As AI continues to break new ground with its transformative abilities, scientists in the UK have deployed the technology to help in wildlife management initiatives, helping solve the UK’s biodiversity challenges.
Under this project, researchers made use of AI-controlled cameras and microphones to track wildlife and identify the various species as well as their general behaviors.
The initiative has been hailed as a milestone towards helping stakeholders come up with a better wildlife conservation plan. According to the independent conservation organization World Wildlife Fund (WWF), AI has proven critical in accelerating the ability to understand and monitor the health of wildlife, forests and other ecosystems.
Piloting the project
The scientists carried out their study on three sites that comprised land alongside rail lines at Barnes, Twickenham and Lewisham in London where they used robot monitors to capture sounds and images. The areas have been fenced to prevent people from straying onto the lines.
Using computers, they identified the various wildlife species available and their locations. Foxes, deer, bats, and hedgehogs were identified while various bird species were known by “their songs.”
Anthony Dancer, a conservation specialist at the Zoological Society of London (ZSL) said they managed to capture a lot of data, which would have been impossible to achieve with human observation only.
“The crucial point is the scale of the operation,” he said.
“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 … Only AI made it possible,” he said.
He also highlighted the possibility of expanding the project to a wider area.
“And now that we have demonstrated the technology’s promise, we can expand to other areas,” said Dancer.
The initial study area used is owned by Network Rail, which also played a critical role in the project.
Tackling the bio-diversity problem
The project helped identify different bird species such as the blackbird, the Eurasian blackcap and the great tit, according to Neil Strong, a biodiversity manager for Network Rail.
All three species, he said, require a healthy environment “including a good supply of berries and nuts.
“That is encouraging and provides important benchmarks for measuring biodiversity in future,” he said.
The AI monitors also helped researchers pick six species of bats, the common pipistrelle included. Dancer said getting more detailed information about the location of bats, which usually use railway bridges for roosting, would be essential to “protect them.”
Strong emphasized that: “In the past, we have had to estimate local wildlife populations from the dead animals such as badgers – that have been left by the track of the roadside. This way, we get a much better idea of population sizes.”
While the project showed more than 30 species of birds and healthy animal species in London, Dancer said that was not the main aim of the project.
“The aim was to show that AI-led technology – linked with acoustic and camera traps- could be used effectively to survey wildlife on Network Rail land but also in other areas in the UK,” said Dancer.
“It will tell us how species are moving in response to climate change and how we should be managing vegetation, not just beside rail lines but on road verges and other places.”
Using data from the project, conservationists will now help hedgehogs in Scotland by opening small holes into the bases of new fencing to allow them to pass through. According to the results of the project, hedgehogs usually commute along UK rail lines.
International #WolfDay 🐺 A decade-long journey – Tracking Indian wolves, raising awareness, community participation, core research. 📚Baseline surveys, conservation plan for 10 crucial districts upcoming. 🌟 #WolfConservation #IndianWolf #TGT #MaharashtraWolves #conservation pic.twitter.com/aNhfX1sbYa
— The Grasslands Trust (@tgtrustindia) August 13, 2023
The project in other areas
The ZSL and Network Rail are now planning to carry out the project in other areas like Chobham in Surrey and the New Forest as the researchers noted AI’s importance in protecting biodiversity.
In India, researchers are looking at utilizing AI and drone technology to study the life cycle of wolves. Data from the forest department shows that there are currently 45 wolves in five to six wolf dens in the grasslands of Saswad.
Traditional tracking systems such as bio-loggers (GPS) collars have proven to have their drawbacks such as being invasive and a “stress-inducing process for the animals.”
The researchers are therefore resorting to AI-based technology to study “behaviours, movement patterns, and habitat structure of Indian wolves living in a human-dominated landscape in Maharashtra.”
“We will use a drone-based tracking method that overcomes the limitations of bio-logging,” said Grasslands Trust founder Mihir Godbole.
The study is also expected to bridge the existing knowledge gap.