A revolutionary combination of AI technology, wireless connectivity and robust, efficient trapping equipment is a potential game-changer in the fight to protect New Zealand’s native birds and wildlife – and even record the sounds of success, in the birdsong returning to our native bush.
The AT520-AI incorporates an automatic resetting trap, with AI, onboard camera and management system that engages the trap only when it recognises a target species – such as a possum, rat or stoat – and reports back when it kills a pest via a remote network of ‘Yarn Mesh’ nodes.
The system, which is designed to create a network of connectivity across New Zealand’s remote, rugged and mountainous environments, is the result of a collaboration between NZ AutoTraps, makers of the award-winning AT220, New Zealand’s first auto-resetting, multi-species trap, and FTP Solutions, a global technology provider focused on helping businesses capture and manage data. NZ AutoTraps is 50% owned by New Zealand Carbon Farming, which uses the traps as part of its operation of the largest private pest control programme in the country.
The product has just been recognised by the NZ Biosecurity Institute, winning this year’s Dave Galloway Innovation Award at the organisation’s annual conference last week.
Shared focus on innovation
NZ AutoTraps Operations Manager Haydn Steel says the collaboration grew from a shared focus on using the latest innovations in AI, machine learning and communications technology to build a more effective and efficient pest trap.
“One of the things we had been looking to improve on for our initial trap design was avoiding the risk of by-kill,” says Haydn. “It’s also important, particularly for groups which are results-funded, to have a reliable record of when the trap has worked.”
AI-targeted pests
FTP Agriculture Manager Jonathan Clark says the new AT520-AI uses a machine learning model to train the AI on thousands of images so it can accurately distinguish between a target and non-target species.
“As an animal approaches the trap, it detects that movement through the proximity sensors on the AT520, and then the AI camera starts firing off a sequence of images – classifying each image in about one twentieth of a second – and arming the trap only when we get a positive ID on a target species,” says Jonathan.
The AT520-AI can also alert other nearby traps on the network to the presence of a targeted pest, which can then also deploy their lures, increasing the probability of removing the animal.
In the next iteration of the AT520-AI, in development for 2025, the AI will also be able to instruct the traps to deploy one of three species-specific lures, and even play audio designed to help attract detected pest animals, using a built-in speaker. An RFID reader will also be included, to prevent micro-chipped domestic cats being caught by the traps.
“We’ve also added some custom solar panel technology onto the trap and that allows indefinite operation without the need to change a battery or recharge a battery,” says Jonathan. “So we’re really moving towards automated, landscape-scale operations with as little human energy and input as required.”
Connected reporting and surveillance
FTP’s Yarn Mesh network means the system is ideal for areas with limited internet connection, especially where direct line of sight is not possible, with traps able to be connected up to 25 kilometres apart.
As well as constantly updating information on the operation of the trap, its store of lure material and battery life, the traps record and send valuable surveillance data for predator management.
“So you can actually see which predators are where within the network, where a trap might need to be redeployed to be more successful, where your hot spots are, and where you’ve knocked something right down and can move on to other areas – all backed by detailed data and photographic evidence of each pest kill,” says Jonathan.
Building a remote network
Haydn says the company has also been attracting interest from organisations looking to use the Yarn Mesh network to provide health and safety support for employees and volunteers working on predator control programmes in remote areas.
“With the mesh, you’ve got the ability to give your workers a personal locator so you can follow them as they move along the network,” says Haydn. “You’ve also got the ability to text message via the network, so if you’ve got no cellular coverage, you can have a two-way text conversation. That means if someone gets in trouble, they can get in touch and help is on its way, or if plans change, you can send them on a different task.”
Proof of improving biodiversity
As well as accurate targeting of pests, and recording of removals, the designers would like to use the product to report on the positive impact the traps’ deployment is having on our native species.
“The big conversation we have is about killing pests,” says Jonathan. “But we can also create the ability to tell what’s coming back. There’s the potential to add microphones to the system, so we can do bird counts as well.”