Ongoing projects

SuperIce

High resolution of sea-ice thickness is instrumental to provide better seasonal forecasts over the Arctic and to better understand energy fluxes between ocean and atmosphere. The "SuperIce" project will leverage artificial intelligence techniques and physical simulation of the sea-ice model neXtSIM to enhance the spatial resolution of current satellite observations of the Arctic sea ice.

NorHAB-ML

Harmful algae blooms happen when specific algae produce toxins. They have impacts on both human health and on the economy of aquacultures. The project “Machine learning for prediction and projection of harmful algae blooms hazards” aims to enhance the accuracy of predicting harmful algae blooms (HABs). In particular, the project will develop a new algorithm for improving the accuracy of remote sensing on the Norwegian shelf and using coastal modelling products. NorHAB-ML aims to predict HABs harmful for aquaculture accurately, as well as high biomass bloom that can be harmful to fisheries. The geographic focus lies on the Norwegian coastal and shelf waters.

SCOPE

Carbon in the sea is of great importance for the carbon cycle and thus the climate. How the amount and distribution of carbon changes over time is something that the researchers in the project "Satellite-based observations of Carbon in the Ocean: Pools, fluxes and Exchanges" study with the help of satellites.

APASIP

In order to produce automated ice maps over the entire Arctic region, the researchers in the project "Automatic pan-Arctic Sea Ice Product from high-resolution satellite data" are developing automatic algorithms to retrieve sea ice concentration and ice type from satellite data using artificial intelligence.