KELPMAP – Upscaling drone-based maps using satellite images shows promise

Helgelandskysten is one of Norway’s most beautiful coastlines, holding World Heritage Status (UNESCO) and ‘Outstanding Universal Value’.

It has thousands of small islands, islets and skerries, mountains, fjords and a great deal of life above and under the water. It must be managed well to safeguard the valuable cultural history and ecosystems. Kelp forests are a key part of the ecosystems in this area. 

Helgelandskysten (above) and kelp forest (below). Photo from H. Gundersen, NIVA.

KELPMAP (NIVA and NR) is investigating if it is possible to map kelp forests using drones, and then upscale the information collected using satellite data. The project is financed by Miljødirektoratet and Norsk Romsenter, 2022 – 2024 (NIVA field report).  

SeaBee is being used to map the benthic habitats. Both rotor drones and fixed-wing drones with RGB and MSI sensors (SeaBee equipment) are used to collect the data which is uploaded to the SeaBee Data Pipeline.

Ground truth data are also sampled in the field, for training of algorithms and validation of data products. The drone images are then annotated, guided by the ground truth, to show which parts of the drone images are kelp forest and other species.

SeaBee has defined 42 different habitat classes in three analysis levels (shared on GitHub), many of them compatible with the NiN classifications. These results are analysed, quality controlled and presented as high-resolution maps of habitat classes for the whole study area – which show the kelp forests and other species. 

Another new aspect is upscaling these results to cover a larger area using satellite imagery (using Sentinel-2 with 10m resolution and PANDA with 2m resolution). The upscaling showed promising results, important for environmental management on larger scales.  

The results will be delivered to Miljødirektoratet this year to be used as a tool for measuring progress and implementation of existing national policies and management plans.

Miljødirektoratet are pleased with progress so far, and with the results that were received. These advances also have potential applications in other national and European research, not the least the Kunming-Montreal Global Nature Agreement (CBD). 

The drone view of Helgelandskysten during field work. Photo from G. Medyan, NIVA.

SeaBee shines at GeoHab 2024

SeaBee Research Infrastructure team members proudly presented at the international GeoHab Conference 2024 (6th – 10th May) in Arendal, Norway.

SeaBee contributed four presentations, and was mentioned in the keynote by Terje Thorsnes (NGU) on marine habitat mapping programs in Norway.    

Kristina Kvile (NIVA) presented the latest news on drones, updated methods and protocols for marine habitat mapping. She shared how habitats are classified and how drones can be used to identify marine vegetation at various hierarchical levels ranging from habitat classes to species level using high-resolution multispectral sensors and AI classification tools.

Collecting direct observations from the ground and boat (above) and the possible resolutions of collected data. Photos from K. Kvile (NIVA).

Håvard Løvas (NTNU) told the audience about hyperspectral solutions for detailed identification of shallow-water species and objects with distinct optical ‘fingerprints’.

Hyperspectral imaging is a novel, powerful tool for coastal drone mapping. You can characterise water quality, classify bottom substrates, and identify simple species based on their optical characteristics. However, interpretating images of underwater features and species is challenging, thus careful, systematic data handling and calibration routines are essential to achieve good results.  

Øyvind Tangen Ødegaard (NIVA) described how to tame a surface drone (Otter Pro USV), and how its sophisticated on-board optical  and acoustic sensors can support the information from flying drones to produce even better maps and classifications of seafloor species and features.

The SeaBee Otter operates with a high-accuracy positioning system (better than 2-3 cm on measured data) which enables precise georeferencing of collected data – be it underwater photo and video,  acoustic data of the seafloor or optical data of the water quality. 

Views of how the SeaBee Otter is handled in the field. Photo by Ø. Odegaard (NIVA).

Kasper Hancke (NIVA) evaluated the use of drones and artificial intelligence for kelp forest and seagrass mapping, highlighting the main advantages of SeaBee Research Infrastructure as well: 

– Drones with RGB and MSI sensors combined are powerful tools for high resolution mapping and monitoring of coastal habitats and species 
– Artificial Intelligence models are a powerful method for classifying benthic habitats and are cost-effective
– High resolution habitat maps are essential for coastal carbon accounting and more sustainable management and for guiding marine preservation and restoration initiatives. 

Great days of science and exciting discussions. Thank you to the organizing committee! – Kasper Hancke, SeaBee project coordinator

For more information on SeaBee Research Infrastructure visit, or follow us on LinkedIn: SeaBee Research Infrastructure.


SeaBee Out and About

The SeaBee experts have been busy, out and about sharing how SeaBee Research Infrastructure can be used, testing new possibilities and implementing the SeaBee Data Pipeline in coastal research and environmental monitoring activities.  

SeaBee at C-BLUES EU kick-off meeting   

There is a lot to discover about blue carbon ecosystems – seagrass meadows, tidal marshes, mangroves and macroalgae. The C-BLUES project aims to significantly advance knowledge and understanding of blue carbon ecosystems to reduce scientific uncertainty, improve reporting of blue carbon, and promote the role of blue carbon in delivering climate policy commitments.  

At the kick-off meeting (held 14-17th April in Barcelona), SeaBee coordinator, Kasper Hancke (NIVA), presented how SeaBee and drones can contribute to efficient mapping and monitoring of blue carbon habitats across a range of coastal environments and how drone data further can be developed into tools for assessing:

  1. ecological status of coastal systems,
  2. species and biomass of marine vegetation,
  3. development for estimating stocks and content of blue carbon, with relevance to sustainable management and research on climate regulation. 

C-BLUES will join forces with the already running Horizon Europe project, OBAMA-NEXT.  

C-BLUES is a Horizon Europe Framework project running from 2024-2028, funded under the call for EU-China international cooperation on blue carbon (HORIZON-CL5-2023-D1-02). 

Group picture at C-BLUES kickoff meeting, 14th – 17th April in Barcelona.
SeaBee at remote sensing seminar at MDIR 

Miljødirektoratet (MDIR) hosted a seminar on remote sensing for Norwegian environmental monitoring and mapping on the 23rd April, 2024.

SeaBee co-coordinator, Hege Gundersen (NIVA), presented the KELPMAP project on using drones for mapping and identification of kelp and underwater vegetation.

KELPMAP develops novel tools for kelp forests mapping using drone products and machine learning-based image classification, and the results demonstrate that drone images can be used to identify klep forests to a water depth of at least 10 m.

MDIR and Norwegian Space Center funded SeaBee to developing the tools to map kelp forests and other habitats for improving marine management actions. 

For more information on SeaBee Research Infrastructure visit, or follow us on LinkedIn: SeaBee Research Infrastructure.