AI for smart conservation

AI for smart conservation

Start date
1 July, 2022
End date
30 October, 2024

In the AI for smart conservation project BAS are collaborating with the Government of Nunavut and WWF to develop practical tools for conservation decision making. By combining satellite observations, GPS tracking and AI-forecasting with local expert knowledge, we develop AI-informed systems which can give early warning and alerts for important environmental tipping points. This information can empower regional experts to design adaptive management plans, ultimately limiting species loss for vulnerable polar wildlife.

Climate change is an increasingly pervasive threat to global biodiversity. Animal populations in the rapidly changing Arctic are often seen as a litmus test for the response of wildlife to climate change, particularly those whose life histories are inextricably tied to seasonal sea ice, such as polar bears, walrus, and certain caribou populations. As Arctic species navigate their increasingly unpredictable and diminishing sea ice habitat, conservation practitioners must develop adaptive management plans which are effective in these rapidly changing environments.

In recent years, advances in the field of AI-based sea ice forecasting have enabled more accurate forecasts of sea ice conditions. One example is IceNet, an in-development operational AI model, which forecasts pan-Arctic sea ice concentration (SIC) up to three months into the future at a 25km2 grid-cell resolution. The IceNet forecast maps have the potential to inform active conservation management and monitoring plans, and provide early warning of SIC tipping points critical for sea ice-dependent species.


Dolphin and Union caribou migrations

In this project BAS have partnered with the Government of Nunavut and WWF to develop tools to conserve endangered Dolphin and Union (DU) caribou. DU caribou migrate across sea ice as part of their annual migration, however due to climate change DU caribou are being forced to migrate later, and over less stable ice (Figure 1). Being able to predict when and where the caribou are expected to cross the ice would allow conservationists to make adaptive plans, for instance imposing restrictions on icebreaking activities from the shipping industry.

Figure 1 : GPS collared caribou migrating across sea ice in the Coronation Gulf during the autumn freeze up. Tracks overlaid on 25km OSI-SAF (left) and 6km AMSR2 data (right). We can see the caribou wait on the south coast of Victoria Island for the sea ice to reach safe levels for crossing. Using IceNet we can predict when the ice will form, and therefore give early warning for when the caribou will begin their migration.

By linking satellite observations of sea ice concentration (SIC) with GPS collar data we are able to establish what SIC the caribou require before beginning their autumn migration. We then use IceNet to forecast when this SIC tipping point is expected to be reached in the region (Figure 2). These maps can be used to guide local experts, for instance deciding the time and locations where shipping limitations should be imposed. Output maps are currently being integrated into an online platform which can be accessed by local agencies, allowing safe upload of real-time collar locations to better guide decision making. The end goal is a human-expert centred decision support tool which can be used for quick and easy assessment of forecast information.


Figure 2: An example output map which can be used for decision making. In this image, we convert the IceNet forecast to show the date at which each grid cell is expected to cross 90% SIC. Conservationists can use this to assess the regions where caribou are most likely to begin migrating, to inform protected zones against ice breaking activity.