Development of a neural network to retrieve chlorophyll concentrations from MERIS images in the Galician coastal waters.
Angela Mosquera Giménez(1), Marta Darriba-Estevez(1), Luis Gonzalez-Vilas(1) and Jesus Torres Palenzuela(1)
(1) University of Vigo, Campus Lagoas-Marcosende, 36310 Vigo, Spain
The Galician coastal waters are highly productive with an abundant fishing that plays an important role in the economy of the region. The phytoplankton is the basis of the trofic chain in the oceans and its abundance is a good index to estimate the productivity. The phytoplankton concentration can be estimated by using remote sensing tools through the retrieval of the chlorophyll concentration in the ocean. In spite of this estimation is relatively precise at global scale, it is not always totally accurate at local areas, so it is necessary an improvement of these techniques. In this paper, it has been done a validation of the chlorophyll concentration from MODIS images using field data of chlorophyll concentration provided by the Technological Institute for the Control of the Marine Environment of Galicia (Intecmar) in 2002. Next, chlorophyll maps derived from MODIS images were used to develop a neural network that allow to create chlorophyll maps from MERIS for the Galician area. Finally, these maps were compared to chlorophyll data retrieved from algorithms developed by Schroeder and Schaale (2005) and Doerffer et al. (2006) for case-2 waters. Results show the ability of the colour sensors to obtain chlorophyll concentrations from space and to get an idea of the productivity of the waters in the study region.
Keywords: ESA European
Space Agency - Agence spatiale europeenne,
observation de la terre, earth observation,
satellite remote sensing,
teledetection, geophysique, altimetrie, radar,
chimique atmospherique, geophysics, altimetry, radar,