Cambridge researchers use AI to map hedgehog habitats from satellite data

Cambridge researchers have developed an AI model that identifies bramble patches from satellite imagery to map potential hedgehog habitats across the UK. This innovative approach addresses a critical conservation challenge, as European hedgehog populations have declined by 30-50% over the past decade, and traditional tracking methods are too expensive and labor-intensive for large-scale monitoring.

How it works: The AI system combines satellite data with citizen science observations to detect brambles, which serve as essential hedgehog habitats for shelter, nesting, and food sources.

• The model uses relatively simple machine learning techniques—logistic regression and k-nearest neighbors classification—rather than complex deep learning models like ChatGPT.
• It processes imagery from the European Space Agency’s Sentinel satellites using TESSERA earth representation embeddings, combined with ground-truth data from iNaturalist, a citizen science platform where people share wildlife observations.
• The system performs best when detecting large, uncovered bramble patches visible from above, while smaller brambles under tree cover show lower confidence scores.

Field testing results: Researchers Gabriel Mahler, Sadiq Jaffer, Anil Madhavapeddy, and Shane Weisz spent a day walking around Cambridge to validate the model’s predictions and found encouraging early results.

• “It took us about 20 seconds to find the first one in an area indicated by the model,” wrote researcher Sadiq Jaffer in a blog post documenting the field test.
• At Milton Country Park, every high-confidence area they checked contained substantial bramble growth.
• Most notably, a major prediction in North Cambridge led them to Bramblefields Local Nature Reserve, which contained extensive bramble coverage as its name suggests.

Why brambles matter: These thorny shrubs provide critical ecosystem services that make them ideal proxies for hedgehog habitat mapping.

• Hedgehogs rely on dense vegetation like brambles for daytime shelter, nesting sites, and protection from predators.
• Brambles attract insects and provide berries, supporting the invertebrate populations that hedgehogs eat.
• Traditional hedgehog surveys require extensive nighttime fieldwork and specialized equipment that don’t scale well for national conservation planning.

Current limitations: The research represents a proof-of-concept that requires more systematic validation before widespread deployment.

• The model has not yet been published in a peer-reviewed journal, and the field validation was an informal test rather than a scientific study.
• The Cambridge team acknowledges these limitations and plans more comprehensive validation studies.
• Gabriel Mahler, who developed the AI model, noted that satellite imagery’s overhead perspective naturally limits detection of brambles obscured by tree cover.

The big picture: This approach demonstrates how AI applications extend far beyond generative models like ChatGPT into practical conservation and environmental monitoring.

• The simplicity of the bramble detector offers practical advantages, potentially enabling the system to run on mobile devices for real-time field validation.
• Similar AI-based approaches combining satellite remote sensing with citizen science data could map invasive species, track agricultural pests, or monitor ecosystem changes.
• For threatened species like hedgehogs, rapidly mapping critical habitat features becomes increasingly valuable as climate change and urbanization reshape their environments.