Advancing Precision Agriculture with Deep Learning and IoT Integration for Effective Tomato Pest Management
Mohamed Zarboubi, Samira Chabaa, Azzedine Dliou
Abstract
The escalating global demand for agricultural products, notably tomatoes, accentuates the urgency of efficient pest management. Notable pests including Helicoverpa Armigera, Fruit Fly, and Whiteflies present formidable threats to tomato crops. This study introduces an innovative paradigm by seamlessly integrating cutting-edge technologies deep learning and the Internet of Things (IoT) to redefine conventional pest management strategies. Through a portable Pest Counting Device that harnesses the YOLOv8 deep learning model on a Raspberry Pi 4B, in conjunction with the Firebase IoT platform, real-time monitoring of pheromone traps becomes feasible. This integration empowers farmers to optimize pest control measures through informed decision-making. By capitalizing on the synergy between advanced technologies, farmers stand to achieve enhanced crop yields while transforming the landscape of traditional pest management approaches. This holistic solution not only empowers farmers but also mitigates the environmental footprint associated with conventional pest control practices, demonstrating the potential of technology to reshape agriculture towards sustainability in the context of persistent pest challenges.