periods off Azores in the North Atlantic Ocean, extracted from 44 years HIPOCAS database. Empirical average conditional exceedances of peak periods are executed. Plausibility of judging the distribution of the peak periods by modelling average conditional exceedance of peak periods by Erlang, generalized Pareto and three-parameter Weibull models is investigated and we also assessed certain peak period statistics predicted by the models. 50 year gamma peak period quantiles are reasonably accurate when compared with 44 year peak period quantiles (HIPOCAS). Erlang and generalized Pareto estimate of mean peak period are reasonable; whereas all the three models fairly evaluate the average of the one-third the highest peak periods. Weibull model derived parametric relation gauged the average of the one-tenth the highest peak periods. A general statistical formula is suggested for estimation of Significant Wave period. Average of one-third the highest peak period estimates by the parametric relation derived from generalized Pareto distribution using the general formula for Significant Wave period, provides reliably precise results. Significant Wave period to mean Wave period observational ratio of 1.2 is appropriately interpreted for both computed and estimated ratios of mean peak period of one-third the highest Significant Wave Heights to mean peak periods.

  • trivariate maximum entropy distribution of Significant Wave Height wind speed and relative direction
    Renewable Energy, 2015
    Co-Authors: Sheng Dong, Xue Li, Guedes C Soares
    Abstract:

    A trivariate maximum entropy distribution of Significant Wave Height, wind speed and the relative direction is proposed here. In this joint distribution, all the marginal variables follow modified maximum entropy distributions, and they are combined by a correlation coefficient matrix based on the Nataf transformation. The methods of single extreme factors and of conditional probability are presented for the joint design of trivariate random variables. The corresponding sampling data about Significant Wave Heights, wind speeds and the relative directions from a location in the North Atlantic is applied for statistical analysis, and the results show that the trivariate maximum entropy distribution is sufficiently good to fit the data, and method of conditional probability can reduce the design values efficiently.

  • parameter estimation of the maximum entropy distribution of Significant Wave Height
    Journal of Coastal Research, 2013
    Co-Authors: Sheng Dong, Shanshan Tao, Shuhe Lei, Guedes C Soares
    Abstract:

    Dong, S.; Tao, S.; Lei, S., and Guedes Soares, C., 2013. Parameter estimation of the maximum entropy distribution of Significant Wave Height. Journal of Coastal Research, 29(3), 597–604. Coconut Creek (Florida), ISSN 0749-0208. This paper compares the estimation of the four parameters of the maximum entropy distribution by different methods and applies them in two test cases with Significantly different characteristics of variability. The moment method and the maximum likelihood method for the maximum entropy distribution with four parameters are formulated in the paper. These methods are compared with the moment method for the maximum entropy distribution with three parameters and an empirical curve-fitting method, both of which have been used earlier. These four estimation methods are applied to two test cases. One consists of hindcast Wave Heights at Weizhoudao hydrological station in the northern area of the South China Sea, which is subject to typhoon type of events. The other data set is hindcast Wave Heights at a location in the North Atlantic Ocean, which is subject to frequent storm weather. The maximum likelihood and the empirical methods appear to provide the most consistent results.

  • application of the r largest order statistics for long term predictions of Significant Wave Height
    Coastal Engineering, 2004
    Co-Authors: Guedes C Soares, Manuel G. Scotto
    Abstract:

    This paper deals with the extremal properties of time series of Significant Wave Height modelled by means of extreme value techniques. The limiting joint generalized extreme value (GEV) distribution for the r largest-order statistic model is used to estimate return values of Significant Wave Height. A method based on filtering the observations to extract the r largest independent values is adopted. A case study of the northern North Sea data set is presented, and the results are compared with those obtained from the Annual Maxima (AM) method.

Enrique Alexandre - One of the best experts on this subject based on the ideXlab platform.

  • accurate estimation of Significant Wave Height with support vector regression algorithms and marine radar images
    Coastal Engineering, 2016
    Co-Authors: Laura Cornejobueno, José Carlos Nieto Borge, Katrin Hessner, Enrique Alexandre, Sancho Salcedosanz
    Abstract:

    Abstract Significant Wave Height ( H s ) is a basic parameter in Wave characterization, important for different problems in marine activities such as the design and management of vessels, marine structures, and Wave energy converters. H s is usually estimated using in-situ sensors, mainly buoys, that record time series of Wave elevation information. In this paper we propose a method for H s estimation based on a Support Vector Regression algorithm over non-coherent X-band marine radar images. Results for three different platforms (Fino 1, Ekofisk and Glas Dowr) at different locations of the North Sea and South Africa are presented, showing that the SVR obtains a better result than the existing standard method in H s prediction, within different sea states observed at each location.

