Title :
Analysis of the Senegalo-Mauritanian upwelling by processing satellite remote sensing observations with topological maps.
Author :
Sawadogo, S. ; Brajard, J. ; Niang, A. ; Lathuiliere, C. ; Crépon, M. ; Thiria, S.
Author_Institution :
Ecole Polytech. de Thies, Univ. de Thies, Thies, Senegal
Abstract :
The Senegalo-Mauritanian upwelling is a very productive upwelling occurring along the West coast of Africa. Its seasonal and inter-annual variability south of 20degN was analyzed by processing ocean color data and sea surface temperature provided by satellite sensors. We used a classification methodology consisting in a neural network topological map and a hierarchical ascendant classification. Four classes can explain most of the variability of the upwelling. Its extent is maximum in February-March, minimum in August September. The variability is linked to that of the wind. The classes can be considered as statistical indices allowing us to investigate the variability of the upwelling.
Keywords :
neural nets; ocean temperature; oceanographic techniques; remote sensing; Senegalo-Mauritanian upwelling; hierarchical ascendant classification; neural network topological map; ocean color data; satellite remote sensing; sea surface temperature; statistical indices; Africa; Color; Neural networks; Ocean temperature; Remote sensing; Satellites; Sea measurements; Sea surface; Surface topography; Temperature sensors;
Conference_Titel :
Neural Networks, 2009. IJCNN 2009. International Joint Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
978-1-4244-3548-7
Electronic_ISBN :
1098-7576
DOI :
10.1109/IJCNN.2009.5178623