National mapping of submerged aquatic vegetation in the shallow Swedish coast using satellite imagery

Submerged aquatic vegetation (SAV) such as kelp forests, eelgrass meadows and rockweed beds are some of the most productive ecosystems on Earth, playing a critical role in maintaining the health and function of aquatic ecosystems. Recent evidence suggests that SAV is one of the most efficient ecosystems when it comes to blue carbon capture and long-term storage. In the European Union, monitoring and assessments of the status of marine waters are key components of the Habitat Directive (HD), the Water Framework Directive (WFD) and the Marine Strategy Framework Directive (MSFD), and SAV health is an indicator of a healthy marine ecosystem. A satellite mapping tool is making it easier for Swedish authorities to map, monitor and evaluate changes in coastal vegetation and biotopes. This contributes to Sweden’s efforts to protect the marine environment and helps the country comply with national and international monitoring and reporting requirements.

Challenge

Up-to-date knowledge of SAV abundance and growth is critical to assess the impacts of management and conservation efforts, monitor overall marine health, evaluate the success of blue carbon strategies and aid in the construction of blue carbon budgets.

However, the highly fragmented nature of SAV in time (due to seasonal changes) and place (as SAV is organised into many heterogeneous patches of individual communities in rather shallow areas) makes monitoring and mapping a challenging, time-consuming and labour-intensive task.

In Sweden, environmental monitoring of the spatial distribution of SAV was lacking due to the challenges of using traditional small-scale methods for large-scale monitoring. Traditional methods such as field-based observations come with limitations such as small coverage areas, high costs and unsystematic data collection, making it difficult to map SAV consistently and comprehensively. As a result, Swedish authorities were limited in their ability to fully understand the intricacies of underwater coastal communities and their evolution over time.

Solution

Building on a robust and scalable approach, and in collaboration with Swedish regional and national authorities, the DHI team developed an SAV monitoring tool to monitor the extent and dynamics of SAV at scale for Sweden in a cost-efficient and timely manner. The project included the entire shallow coastal zone of Sweden, an area covering almost 50,000 km². The cloud-based web platform allows non-EO specialists to apply advanced machine learning algorithms and the latest earth observation data to conduct scalable and detailed SAV classification on demand.

The team first combined Copernicus Sentinel-2 satellite imagery, novel machine learning techniques and advanced data processing to create the first spatial overview of the distribution of SAV at a national scale in Sweden. A training dataset constructed with more than 30,000 manually labelled polygons was used to build the classification model, with which more than 3,800 km² of underwater habitats of the entire shallow coastal zone of Sweden was mapped.

With this novel tool, authorities can now execute the entire mapping process in a few clicks – from the selection of suitable imagery to the final classification – just by interactively adding relevant training data. The user-friendly platform enables SAV mapping to be conducted on demand to ensure that data quality and update frequency meets the needs of Swedish authorities.

The project outcome and methodologies are further described in the following peer-reviewed article: Huber, Silvia. et al. (2021), Novel approach to large-scale monitoring of submerged aquatic vegetation: A nationwide example from Sweden. Integrated Environmental Assessment and Management.