  • a hybrid genetic algorithm extreme learning machine approach for accurate Significant Wave Height reconstruction
    Ocean Modelling, 2015
    Co-Authors: Enrique Alexandre, J C Nietoborge, L Cuadra, G Candilgarcia, M Del Pino, Sancho Salcedosanz
    Abstract:

    Abstract Wave parameters computed from time series measured by buoys (Significant Wave Height Hs, mean Wave period, etc.) play a key role in coastal engineering and in the design and operation of Wave energy converters. Storms or navigation accidents can make measuring buoys break down, leading to missing data gaps. In this paper we tackle the problem of locally reconstructing Hs at out-of-operation buoys by using Wave parameters from nearby buoys, based on the spatial correlation among values at neighboring buoy locations. The novelty of our approach for its potential application to problems in coastal engineering is twofold. On one hand, we propose a genetic algorithm hybridized with an extreme learning machine that selects, among the available Wave parameters from the nearby buoys, a subset F n S P with nSP parameters that minimizes the Hs reconstruction error. On the other hand, we evaluate to what extent the selected parameters in subset F n S P are good enough in assisting other machine learning (ML) regressors (extreme learning machines, support vector machines and gaussian process regression) to reconstruct Hs. The results show that all the ML method explored achieve a good Hs reconstruction in the two different locations studied (Caribbean Sea and West Atlantic).

Laura Cornejobueno - One of the best experts on this subject based on the ideXlab platform.

  • Significant Wave Height and energy flux estimation with a genetic fuzzy system for regression
    Ocean Engineering, 2018
    Co-Authors: Laura Cornejobueno, Pablo Rodriguezmier, Manuel Mucientes, J C Nietoborge, Sancho Salcedosanz
    Abstract:

    Abstract This paper proposes a regression Genetic Fuzzy System (GFS, FRULER) for a problem of sea Wave parameters estimation from neighbor buoys, with application on Wave energy systems. FRULER is a recently proposed, three-staged algorithm that combines an instance selection method for regression, a multigranularity fuzzy discretization of the input variables and an evolutionary algorithm to generate accurate and simple Takagi-Sugeno-Kant (TSK) fuzzy rules. We have applied FRULER to a real problem of Significant Wave Height and energy flux prediction in one buoy of the West Coast of the USA (California), from values of other two neighbor buoys. In the case of the Significant Wave Height, FRULER is able to obtain a robust prediction with only three rules, which in addition are fully interpretable, since they clearly separate swell situations from wind-sea in the prediction. In both cases, the variables used in the Significant Wave prediction are completely different and can be identified as relevant for the specific case (swell or wind-sea). In the case of the energy flux prediction, the interpretation of the rules provided by FRULER is more difficult, since eight rules are necessary to obtain the prediction. Even in this case, several rules can be clearly classified as swell predictors, and the rest of the rules describe local wind situation of Waves. This study shows that the GFSs are useful tools to obtain robust and interpretable predictions in ocean Wave parameter estimation problems.

  • Significant Wave Height and energy flux prediction for marine energy applications a grouping genetic algorithm extreme learning machine approach
    Renewable Energy, 2016
    Co-Authors: Laura Cornejobueno, J C Nietoborge, P Garciadiaz, G Rodriguez, Sancho Salcedosanz
    Abstract:

    This paper proposes a novel hybrid approach for feature selection in two different relevant problems for marine energy applications: Significant Wave Height (Hm0) and Wave energy flux (P) prediction. Specifically, a hybrid Grouping Genetic Algorithm – Extreme Learning Machine approach (GGA-ELM) is proposed, in such a way that the GGA searches for several subsets of features, and the ELM provides the fitness of the algorithm, by means of its accuracy on Hm0 or P prediction. Since the GGA was specifically created for problems involving a number of groups, the proposed algorithm may be used to evolve different groups of features in parallel, which may improve the performance of the predictions obtained. After the feature selection process with the GGA-ELM, the final results are given by an ELM and also by a Support Vector Machine, both working on the best GGA groups obtained. The performance of the proposed system has been tested in a real problem of Hm0 and P prediction at the Western coast of the USA, obtaining good results.

