Specifically, the researchers examined how the combination of AI and drones could help fight Halyomorpha halys, otherwise known as the brown marmorated stink bug, which has caused untold damages in orchards throughout North America and southern Europe.

Source: University of Modena and Reggio Emilia

Current approaches for dealing with these pests — such as pheromone traps, visual sampling and sweep-netting — are reportedly labor-intensive and difficult to execute within large orchards.

As such, the team sought an approach that consumed less time and energy by developing an automated flight protocol wherein drones could capture high-resolution images of pear orchards from a height of 26 ft above. These captured images were then used to train AI models in identifying a pest infection.

According to the researchers, the models trained on those images were more successful at identifying the stink bug with an accuracy of 97% versus those trained from scratch.

The team’s findings are detailed in the article, “First use of unmanned aerial vehicles to monitor Halyomorpha halys and recognize it using artificial intelligence,” which appears in the journal Pest Management Science.