The goal of the MASSIMAL project is to develop new methods for mapping underwater vegetation (seagrass and macroalgae). Using a hyperspectral camera mounted on a drone, the seafloor will be imaged from 50-100 meters above the sea surface. By combining the hyperspectral images with manual sampling of the vegetation, machine learning algorithms can produce detailed maps of e.g. the different species distribution, vegetation density and physiological state.
Seagrass and macroalgae are parts of the underwater "blue forests". These form habitats for several marine species, capture large amounts of carbon, and absorb nutrients in the water. The blue forests are threatened by human activity, climate change and overgrazing by sea urchins. New tools are needed for monitoring and studying how and why these ecosystems change.
When sunlight reaches the underwater vegetation, some light is absorbed and some is reflected back towards the surface. The distribution of reflected light across different wavelengths (a “spectrum”) can carry a lot of information. The human eye is sensitive to three wavelength ranges; red, green and blue. The distribution between these three "color channels" dictates the color we perceive. A hyperspectral camera has several hundred such channels. With such a detailed measurement of the light spectrum, the hyperspectral image has a "light fingerprint" in each pixel. A computer model can compare the fingerprint with manual sampling taken at the pixel location and learn how to interpret the image.
MASSIMAL research campaigns will be carried out close to Bodø, Smøla and Larvik. At Bodø and Smøla, sea urchin grazing and commercial kelp harvesting create mosaics of bare rock and kelp vegetation. These areas are expected to generate useful test data for developing the methodology. At Bodø and Larvik different types of vegetation will be imaged several times over a 3-year period, to study how these types changes over time.