| Title: | INTERPOLATION OF TIME SERIES OF SEA STATE VARIABLES USING NEURAL NETWORKS |
| DOI No: | 10.1142/9789812701916_0078 |
| Source: | COASTAL ENGINEERING 2004 (pp 985-996)
|
| Author(s): | JOSEP R. MEDINA
Lab. Ports and Coasts, Dept. of Transportation, Universidad Politécnica de Valencia, Camino de Vera s/n, 46022 Valencia, Spain
OBDULIO SERRANO-HIDALGO
Puertos del Estado, Avda. del Partenón, 10 28042 Madrid, Spain
|
| Abstract: | A methodology to reconstruct time series of sea state variables recorded from a wave measurement network is presented. This new methodology is based on the use of pruned neural network models optimized by evolutionary strategies and the utility function concept. The method is applied to reconstruct the time series of the significant wave height of the waverider buoy at Bilbao on the northern coast of Spain using the wave records taken by a directional buoy and a waverider buoy also located on the northern coast of Spain. The method may be used to transfer information among wave measurement points and hindcasting points, to monitor quality and recover missing data from wave recording networks. |
| Full Text: | View full text in PDF format (796KB) |
| TOC: | Back to Table of Contents |
|
|
