What is it about?
This work presents a smart, AI-powered pest monitoring system for apple orchards. It focuses on the real-time detection of codling moths (Cydia pomonella), a major pest that can seriously damage apple production. The system combines an improved YOLOv10-m deep learning model with IoT technology through a Raspberry Pi-based smart trap designed for field deployment. The proposed system captures insect images, automatically detects and counts codling moths, sends the results to an IoT dashboard, displays trap locations using GPS, and alerts farmers when pest numbers exceed a predefined threshold. Its main goal is to support Integrated Pest Management by helping farmers apply pesticides only when necessary, reducing unnecessary chemical use and promoting more sustainable and eco-friendly apple farming.
Featured Image
Photo by Iryna Mokhonko-Nosach on Unsplash
Why is it important?
This study is important because codling moths can cause serious damage to apple orchards, while traditional monitoring often relies on manual trap inspection, which is slow, costly, and time-consuming. The proposed system makes pest monitoring faster, smarter, and more practical by using AI and IoT to detect insects automatically and transmit real-time information to farmers. This helps farmers identify when and where intervention is needed, instead of applying pesticides routinely or excessively. As a result, this study proposes a system that can help reduce unnecessary pesticide use, limit environmental pollution, protect human health, save labor costs, and support more sustainable and eco-friendly apple farming.
Perspectives
This work opens several promising perspectives for the future of smart and sustainable pest management. First, the system can be improved by collecting more field images across different seasons, regions, and environmental conditions, allowing the AI model to become more robust and accurate over time. Second, the smart trap could be connected to a dedicated IoT platform and mobile application, giving farmers easier access to real-time pest data, trap locations, alerts, and decision-support tools. This would make the system more practical for large-scale orchard monitoring. Third, future versions could integrate additional functions, such as automatic pesticide recommendation, disease detection on apple leaves, and predictive models to anticipate pest outbreaks before they become severe. Finally, this approach could be adapted to other crops and pests, making it a scalable solution for precision agriculture, Integrated Pest Management, and eco-friendly farming.
Mohamed Zarboubi
Read the Original
This page is a summary of: Towards eco-friendly apple farming: Real-time codling moth monitoring using improved YOLOv10 and IoT integration, PLOS One, April 2026, PLOS,
DOI: 10.1371/journal.pone.0346415.
You can read the full text:
Resources
Contributors
The following have contributed to this page
