Revolutionizing UAV: Experimental Evaluation of IoT-Enabled Unmanned Aerial Vehicle-Based Agricultural Field Monitoring Using Remote Sensing Strategy

Agricultural monitoring has evolved significantly with the advent of unmanned aerial vehicles (UAVs), which offer innovative solutions for precision farming. Traditional agricultural practices often rely on manual inspection and limited ground-based sensors, which can be time-consuming and prone to inaccuracies. This paper explores the integration of UAV and ground-based IoT sensor data through advanced data fusion techniques to enhance data reliability and precision. Our hybrid machine learning model (HMLM), combining random forest and support vector machine algorithms, is employed for accurate crop health assessment, disease detection, and yield prediction. The implementation of UAV-based agricultural monitoring systems leverages the unique capabilities of quadcopters and fixed-wing UAVs. Quadcopters are utilized for detailed field surveys and spot checks, offering high-resolution imaging for precise inspections, while fixed-wing UAVs are deployed for large-scale monitoring, providing extensive coverage and long-flight endurance. Equipped with advanced IoT devices and sensors, including multispectral and hyperspectral cameras, GPS modules, and real-time communication systems, these UAVs enable comprehensive data collection and analysis. Our hybrid machine learning model (HMLM) improves classification accuracy and predictive power, achieving an impressive accuracy of 98.74%, leading to precise crop management and higher yields.