Automatic extraction of fuzzy rules from MERIS data to identify sea water optically active constituent concentration

Abstract

Determining the concentrations of dissolved organic matter and suspended non-chlorophyllous particles in sea water is basic to the study of the impact of anthropic activity in coastal areas. As these concentrations affect the spectral distribution of the solar light back-scattered by the water body, their estimation can be computed by using a set of measures of average subsurface reflectances over spectral channels centered around prefixed wavelength of a MEdium Resolution Imaging Spectrometer (MERIS) on board a satellite. In this paper, the relation between the concentrations of interest and the average subsurface reflectances is modeled by a set of fuzzy rules extracted automatically from MERIS data through a two-step procedure. First, a compact initial rule base is generated by projecting onto the input variables the clusters produced by a fuzzy clustering algorithm. Then a genetic algorithm is applied to optimize the rules. Appropriate constraints maintain the semantic properties of the initial model during the genetic evolution. Results of the application of the fuzzy model are shown and discussed.