AI-Powered Drones for Automated Pest Monitoring

Researchers in Italy have announced the first effective use of commercial drones and artificial intelligence (AI) to monitor the invasive agricultural pest, Halyomorpha halys, also known as the brown marmorated stink bug. This study, published in the SCI journal Pest Management Science, represents a significant step forward in the use of unmanned aerial vehicles (UAVs) for automated monitoring of invasive species.

Halyomorpha halys is infamous for causing significant damage to orchard crops in southern Europe and North America. In 2019, this invasive pest caused approximately 588 million euros worth of damage to fruit production in Italy.

Pheromone traps, visual sampling, and sweep-netting are examples of traditional monitoring techniques that require a lot of labor and are frequently useless across a wide region.

Current monitoring methods have some important drawbacks, such as “trap spillover” and the need and cost for operators to perform active monitoring.

Daniele Giannetti, Study Co-Lead Author and Researcher, University of Parma

Lara Maistrello, Professor at the University of Modena and Reggio Emilia and Co-Lead Author of the study, added, “Our aim was to find a reliable way of monitoring these invasive insects without the negative effects of the time and energy-consuming methods currently used.”

Drones Reduce Disruption

The scientists created an automated flight technique that can be operated by a smartphone app to take high-resolution images of pear orchards up to eight meters high.

Notably, drones were shown to be far less disruptive to bugs than human observers, allowing for more precise data collection on pest distribution. Adult bugs were discovered to freeze in reaction to the presence of a UAV, allowing for the acquisition of high-resolution images.

AI for Autonomous Pest Recognition

AI models for recognizing H. Halys were trained, validated, and tested using the picture dataset. The best-performing model had a detection accuracy of 97 %. Transfer learning models, which use pre-existing recognition skills, significantly outperformed models trained from scratch.

Giannetti added, “Overall, this novel monitoring system demonstrated the potential of integrating UAV and AI to detect and quantify the presence of insect pests with the size and shape of H. halys.”

This technique has important ramifications for integrated pest control strategies, such as the creation of accurate forecasting models that adjust to environmental and meteorological factors.

Giannetti noted, “This is particularly important today in the face of rapid climate change.”

Looking Beyond Stink Bugs

There could be numerous applications for this innovative monitoring system.

The imaging application can be easily adapted to different crops. Of course, if you want to move on to other insects, you will have to train new models, but this experience is really encouraging. We find these results exciting, especially because their future applications are so many.

Lara Maistrello, Study Co-Lead Author and Professor, University of Modena

Journal Reference:

Giannetti, D., et al. (2024) First use of unmanned aerial vehicles to monitor Halyomorpha halys and recognize it using Artificial Intelligence. Pest Management Science. doi:10.1002/ps.8115