AI-generated peatland map confuses bogs with stone walls

An AI-generated map intended to guide England’s peatland conservation was criticised after it misidentified bogs, stone walls, quarries and even granite outcrops, leading to significant mapping errors and confusion among land managers and policymakers. What happened Natural England’s AI4Peat project, funded by UK government department DEFRA, used machine learning models trained on aerial imagery, LiDAR, and field data to create a national peatland map. Despite claims of over 95 percent accuracy, users quickly discovered glaring mistakes: quarries, bare rock, woodland, and even iconic granite tors were labeled as deep peat, while some genuine peat sites were missed entirely. Given the map is intended to inform peatland restoration funding, land management, and environmental policy, t he errors are seen to have real-world consequences, with landowners fearing they could be denied funding or face regulatory decisions based on inaccurate data. Why it happened The primary cause was the reliance on AI models trained with limited or imperfect ground-truth data, combined with the inherent difficulty of distinguishing peatland features from above. The models sometimes confused visual cues - such as the colour and texture of stone walls or rocky outcrops - with those of peat bogs, especially in landscapes where peat is rare or modified by agriculture. While Natural England did conduct field checks, critics argue that not enough “ground truthing” or local verification was done before the map’s release. The statistical accuracy touted by the developers masks the severity of errors in rare or complex landscapes, where even a small percentage of mistakes can have outsized impacts. What it means For landowners, farmers, and conservationists, the map’s inaccuracies undermine trust in AI-driven environmental management and risk misdirecting restoration resources. Decisions based on flawed data could lead to inappropriate land use restrictions or missed opportunities for genuine peatland restoration. For policymakers, the incident highlights the need for more robust validation and local engagement before deploying AI tools at scale. More broadly, it serves as a cautionary tale about the limitations of AI in complex, real-world environmental mapping, emphasising that technology must be complemented by local expertise and thorough verification to avoid costly mistakes and policy missteps.

Date it happened

2025-01-01

Organisation involved

Natural England

Product, system or model

AI4Peat

This is a record of what was reported, not a finding that anyone broke the law. If it names your organisation and you believe it is wrong, the corrections process is free and open to everyone.