AI4Peat

Automating peatland mapping

  • Publicly sourced

The challenge

Traditional manual mapping of peatland features across England's uplands would take approximately 10 years. The cost would be around £6 million. Natural England needed detailed mapping of peatland drainage features, erosion patterns, and restoration progress. This information was essential to guide targeted conservation efforts and carbon sequestration initiatives.

The solution

AI4Peat is a machine learning system that uses computer vision to automatically detect and map peatland features from high-resolution aerial imagery. The tool processes 12.5cm resolution aerial photography with LiDAR terrain data to identify drainage channels, gullies, eroded edges, and restoration dams, reducing mapping time significantly.

The results

AI4Peat has been operational since Spring 2025. The total investment for development of this solution was £288,000 compared to a £6 million manual alternative. The system reduced the 10-year manual timeline to automated processing in months. It has mapped 3.2 billion tonnes of carbon storage across UK peatlands, covering 12% of the country.

Details

Organisation name
Natural England / Department for Environment, Food & Rural Affairs (DEFRA)
Government body
UK Government
User group
Wider public sector
Use case type
Specific
Type of technology
Machine Learning
Phase
Live
Impact
Cost savings / Time savings / Improved efficiency

Links

Get in touch

Email ai-knowledge-hub@dsit.gov.uk to:

  • find out how to use or collaborate on this tool
  • review content for this tool
  • talk to us about your own tool

Content created: 15 September 2025