Britain's largest ever woodland survey of bats has recorded some of the country's rarest species, including the red-listed Barbastelle, in the south-west of England, in a project researchers say would not have been feasible without artificial intelligence.
Devices left on poles among the trees of 310 woodlands across Britain recorded 98 million bat calls over three years. The project involved researchers from University College London, the Bat Conservation Trust and Forest Research. The calls would have taken more than 30 years to analyse without AI.
Kate Jones, from University College London, said: "AI has fundamentally changed the scale at which we can monitor wildlife." She described the survey as a "nice story of AI for good", adding: "Previously, analysing this volume of acoustic data would simply not have been feasible. 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, one of the rarest bat species in England, roams ancient forests but its elusive nature has made it challenging to track. Hotspots of Barbastelle activity detected in the survey were concentrated across the South West.
Lia Gilmour, of the Bat Conservation Trust, said the project was "unprecedented". "Somerset is generally a really good stronghold for the bat species we have across the UK. It's been quite exciting some of the rarest species popping up in Somerset as part of the survey," she said. "In biodiversity monitoring, we view AI as a powerful tool. 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."
Analysis
Why This Matters
- The survey provides a national-scale picture of where Britain's rarest bats are found, which can help target woodland conservation efforts.
- It shows AI can make large-scale acoustic monitoring of wildlife practical, a method that could be applied to other species.
- The Barbastelle is red-listed, and the new activity hotspots in the South West could matter for protecting ancient woodland habitat.
Background
Bats are a key indicator of ecosystem health, and many British species have declined. The Barbastelle is one of the rarest, associated with ancient forests and difficult to survey because of its elusive behaviour. This project was the largest woodland bat survey ever carried out in Britain.
What to Watch
- Whether the Barbastelle hotspots identified in the South West lead to new conservation measures for ancient woodland.
- Whether the open-source AI tools used in the survey are adopted for monitoring other wildlife at a national scale.
Checked
12 claims in this story checked against 1 source: 11 supported.
Show each claim
- SupportedThe survey recorded Barbastelle bats in south-west England.BBC News: “Some of Britain's rarest and most threatened bats, including the red-listed Barbastelle, have been recorded in the south-west of England, including Somerset, Devon, Cornwall and Dorset.”
- Partly supportedThe survey was Britain's largest ever bat survey.BBC News: “Britain's largest ever woodland survey of bats would "simply not have been feasible" without AI, scientists say.”
- SupportedThe survey recorded 98 million calls in 310 woodlands over three years.BBC News: “Researchers left devices on poles among the trees of 310 woodlands across Britain, recording 98 million bat calls over three years”
- SupportedSome of Britain's rarest species, including the red-listed Barbastelle, were recorded in south-west England.BBC News: “Some of Britain's rarest and most threatened bats, including the red-listed Barbastelle, have been recorded in the south-west of England, including Somerset, Devon, Cornwall and Dorset.”
- SupportedThe survey would not have been feasible without AI, researchers say.BBC News: “Britain's largest ever woodland survey of bats would "simply not have been feasible" without AI, scientists say.”
- SupportedAnalysing the recorded calls would have taken more than 30 years without AI.BBC News: “recording 98 million bat calls over three years, which would have taken more than 30 years to analyse without AI.”
- SupportedKate Jones said AI had fundamentally changed the scale at which wildlife could be monitored.BBC News: “Kate Jones, from University College London, said: "AI has fundamentally changed the scale at which we can monitor wildlife."”
- SupportedJones described the survey as a “nice story of AI for good”.BBC News: “She added the survey was a "nice story of AI for good".”
- SupportedJones said analysing the data would not have been feasible and that open-source AI tools identify calls and patterns and flag species at national scale.BBC News: “Previously, analysing this volume of acoustic data would simply not have been feasible. "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."”
- SupportedGilmour called the project “unprecedented”.BBC News: “Lia Gilmour, of the Bat Conservation Trust, which was involved in the survey alongside Forest Research, said the project was "unprecedented".”
- SupportedGilmour said Somerset was a stronghold for UK bat species and that some of the rarest species had appeared there in the survey.BBC News: “"Somerset is generally a really good stronghold for the bat species we have across the UK. "It's been quite exciting some of the rarest species popping up in Somerset as part of the survey."”
- SupportedGilmour said AI was a powerful tool and that the 90,000 hours of recording could not have been processed manually.BBC News: “"In biodiversity monitoring, we view AI as a powerful tool," Gilmour added. "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."”
