Machine Learning-Based Approaches for Early Detection of Bacterial Infections in Rice Crops

In India, rice is a vital crop cultivated extensively across various regions. The timely detection and management of rice diseases are critical for maximizing yields and minimizing crop damage. Early detection and intervention play a crucial role in maintaining high production levels and sustaining the agricultural economy. Bacterial infections, such as Bacterial Leaf Blight, Panicle Blight, and Leaf Streak, pose a significant threat to rice productivity and global food security. Environmental factors, including strong winds, heavy rainfall, extreme temperatures, humidity, and excessive nitrogen fertilizer use, exacerbate the spread of these diseases. This study introduces a machine learning-based approach for the early detection of bacterial rice diseases using image processing and Convolutional Neural Networks (CNNs). By detecting diseases such as Leaf Blight, Panicle Blight, and Leaf Streak in the early stages, this method improves disease management and reduces crop losses. The CNN model achieved an accuracy of 77%, demonstrating its potential for providing timely and effective solutions to protect crop yields. By recognizing early signs of bacterial infections and implementing preventive strategies, farmers can safeguard their rice crops and ensure successful harvests, contributing to food security