The island of Jersey is known for its picturesque scenery and mild climate. But its proximity to the European continent put it in the path of an invasive predator: the Asian hornet. vespa velutina. This is bad news for the island’s wildlife, but it makes Jersey an ideal place to test new methods of tackling wasps.
Using the island as a test bed, our team of biologists and data scientists developed an AI system that can automatically detect Asian hornet infestations into new regions and ensure they are eradicated before they can gain a foothold. The VespAI system identifies Asian hornets with over 99% accuracy, as recent results published in the journal Communications Biology show.
This early warning system is needed because Asian hornets, also known as yellow-legged hornets, pose a rapidly spreading threat to biodiversity. Originating in Southeast Asia, the species has invaded Europe, eastern Asia and the United States within two decades, preying on honeybees and other important pollinators.
To tackle the problem, VespAI uses deep learning technology, a computational method inspired by the human brain, to visually identify Asian hornets, capture images and send automatic alerts to the beekeeper, landowner or government official using the system.
Installation is simple. A sponge impregnated with a wasp attractant, a tasty mixture of sugar and fruit extracts, is placed under a small camera that takes pictures of visiting insects descending to feed. These images are then analyzed by the system’s artificial intelligence algorithm, allowing the monitor to identify Asian hornets with almost perfect accuracy.
VespAI meets an urgent need for the UK as the UK lies on the edge of the wasps’ European invasion front. Asian hornet attacks on the UK began in 2016 and are now occurring on an annual basis. Although the national eradication strategy has limited the hornets’ ability to fully establish, 2023 has been a particularly bad year, with a record 72 nests discovered.
In Europe, traditional methods such as baited traps constitute the first line of defense. However, these kill significant numbers of native insects, including many pollinators. Additionally, kill traps do little to meaningfully reduce wasp numbers, as colonies continue to survive unless the queen is destroyed.
VespAI provides a significant advantage over trapping by preventing damage to visiting insects. Additionally, Asian hornets detected by the system remain alive so they can be tracked back to their nests. This is important because it is the only proven way to destroy colonies.
The main reason for the hornets’ success is the difficulty of detecting their initial invasions into new areas. New colonies start from a single queen but can produce hundreds of additional queens within a year, causing the number to increase exponentially.
As a result of this rapid expansion, hornet populations often form before or soon after they are noticed by humans, making them almost impossible to eradicate. The risk of mistaken identity is also high, as early detection of infestations depends on public observations. In the UK, only 0.06% of the thousands of Asian hornet reports submitted each year are correct identifications.
A scalable solution
To test the effectiveness of VespAI, we conducted rigorous field trials on the island of Jersey, where attacks by Asian hornets from France are common. Working with the Jersey Asian Hornet Group and the island’s government, we deployed prototype systems in areas where Asian hornets, European hornets and other insects are abundant.
We then meticulously analyzed thousands of images collected by the prototype systems. We manually checked each one to ensure that the AI algorithm correctly identified all Asian hornets without mistakenly identifying other insects as hornets.
So far our results are promising. VespAI provides a significant advantage over previous methods by accurately detecting Asian hornets with over 99% accuracy. Although this technology is still in development, our experiments show that the system could transform Asian hornet management in at-risk areas such as the UK and USA.
Britain’s first confirmed Asian hornet in 2024 was recorded in March, much earlier than usual, and the high number of nests in 2023 suggests this year could be the toughest yet. Further trials of the VespAI system will take place in the UK over the next few months as we work with government authorities to support eradication efforts at this critical time.
This article is republished from The Conversation under a Creative Commons license. Read the original article.
Thomas O’Shea-Wheller receives funding from UK Research and Innovation (UKRI).
Peter Kennedy receives funding from UK Research and Innovation (UKRI) and the Halpin Trust.