A Deep Learning Hybrid Approach for Automated Leaf Disease Identification in Paddy Crops

The agriculture sector is facing unprecedented chal-lenges, including the need to increase crop yields to meet rising global food demand. Paddy agriculture provides a significant portion of the global population's food supply, therefore finding innovative ways to increase productivity and resource utilization is critical. This study proposes an intelligent automated approach using deep learning techniques to boost paddy crop productivity. We employed a deep learning hybrid model comprising Convo-lutional Neural Networks (CNN) and Support Vector Machine (SVM) classifier to predict the presence of three common paddy leaf diseases: brown spot, bacterial leaf blight, and leaf smut. The proposed system is implemented as a web application that uses deep learning approach to predict diseases. With this technology, diseases can be recognized and diagnosed early on, allowing for rapid treatment to reduce output losses and ensure paddy crop sustainability. The proposed model exhibits excellent accuracy, with an accuracy rate of over 98 %. Deep learning predictions of paddy leaf diseases help farmers in a variety of ways, including early detection and intervention, improved resource management, greater crop productivity and quality, reduced dependency on pesticides, and increased food security. This allows farmers to optimize their farming operations for increased productivity and sustainability, as well as make more informed decisions.