Britain’s largest ever woodland survey of bats would simply not have been feasible without the help of artificial intelligence, according to scientists. Researchers placed recording devices on poles among the trees of 310 woodlands across Britain, capturing 98 million bat calls over a three-year period.
Unprecedented Scale and AI Analysis
Analyzing the massive volume of acoustic data manually would have taken more than 30 years. Kate Jones from University College London stated that artificial intelligence has fundamentally changed the scale at which researchers can monitor wildlife, calling the project a nice story of AI for good.
Jones explained that efficient open-source artificial intelligence tools allow scientists to identify millions of bat calls across thousands of nights of recordings, recognize patterns, and flag species on a national scale. Lia Gilmour from the Bat Conservation Trust, which conducted the survey alongside Forest Research, noted that the project was unprecedented and highlighted that manual processing of 90,000 hours of recordings would have been impossible.
Rare Species and Regional Hotspots
Some of Britain’s rarest and most threatened bats, including the red-listed Barbastelle, were recorded in the south-west of England, encompassing Somerset, Devon, Cornwall, and Dorset. The Barbastelle roams ancient forests, but its elusive nature has historically made tracking difficult.
Gilmour stated that hot spots of Barbastelle activity were concentrated across the South West, adding that Somerset serves as a particularly strong stronghold for bat species across the United Kingdom and noting that the appearance of rare species has been exciting.
Researchers view artificial intelligence as a powerful instrument in biodiversity monitoring as the project continues to track vulnerable wildlife populations.
