Drones and AI: a winning cocktail for modern agriculture?

Faced with the growing imperatives of modern agriculture – ravages of pests, imperative to optimize yields – certain farmers are turning to cutting-edge technologies. Today, the joint use of drones and artificial intelligence is one of the most promising alliances to guarantee crop monitoring. This technological synergy not only enables proactive problem detection, but significantly increases agricultural management performancemaking the whole process more precise and responsive.

The brown marmorated stink bug: a scourge

Although known for their foul odor when crushed, bedbugs actually represent one of the most formidable agricultural scourges in North America and southern Europe. We are talking here about the brown marmorated stink bug or diabolical stink bug (Halyomorpha halys), originally from Asia. These caused damage estimated at 500 million euros on the Old Continent in 2019 alone. They attack apple trees, pear trees, vines, soybeans or corn. A real calamity on six legs.

Monitoring these pests is essential as they threaten the sustainability of crops. However, the methods currently used are often tedious and inefficient on a large scale. A recent study conducted by Italian researchers and published in the journal Pest Management Science in April looked at the use of drones equipped with cameras and AI algorithms. They used this system to monitor these bugs in pear orchards.

Agriculture 3.0

For their experiment, the scientists used a commercial drone, the DJI Matrice 300. Equipped with a high-definition camera, it was able to capture highly detailed images of the bugs infesting the orchard. By developing an automated flight protocol, they were able to remotely pilot the drone using a mobile application, flying it over areas attacked by the insect.

The drone thus captured hundreds of excellent quality photos, which were then used for training. an AI algorithm capable of identifying bedbugs with 97% accuracy. Daniele Giannetti, researcher at the University of Parma and co-author of the study, said: “ This innovative monitoring system demonstrated the potential of integrating drones and AI to detect and quantify the presence of pests “.

Apart from this experiment, bedbug monitoring is an extremely tiring task. This was carried out mainly through the use of pheromone traps attracting insects, followed by manual counting. A very widespread method, but labor costs are very high and it is much more limited in its effectiveness if we compare it to the drone+AI method.

During the drone’s flights, the researchers witnessed some unexpected behavior from the bedbugs. Far from fleeing or falling from the plants, the pests remained perfectly still while the drone flew over them at heights of between 4 and 8 meters. Nearly 85% of the specimens observed exhibited this freezing behavior.. A phenomenon that allowed the drone to capture photos of excellent clarity, with the bedbugs appearing clearly in the frame. Of the 2,459 images captured by the drone, 402 contained bedbugs.

The researchers then manually annotated these photos in order to train the artificial intelligence algorithm, which proved extremely effective in identifying pests in other shots. Although the study focused on bedbugs, scientists believe that the same principles could be applied to monitoring other pestsby exploiting drone images to train AI models specialized in this task.

The integration of drones and artificial intelligence in the agricultural sector therefore opens exciting prospects for crop management and pest control. Lara Maistrello, professor at the University of Modena and co-author of the study, was particularly convinced: “ This experience is really promising. We welcome these results with keen interest, particularly because of the wide range of future applications “. Indeed, other applications are imaginable and just as attractive : soil analyses, monitoring of weed expansion, optimization of irrigation, etc.

  • Italian researchers have developed a new type of protocol to monitor a pear orchard infested with bedbugs.
  • They used a drone equipped with a camera and fed with AI algorithms to spot bedbugs in trees.
  • A much more effective method than traditional methods, which could be applied to other areas of the agricultural sector.

📍 To not miss any news from Presse-citron, follow us on Google News And WhatsApp.