August 13th, 2023
Researchers have developed arrays of AI-controlled cameras and microphones to identify animals and birds, as well as monitor their movements in the wild – technology they say will help tackle Britain's growing biodiversity problem.
The robotic monitors have been tested at three sites, capturing sounds and images that computers could use to identify specific species and map their locations. Dozens of different bird species were recognized from their songs, while foxes, deer, hedgehogs, and bats were pinpointed and identified through AI analysis. Human observers were not involved.
"The crucial point is the scale of the operation," said Anthony Dancer, a conservation specialist at the Zoological Society of London (ZSL). "We have captured tens of thousands of data files and thousands of hours of audio from these test sites and identified all sorts of animals from them. We couldn't have done it at that scale using human observers. Only AI made it possible."
The project's test sites were chosen on land alongside rail lines in Barnes, Twickenham, and Lewisham in London. Owned by Network Rail, which played a key role in setting up the project, these areas are fenced off to prevent people from straying onto the tracks and are infrequently visited by track maintenance staff.
"Access to relatively wild land was therefore easy – an important factor for starting our project," said Dancer. "And now that we have demonstrated the technology's promise, we can expand to other areas."
Network Rail owns over 52,000 hectares of land, with many areas playing a significant role in protecting the nation's biodiversity.
"Consider birds like the Eurasian blackcap, blackbird, and great tit," said Neil Strong, biodiversity strategy manager for Network Rail. "All three species require healthy environments – including good supplies of berries and nuts – and all three were detected by AI from the acoustic signals collected by our sensors at our three test sites. That is encouraging and provides important benchmarks for measuring biodiversity in the future."
The AI monitors also pinpointed other creatures, including six bat species, such as the common pipistrelle.
"Bats almost certainly use railway bridges for roosting," Dancer told the Observer. "So if we can get more detailed information about the exact locations of their roosts using AI monitors, we can help protect them."
Strong emphasized this point. "In the past, we have had to estimate local wildlife populations from the deceased animals – like badgers – found by the track or roadside. This way, we gain a much better understanding of population sizes."
The project also revealed hedgehogs as regular commuters on UK rail lines. "Hedgehogs are constrained to certain locations due to fencing," said Strong. "But there are solutions. In Scotland, they are creating hedgehog highways on rail lines, involving cutting small holes into the bases of new fences to allow hedgehogs to pass through while preventing larger animals from entering."
ZSL and Network Rail now plan to extend the use of AI monitors to other areas, including Chobham in Surrey and the New Forest. "In the sites we tested, we found signs of over 30 bird species and six bat species, as well as foxes and hedgehogs. We were pleasantly surprised by the relatively healthy wildlife levels in London," said Dancer. "However, that wasn't the primary goal of our project.
"The aim was to demonstrate that AI-led technology – coupled with acoustic and camera traps – could effectively survey wildlife on Network Rail land and other areas in the UK. It will reveal how species respond to climate change and guide vegetation management, not only beside rail lines but also on road verges and other locations."
The crucial point is that machine learning – AI – will be vital in protecting biodiversity as the country faces increasing temperatures. "This technology will require analyzing tens of thousands of hours of recordings and hundreds of thousands of images," said Strong. "Realistically, only computers can accomplish that for us."
Source: TheGuardian