AI Powers Britain's Largest Bat Survey, Enabling Unprecedented Wildlife Monitoring

Scientists have utilized artificial intelligence to conduct Britain's most extensive woodland bat survey, a project that would have been unfeasible without the technology. Researchers deployed recording devices in 310 woodlands across Britain, capturing 98 million bat calls over a three-year period. AI analysis of this vast dataset significantly accelerated the process, which would have required over 30 years to complete through manual review.

This technological advancement has allowed for the identification of rare and threatened bat species, including the red-listed Barbastelle, which was detected in hotspots across the South West of England, particularly in Somerset, Devon, Cornwall, and Dorset. Kate Jones of University College London stated that AI has fundamentally changed the scale of wildlife monitoring, calling the survey a "nice story of AI for good."

"Previously, analyzing this volume of acoustic data would simply not have been feasible," Jones explained. "These efficient open-source AI tools allow us to identify millions of bat calls across thousands of nights of recordings, identify patterns and flag species at a national scale."

The Barbastelle, known for its elusive nature and preference for ancient forests, has been challenging to track. The survey revealed significant activity of this species concentrated in the South West.

Lia Gilmour from the Bat Conservation Trust, a partner in the survey alongside Forest Research, described the project as "unprecedented." She highlighted the substantial bat activity in Somerset and the presence of rare species in the county, noting that "In biodiversity monitoring, we view AI as a powerful tool."

Gilmour emphasized the sheer volume of data processed, stating, "We were looking at huge volumes of data and 90,000 hours of recording, there was no way we would be able to do this manually."