Development of a remote sensing algorithm for Cyanobacterial Phycocyanin pigment in the Baltic Sea using Neural Network approach

Abstract

Water quality monitoring in the Baltic Sea is of high ecological importance for all its neighbouring countries. Satellite remote sensing allows frequent observations of wide areas of the Baltic Sea with special focus on its two seasonal algae blooms. For a better monitoring of the Cyanobacteria dominated, summer blooms, an algorithm is needed which takes into account the special optical properties of these blue-green algae. Chlorophyll-a standard algorithms usually fail in a correct recognition of these occurrences. To significantly improve the forecast regarding the Cyanobacteria blooms, the Marine Remote Sensing group of DLR has started the development of a model based inversion algorithm that includes a four component bio-optical water model for Case2 waters, which extends the commonly calculated parameter set Chlorophyll, Suspended Matter and Gelbstoff with an additional parameter for the estimation of Phycocyanin absorption. The inversion of satellite remote sensing data is based on an artificial Neural Network technique. The specially developed Neural Network is trained with a comprehensive dataset of simulated reflectance values according to the wavelengths of MERIS VIS/NIR bands. The Poster will demonstrate the theoretical basis and development of the algorithm together with first results from MERIS scenes in the Baltic Sea. Furthermore it will compare the Phycocyanin-algorithm to the standard DLR PCI algorithm based on the related inversion technique “Principal Component Analysis” and discusses the different inversion approaches.