DEEP LEARNING TECHNIQUES FOR EARLY DETECTION OF PADDY LEAF DISEASES IN PRECISION AGRICULTURE

Rice (Paddy) is a major stable crop globally, yet its productivity is significantly impacted by various leaf diseases, often identified too late for effectivity intervention.With the advancement of smart farming, integrating Deep learning with Precision Agriculture technology offer a promising solution for early disease detection and prevention.This research aims to develop an intelligent system that monitors paddy crops in real time using high-resolution field images and sensor data.Convolution Neural Network (CNN) and advanced images classification models are employed to accurately detect and classify major paddy leaf disease such as Blast, Bacterial Leaf Blight, and Brown Spot.The system further analyzes environmental factor such as humidity, temperature, and nutrients levels to predict disease outbreak risks and suggest timely control measures.By providing automated early alerts and data-driving recommendations, the system enhances crop health monitoring , reduces chemical usage, and supports sustainable agriculture practices.This study demonstrates the potential of deep learning-enabled precision agriculture to strengthen food security and boost farmer productivity.