MODERN AGRICULTURE SYSTEMS: ENHANCING PRECISION FARMING THROUGH ADVANCED AERIAL TECHNIQUES

Resumen

In modern agriculture, early detection and treatment of crop diseases and pests are necessary for increasing yields and ensuring food security. Traditional methods are labor-intensive and time-consuming, leading to inefficiencies and delayed responses. This research presents a solution using drones for continuous monitoring and automated spraying of fertilizers and pesticides. Drones equipped with multispectral, thermal, and red, green, and blue (RGB) cameras collect high-resolution images of fields, which are then processed using machine learning techniques such as YOLOv5 for disease detection and Random Forest for fertilizer classification. Data is transmitted to an Internet of Things (IoT) platform, where it i1s analyzed to generate vegetation indices such as the Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI), which offer information on crop health. Upon detecting a disease, the system automatically triggers the drone’s spraying mechanism, ensuring targeted management. Field trials demonstrate the system’s ability to accurately detect diseases and optimize resource usage, improving crop health and yield. The integration of IoT enables real-time monitoring and alerts, allowing farmers to make informed decisions promptly. This study demonstrates the potential for combining drone technology, machine learning, and IoT to revolutionize agriculture, providing a scalable and efficient solution to modern farming challenges.