  • accurate estimation of Significant Wave Height with support vector regression algorithms and marine radar images
    Coastal Engineering, 2016
    Co-Authors: Laura Cornejobueno, José Carlos Nieto Borge, Katrin Hessner, Enrique Alexandre, Sancho Salcedosanz
    Abstract:

    Abstract Significant Wave Height ( H s ) is a basic parameter in Wave characterization, important for different problems in marine activities such as the design and management of vessels, marine structures, and Wave energy converters. H s is usually estimated using in-situ sensors, mainly buoys, that record time series of Wave elevation information. In this paper we propose a method for H s estimation based on a Support Vector Regression algorithm over non-coherent X-band marine radar images. Results for three different platforms (Fino 1, Ekofisk and Glas Dowr) at different locations of the North Sea and South Africa are presented, showing that the SVR obtains a better result than the existing standard method in H s prediction, within different sea states observed at each location.

He Wang - One of the best experts on this subject based on the ideXlab platform.

  • empirical algorithm for Significant Wave Height retrieval from Wave mode data provided by the chinese satellite gaofen 3
    Remote Sensing, 2018
    Co-Authors: He Wang, Jianhua Zhu, Jingsong Yang, Jing Wang, Lin Ren, Xinzhe Yuan, Chunhua Xie
    Abstract:

    Gaofen-3 (GF-3), the first Chinese civil C-band synthetic aperture radar (SAR), was successfully launched by the China Academy of Space Technology on 10 August 2016. Among its 12 imaging modes, Wave mode is designed to monitor the ocean surface Waves over the open ocean. An empirical retrieval algorithm of Significant Wave Height (SWH), termed Quad-Polarized C-band Wave algorithm for GF-3 Wave mode (QPCWave_GF3), is developed for quad-polarized SAR measurements from GF-3 in Wave mode. QPCWave_GF3 model is built using six SAR image and spectrum related parameters. Based on a total of 2576 WaveWatch III (WW3) and GF-3 Wave mode match-ups, 12 empirical coefficients of the model are determined for 6 incidence angle modes. The validation of the QPCWave_GF3 model is performed through comparisons against independent WW3 modelling hindcasts, and observations from altimeters and buoys from January to October in 2017. The assessment shows a good agreement with root mean square error from 0.5 m to 0.6 m, and scatter index around 20%. In particular, applications of the QPCWave_GF3 model in SWH estimation for two storm cases from GF-3 data in Wave mode and Quad-Polarization Strip I mode are presented respectively. Results indicate that the proposed algorithm is suitable for SWH estimation from GF-3 Wave mode and is promising for other similar data.

  • validation of the Significant Wave Height product of hy 2 altimeter
    Remote Sensing, 2017
    Co-Authors: Chuntao Chen, Mingsen Lin, He Wang, Jianhua Zhu, Yili Zhao, Jin Wang
    Abstract:

    HY-2 was launched by China on August 2011, which has provided continuous Wave Height measurements to monitor ocean dynamic environments for more than 5 years. Before using these data, however, the measurements need to be validated. Based on the in situ buoy data from the National Data Buoy Center (NDBC) and the Jason-2 altimeter data, the HY-2 Ku-band Significant Wave Height (SWH) measurements were validated. The comparisons showed that a linear regression with NDBC measurements can be used to improve the accuracy of the HY-2 SWH measurements. Compared with the NDBC SWH data, the validation results of the HY-2 SWH data show an RMS (root mean square) of 0.33 m, which is similar to that of the Jason-1 and Jason-2 data; the RMS of the HY-2 SWH is 0.30 m, which, corrected via linear regression, is similar to that of the corrected Jason-1 and Jason-2 data (0.27 m and 0.23 m, respectively). Therefore, the accuracy of the HY-2 SWH products is close to that of the Jason-1/2 SWH data.

  • the validation of the Significant Wave Height product of hy 2 altimeter primary results
    Acta Oceanologica Sinica, 2013
    Co-Authors: Chuntao Chen, Mingsen Lin, He Wang, Jianhua Zhu, Youguang Zhang, Yili Zhao, Xiaoqi Huang, Hailong Peng
    Abstract:

    The HY-2 satellite was successfully launched on 16 August 2011. The HY-2 Significant Wave Height (SWH) is validated by the data from the South China Sea (SCS) field experiment, National Data Buoy Center (NDBC) buoys and Jason-1/2 altimeters, and is corrected using a linear regression with in-situ measurements. Compared with NDBC SWH, the HY-2 SWH show a RMS of 0.36 m, which is similar to Jason-1 and Jason-2 SWH with the RMS of 0.35mand 0.37mrespectively; the RMS of corrected HY-2 SWH is 0.27 m, similar to 0.27 m and 0.23 m of corrected Jason-1 and Jason-2 SWH. Therefore the accuracy of HY-2 SWH products is close to that of Jason-1/2 SWH, and the linear regression function derived can improve the accuracy of HY-2 SWH products.