Largest woodland bat survey a 'nice story of AI for good'

Largest woodland bat survey a 'nice story of AI for good'Image source, Daniel HargreavesImage caption, The red-listed Barbastelle is one of the rarest bat species in EnglandByHarriet Bradshaw and Clara BullockSomersetBritain's largest ever woodland survey of bats would "simply not have been feasible" without AI, scientists say.Researchers left devices on poles among the trees of 310 woodlands across Britain, recording 98 million bat calls over three years, which would have taken more than 30 years to analyse without AI.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.Kate Jones, from University College London, said: "AI has fundamentally changed the scale at which we can monitor wildlife." She added the survey was a "nice story of AI for good".More from SomersetJones added: "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 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.Image source, Daniel HargreavesImage caption, The Barbastelle was mostly found in the south-west of EnglandLia Gilmour, of the Bat Conservation Trust, which was involved in the survey alongside Forest Research, said the project was "unprecedented"."We're getting some really good bat activity in the south-west area of Somerset," Gilmour said."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."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."Get in touchMore on this storyRelated Internet Links