DocumentCode :
3395783
Title :
Day Ahead Ocean Swell Forecasting With Recursively Regularized Recurrent Neural Networks
Author :
Mirikitani, Derrick Takeshi
Author_Institution :
Univ. of London, New Cross
fYear :
2007
fDate :
18-21 June 2007
Firstpage :
1
Lastpage :
4
Abstract :
Day ahead forecasts of ocean swell amplitude at fixed deep water observation platforms could provide critical decision making information for a large number of costal ocean activities. Currently the hourly measurements of wave height data provided from fixed deep water observation platforms tend to be irregular, and contaminated with noise. This data quality issue has been problematic for previous approaches to wave amplitude forecasting. This paper proposes a solution to the data quality issue through recursively regularized weight estimation for a recurrent multilayer perceptron neural network. Experimentation has shown that the proposed model out preforms standard feed forward models as well as extended Kalman filter trained recurrent neural models in a next day forecasting task.
Keywords :
Kalman filters; geophysics computing; multilayer perceptrons; ocean waves; oceanographic techniques; coastal ocean activities; data quality; day ahead ocean swell forecasting; decision making information; deep water observation platform; extended Kalman filter; feedforward model; multilayer perceptron; ocean waves; recursively regularized recurrent neural networks; recursively regularized weight estimation; Current measurement; Decision making; Noise measurement; Oceans; Pollution measurement; Predictive models; Recurrent neural networks; Recursive estimation; Sea measurements; Water pollution;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
OCEANS 2007 - Europe
Conference_Location :
Aberdeen
Print_ISBN :
978-1-4244-0635-7
Electronic_ISBN :
978-1-4244-0635-7
Type :
conf
DOI :
10.1109/OCEANSE.2007.4302449
Filename :
4302449
Link To Document :
بازگشت