Our customer Akvaplan-niva is currently running two large, exciting projects with the mission of mapping litter along shorelines and the sea surface in Arctic Norway and Russia.
The project is called “Detecting, identifying and mapping plastic in the Arctic using robotic and digital solutions” or DIMARC for short. As such, the project will make use of autonomous unmanned robots, a Wave Glider and digital solutions that include machine learning to collect and analyze data. On top of this, project members will be developing a remote sensing methodology that will examine high resolution satellite and aerial drone imagery. Project DIMARC is being funded by the Norwegian Retailers’ Environment Fund, “the largest private environmental fund in Norway”, and aims to identify lost fishing gear on shorelines. According to an article in The Barents Observer by Frank Beuchel, Lionel Camus and Salve Dahle from Akvaplan-niva, “lines, nets, buoys, and other fishing gear account for up to 50% of all recorded beach litter” and continually threaten animals.
The project also wants to take advantage of underwater images taken with autonomous sliders. They are self-propelled vessels with mounted cameras that take continuous pictures during the day and transfer these at night to the Akvaplan-niva facilities. Hundreds of thousands of images will be analyzed with machine learning in eCognition to automatically detect rubbish. The project team is using Trimble eCognition’s machine learning tools for the analysis of both the satellite and drone images. SALT is performing the field work along the beaches in Troms and Finnmark and TerraNor is responsible for eCognition and satellite images and assists with the analysis.
The second project that Akvaplan-niva is working on is called MALINOR (Mapping marine litter in the Norwegian and Russian Arctic Seas). It is being financed by The Research Council of Norway and focuses on the use of “electrically powered aerial multicopter drones to validate novel technologies for mapping and predicting the quantity of accumulated litter but also is investigating the use of satellite imagery. The knowledge won from the project “can be useful when planning beach-cleaning activities”.
The initial results from the projects are starting to come in and the teams already see that “using artificial intelligence to analyse satellite images clearly demonstrate that lost fishing gear can be detected and identified. From drone images, several types of plastic can be quantified, down to a size of a few centimetres”.
The projects will integrate ocean current models to determine trajectories and potentials sources of sea litter as well as where it could wash ashore- “Using different model scenarios, we can simulate the drift of surface litter in the open sea, and predict where we can expect to find accumulation zones for marine litter on shorelines”. The ultimate goal is to develop a tool that can forecast where the litter will be.
It is great to see our Trimble technology used in this context and making the world a better place. I have had the pleasure of visiting Arctic Norway and it is a beautiful place that I hope will stay that way. It feels good being able to help make that possible, however remotely (excuse the pun).