Inverse modeling to derive wind parameters from wave measurements

Charhate, Shrikant; Deo, M. C.; Londhe, Shreenivas

doi:10.1016/j.apor.2008.08.002

Cited by 14 publications

(9 citation statements)

References 18 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They suggest the usefulness of the programbased GP as an inverse modeling technique. A comparison of the present results with those of Charhate et al (2008), who used an equation-based GP and ANN, shows that, in general, the values of RMSE and MAE realized in this work are lower indicating a better performance, but the value of R is also low indicating lack of linear co-variation in between the predicted and the actual values. Due to its purely nonlinear nature and high flexibility, the program-based format of GP enables us to carry out the inverse modeling most efficiently.…”

Section: Resultsmentioning

confidence: 44%

See 1 more Smart Citation

Alternative data-driven methods to estimate wind from waves by inverse modeling

Daga

Deo

2008

Nat Hazards

View full text Add to dashboard Cite

An attempt is made to derive wind speed from wave measurements by carrying out an inverse modeling. This requirement arises out of difficulties occasionally encountered in collecting wave and wind data simultaneously. The wind speed at every 3-h interval is worked out from corresponding simultaneous measurements of significant wave height and average wave periods with the help of alternative data-driven methods such as program-based genetic programming, model trees, and locally weighted projection regression. Five different wave buoy locations in Arabian Sea, representing nearshore and offshore as well as shallow and deep water conditions, are considered. The duration of observations ranged from 15 months to 29 months for different sites. The testing performance of calibrated models has been evaluated with the help of eight alternative error statistics, and the best model for all locations is determined by averaging out the error measures into a single evaluation index. All the three methods satisfactorily estimated the wind speed from known wave parameters through inverse modeling. The genetic programming is found to be the most suitable tool in majority of the cases.

show abstract

Section: Resultsmentioning

confidence: 44%

“…Charhate et al (2008) attempted such an inverse modeling with the help of artificial neural network (ANN) and an equation-based genetic programming (GP). This study explores suitability of additional and more recent data-driven tools of locally weighted projection regression (LWPR), model tree (MT), and program-based GP.…”

mentioning

confidence: 99%

Alternative data-driven methods to estimate wind from waves by inverse modeling

Daga

Deo

2008

Nat Hazards

View full text Add to dashboard Cite

show abstract

“…It was found that GP rivaled ANN predictions at all the cases and even bettered it particularly for open sea location. The results for prediction of wind speed and wind direction together were better when training of GP and ANN models was done on the basis of splitting of wind vector into two components along orthogonal directions although a separate model for wind speed alone was better (as shown by [22]). In general long interval predictions were less accurate compared to short interval predictions for both the techniques.…”

Section: Applications In Ocean Engineeringmentioning

confidence: 95%

“…Estimation of wind speed and wind direction using the significant wave height, zero cross wave period, average wave period and the soft tools of ANN and GP was carried out at 5 locations around Indian coastline [22]. The paper has three folds in that in the first attempt both ANN and GP were tried for estimating the wind speed in which GP was found better and therefore in the second fold GP was only used to determine both wind speed and direction by calibrating the model by splitting of wind vector into two components.…”

Section: Applications In Ocean Engineeringmentioning

confidence: 99%

Genetic Programming: A Novel Computing Approach in Modeling Water Flows

Londhe¹,

Dixit²

2012

Genetic Programming - New Approaches and Successful Applications

View full text Add to dashboard Cite

“…are very complex three dimensional phenomena. Researchers have found traditional numerical and statistical methods to be less accurate, for ocean waves [3] and/or wind prediction [4] [5]. Several types of ANN are found to be more accurate in comparison with these methods.…”

Section: Gp In Ocean Engineegringmentioning

confidence: 97%

‘Application of Genetic Programming for estimation of ocean wave heights’

Nitsure¹,

Londhe²,

Khare

2009

2009 World Congress on Nature &Amp; Biologically Inspired Computing (NaBIC)

View full text Add to dashboard Cite

In the recent past, researchers and investigators in Civil Engineering have increasingly used soft computing tools to yield better results than the traditional numerical and statistical techniques in modelling water flows. Artificial Neural Network (ANN) is one such technique which has attained a strong foothold in the field of Hydrology and Ocean Engineering particularly for forecasting stream flows, wave forecasting, water level forecasting etc. In the last few years another efficient and useful soft computing tool, 'Genetic Programming' (GP) has caught attention of the researchers for ocean engineering computations. GP is found to be a promising tool for prediction of oceanic parameters. This paper outlines the basic principles of GP Modelling and makes an attempt to estimate an important oceanic parameter -Significant Wave Height (SWH) using the wind information. Wave and wind measurements taken by moored ocean buoys are used to develop the GP models. The GP based estimations are found to have a reasonable accuracy in estimation of significant wave heights as evident from wave plots and accompanying high values of correlation coefficient.

show abstract

Inverse modeling to derive wind parameters from wave measurements

Cited by 14 publications

References 18 publications

Alternative data-driven methods to estimate wind from waves by inverse modeling

Alternative data-driven methods to estimate wind from waves by inverse modeling

Genetic Programming: A Novel Computing Approach in Modeling Water Flows

‘Application of Genetic Programming for estimation of ocean wave heights’

Contact Info

Product

Resources

About

Inverse modeling to derive wind parameters from wave measurements

Cited by 14 publications

References 18 publications

Alternative data-driven methods to estimate wind from waves by inverse modeling

Alternative data-driven methods to estimate wind from waves by inverse modeling

Genetic Programming: A Novel Computing Approach in Modeling Water Flows

&#x2018;Application of Genetic Programming for estimation of ocean wave heights&#x2019;

Contact Info

Product

Resources

About

‘Application of Genetic Programming for estimation of ocean wave heights’