Hyperspectral classification approaches for intertidal macroalgae habitat mapping: a case study in Heligoland

Analysis of coastal marine algae communities enables to adequately estimate the state of marine environment and provides evidence for environmental changes. remote sensing provides a tool for mapping macroalgal habitats if the algal are spectrally resolvable. We compared the performance of three classification to determine the distribution of macroalgae communities in the rocky intertidal of Heligoland (Germany) using airborne hyperspectral (AISAeagle) data. The classification of two supervised approaches (maximum likelihood classifier and spectral angle ) are compared with an approach combining k-Means classification of derivative . We identified regions of different slopes between main pigment absorption of macroalgae and classified the resulting slope bands. The maximum likelihood gained best results (Cohan’s kappa = 0.81), but the new approach turned out as effective possibility to identify the dominating macroalgae species with sufficient (Cohan’s kappa = 0.77), even in the heterogeneous and patchy coverage of the area.