This study explores the integration of machine learning (ML) technologies in precision agriculture, with a specific focus on the application of drones equipped with advanced sensors. The core of this research lies in the deployment of Artificial Intelligence (AI) algorithms to facilitate real-time identification and classification of key agricultural factors, particularly crop health. In this work, YOLOv8 is trained on annotated datasets comprising both RGB and Normalized Difference Vegetation Index (NDVI) images and its performance was compared with Support Vector Machine (SVM) algorithm. The study reveals that YOLOv8 exhibits superior performance compared to SVM for both types of images, achieving an average accuracy rate of 86.5%. This highlights the pivotal role of integrating drone technology and sensory vision in revolutionizing precision agriculture, offering valuable insights into the future of smart cities and sustainable farming, especially in areas with limited water resources.