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

Britain's most extensive woodland survey of bats would have been impossible without the use of artificial intelligence (AI), scientists claim. Researchers installed devices on trees in 310 woodlands across the country, monitoring 98 million bat calls over a period of three years. Without AI, analyzing this data would have taken over 30 years, according to the research team.

Among the rarest and most threatened bat species recorded in the survey were the Barbastelle, a bat listed as red-listed in Britain. These elusive creatures were detected in the south-west of England, including Somerset, Devon, Cornwall, and Dorset.

Kate Jones, a researcher from University College London, emphasized the transformative impact of AI on wildlife monitoring. "AI has fundamentally changed the scale at which we can monitor wildlife," she stated, adding that the survey was a "nice story of AI for good."

The sheer volume of acoustic data collected during the survey would have been unmanageable without advanced AI tools. "Previously, analyzing this volume of acoustic data would simply not have been feasible," Jones noted. These efficient, open-source AI tools enable researchers to identify millions of bat calls across thousands of nights of recordings, pinpoint patterns, and flag species activity across the nation.

Lia Gilmour, from the Bat Conservation Trust, described the project as "unprecedented." She shared that the survey revealed substantial bat activity in the south-west area of Somerset, highlighting that the region is a strong stronghold for various bat species in the UK. Gilmour also expressed excitement about the detection of rare bat species in Somerset during the survey.

She emphasized that in biodiversity monitoring, AI serves as a powerful tool, allowing researchers to process vast amounts of data and hours of recordings that would be otherwise impossible to analyze manually.