An Early Warning System for Tracking Asian Hornets With AI

British researchers have developed a groundbreaking early warning system, VespAI, which uses artificial intelligence to track and identify Asian hornets, a threat to the UK's bees. By offering a cost-effective, versatile solution, the team behind the project hopes to both r

Share
An Early Warning System for Tracking Asian Hornets With AI

An early warning system designed to track and trace predatory Asian hornets using artificial intelligence has been presented by experts from a UK university.

Researchers from the University of Exeter have invented a system that lures hornets to a monitoring station. They land on a sponge pad soaked in food, and a camera above captures images.

The AI determines whether they're Asian hornets, which pose an existential threat to the UK's bees. If they're Asian hornets, an alert is sent to the operator's phone or computer.

Once a hornet has found what appears to be a safe food source, it's likely to return, and a team will be able to track the Asian hornet back to its nest.

Asian hornets (Vespa velutina) have already invaded large parts of mainland Europe, and last month it emerged that they may have established themselves in the UK, following the earliest-ever recorded sighting of the insect.

They sit outside beehives and catch bees as they go in and out. A single Asian hornet can hunt down and eat 30 to 50 honeybees a day.

The invention by the Exeter researchers, named VespAI, could be a gamechanger, since it's crucial to detect the arrival of Asian hornets in an area early, before new queens are produced, as it's nearly impossible to get rid of them once established. The goal is to keep the cost of the components under £100 so the device can be used widely.

The Goal: Cost-Effective, Versatile Monitoring

"Our goal was to develop something cost-effective and versatile, so that anyone – from governments to individual beekeepers – could use it," said Thomas O'Shea-Wheller, from the Environment and Sustainability Institute at the university's Penryn campus in Cornwall. "This study tested a prototype version, and the results were encouraging."

Currently, the UK's strategy for responding to Asian hornets relies on people spotting, identifying, and reporting them, but the vast majority turn out to be cases of mistaken identity. Typically, fewer than 1% of suspected Asian hornet sightings are accurate.

VespAI uses a compact processor – essentially a small computer – to operate, and it remains dormant unless its sensors detect an insect within the size range of a hornet.

If this happens, the system's AI algorithm activates, analyzing the image to determine whether it's an Asian hornet. If an Asian hornet is detected, the monitor sends an alert to the user.

Dr. Peter Kennedy, who worked on the project, said: "The majority of reports submitted are misidentified native species, meaning authorities have to manually validate thousands of images every year.

"In parts of Europe, detection relies on trapping hornets – but such traps kill many native insects and do little to affect Asian hornet numbers. VespAI ensures live hornets can be tracked back to the nest, which is the only effective way to destroy them."

Tracking teams can find the nest by observing which direction the hornets fly off in. By repeating this from other nearby locations, the likely location of the nest can be estimated through triangulation.

The system was tested on the island of Jersey, which experiences a large number of Asian hornet incursions. Thousands of images of Asian hornets and other insects were collected, and the AI learned to identify Asian hornets based on coloring, size, and morphology.

This year, the team will begin deploying additional prototypes in collaboration with the UK government, the National Bee Unit, the British Beekeepers Association, and the company Vita Bee Health.