In recent years, agriculture has witnessed significant advancements driven by modern technology, particularly in enhancing crop productivity and optimizing orchard management. Traditionally, tasks such as crop counting and production estimation were labor-intensive and time-consuming, relying heavily on manual methods. However, the rise of precision agriculture has dramatically transformed these processes. Integrating drones with the Internet of Things (IoT) has become essential for acquiring crucial data. These advanced technologies facilitate rapid and accurate large-scale data collection, providing insights that were previously unattainable. By employing machine learning (ML) and deep learning (DL) models to analyze this data, we can effectively implement these models alongside customized training strategies tailored to factors such as agricultural object types, image resolutions, and specific crop characteristics. In this study, we explored the application of ML and DL techniques within drone-enabled IoT networks for managing apricot crops. When benchmarked against other leading methods, YOLOv10 achieved an F1 Score of 88%. Additionally, linear regression was applied for yield prediction, resulting in a Relative Error of 2.18% across the selected trees. These results underscore the remarkable potential of ML and DL technologies in revolutionizing precision agriculture. This chapter provides a thorough exploration of these transformative applications.