Satellites and AI used to track UK hedgehogs in bid to slow decline

Source: BBC Technology

AI‑driven hedhog conservation

Researchers at the University of Cambridge are using satellite data and AI in an effort to slow the decline in Britain’s hedgehog population.

Using an AI tool called Tessera, which analyses detailed images of the UK gathered from space, experts can precisely determine the locations of hedgehog habitats – and where these are disappearing. The resulting maps capture landscapes in minute detail, down to individual hedgerows, while AI can accurately predict hedgehog‑friendly places obscured by cloud cover.

The project aims to shed light not just on where hedgehogs live across the UK, but also on the barriers preventing them from finding food and mates. Tessera’s outputs can be used to track the impact of new housing developments and other environmental changes on landscapes that could affect hedgehogs over time. These insights can be combined with data gathered elsewhere – including tiny GPS trackers physically attached to some hedgehogs to monitor their movements in real time.

Researchers are also looking to use AI systems and models that can crunch large amounts of data and surface patterns to aid conservation efforts worldwide. Some, however, have urged caution around using the power‑hungry technology, citing concerns about its environmental impact.

Getty Images

Digi‑hogs

Hedgehog populations have declined dramatically across Europe in recent decades. In the UK, a 2022 report estimated their numbers have fallen by up to 75 % in rural areas since 2000.

Prof. Silviu Petrovan, strategy and research manager at People’s Trust for Endangered Species, is optimistic that AI can help protect the tiny mammals:

“What we’re really hoping is that we can use these powerful models to understand, for instance, what are the very specific barriers for hedgehogs to find food and find their mates, and be able to safely move around the countryside?”

Researchers refer to hedgehogs equipped with trackers as “digi‑hogs.” To accurately identify the tiny creatures and other objects in image data, the Tessera system was trained on vast amounts of data – around 20 petabytes, the equivalent of 10 billion standard digital photos. After reaching the limits of the university’s computing power, additional processors were installed, and a new deal with US tech firms AMD and Vultr provided extra infrastructure.

University of Cambridge

The huge, open‑source Tessera system is not just for hedgehogs. Anil Madhavapeddy, professor of planetary computing at Cambridge, notes that more than 100 research groups have accessed the tool. It can also be used to monitor farmland and track which crops are being grown in which fields over time, building a detailed picture of UK agriculture.

“Satellite data is really complicated to use and really noisy, because you have to do things like cloud removal and adjust for day and night,” he said. “Tessera compresses loads of that data and gives us easy‑to‑use maps of the UK, where we can ask very specific questions about things we can see from space.”