The Zoological Society of London (ZSL) has teamed up with Network Rail to use artificial intelligence technology to develop a new wildlife monitoring method, hoping to solve the UK’s growing biodiversity problem.
Image source Pexels
The technology has been tested at three locations, successfully capturing sounds and images of various animals, which are analyzed and localized by computers. Dozens of different bird species were identified from their calls, and animals ranging from foxes to deer to hedgehogs to bats were also accurately identified without the involvement of human observers.
Anthony Danser, a conservation expert at the Zoological Society of London (ZSL), said, “We have collected tens of thousands of data files and thousands of hours of audio from these test sites, and we have found a variety of animals. If we use human observers, we cannot Doing this at this scale is only possible with artificial intelligence.”
It is noticed that the project selected three test locations next to the railway, namely Barnes, Twickenham and Lewisham in London. The areas are owned by Network Rail, which has played a major role in the project. These areas are fenced to keep people from straying onto the tracks, and maintenance crews rarely enter. British Rail owns more than 52,000 hectares, many of which play an important role in protecting the country’s biodiversity.
ZSL and British Rail plan to expand the use of AI monitors to other areas, including Chobham and the New Forest in Surrey. “At the sites we’ve tested, we’ve found more than 30 species of birds and six species of bats, as well as signs of animals such as foxes and hedgehogs, so we were pleasantly surprised by the relatively healthy level of wildlife found in London,” Danser said “However, this was not the main aim of our project. Our aim was to demonstrate that AI-led techniques, combining acoustic and camera traps, can be effective in surveying wildlife on UK rail lands, but also in other parts of the UK. This will tell us how species respond to climate change, and how we should manage vegetation, not just next to railways, but along road verges and other places.” important.
By analyzing tens of thousands of hours of recordings and hundreds of thousands of pictures, machine learning technology will play a key role in protecting biodiversity and providing more accurate data support.