Seaweed Habitats on the Shore: Characterization through Hyperspectral UAV Imagery and Field Sampling

Intertidal macroalgal habitats are major components of temperate coastal ecosystems. Their distribution was studied using field sampling and hyperspectral remote mapping on a rocky shore Porspoder (western Brittany, France). Covers both dominating macroalgae the sessile fauna were characterized in situ at low tide 24 spots, according to four bathymetric levels. A zone ca. 17,000 m2 drone equipped with camera. Macroalgae identified by image processing two classification methods assess representativeness spectral classes. Finally, comparison imaging data conducted. Seven seaweed classes distinguished pictures, including five different species Fucales. The maximum likelihood (MLC) angle mapper (SAM) trained image-derived spectra. MLC more accurate classify main (Overall Accuracy (OA) 95.1%) than SAM (OA 87.9%) site scale. However, points scale, results depend level. This study evidenced efficiency accuracy sensing evaluate intertidal potential for combined field/remote approach ecological state communities.