Record Details

Neural networks for wave forecasting

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Neural networks for wave forecasting
 
Creator DEO, MC
JHA, A
CHAPHEKAR, AS
RAVIKANT, K
 
Subject waves
sampling
forecasting
personnel training
 
Description The physical process of generation of waves by wind is extremely complex, uncertain and not yet fully understood. Despite a variety of deterministic models presented to predict the heights and periods of waves from the characteristics of the generating wind, a large scope still exists to improve on the existing models or to provide alternatives to them. This paper explores the possibility of employing the relatively recent technique of neural networks for this purpose. A simple 3-layered feed forward type of network is developed to obtain the output of significant wave heights and average wave periods from the input of generating wind speeds. The network is trained with different algorithms and using three sets of data. The results show that an appropriately trained network could provide satisfactory results in open wider areas, in deep water and also when the sampling and prediction interval is large, such as a week. A proper choice of training patterns is found to be crucial in achieving adequate training.
 
Publisher Elsevier
 
Date 2009-04-28T05:23:27Z
2011-12-08T06:34:58Z
2011-12-26T13:01:40Z
2011-12-27T05:46:00Z
2009-04-28T05:23:27Z
2011-12-08T06:34:58Z
2011-12-26T13:01:40Z
2011-12-27T05:46:00Z
2001
 
Type Article
 
Identifier Ocean Engineering 28(7), 889-898
0029-8018
10.1016/S0029-8018(00)00027-5
http://hdl.handle.net/10054/1248
http://dspace.library.iitb.ac.in/xmlui/handle/10054/1248
 
Language en