Monitoring and Identifying Paddy Leaf Diseases Using Unmanned Aerial Vehicles (UAVs) with Machine Learning- A Survey

Paddy leaf diseases substantially threaten global rice production, resulting in significant crop yield losses and economic implications. Therefore, timely detection and accurate identification of these diseases are imperative for effective management strategies. Recent advancements in agricultural technologies have led to Unmanned Aerial Vehicles (UAVs) emerging as a promising tool for crop monitoring due to their capability to provide higher-resolution and real-time data. This research paper aims to afford a comprehensive outline of the use of UAVs in monitoring and identifying paddy leaf diseases, shedding light on their potential applications, challenges, and prospects. This paper showcases the pivotal role of UAVs in transforming disease monitoring practices in paddy fields. Equipped with sophisticated cameras and sensors, UAVs can capture aerial images and multispectral data of vast agricultural areas efficiently. These data can then be processed and analyzed using state-of-the-art image processing and machine-learning algorithms to identify disease symptoms, classify disease types, and assess the severity of infections. The paper delves into the various UAV-based disease identification techniques, elaborating on image processing methods employed for feature extraction, such as image segmentation, texture analysis, and color space transformations. Finally, the research paper addresses the prospects of UAVs in paddy leaf disease monitoring. The paper also suggests directions for further research on real-time disease mapping and automated spraying systems based on UAV data, aiming to optimize disease management efforts. Applications based on UAVs should dynamically implement pest and nutrient management approaches.