Optimized Deep Learning Approaches for Sugarcane Leaf Disease Classification Using CNN Model

Sugarcane is a crucial agricultural crop that is extensively grown in tropical and subtropical areas. It plays a vital role in the global economy by significantly contributing to the production of sugar, ethanol, and various other byproducts. Nevertheless, sugarcane cultivation encounters substantial obstacles caused by diverse diseases that affect the crop's quantity and quality. Conventional disease diagnosis techniques heavily depend on visual examinations conducted by specialists, which are time-consuming, subjective, and susceptible to human mistakes. Given these constraints, there is a pressing requirement for automated and dependable systems that can promptly detect and categorize diseases, thereby assisting in managing extensive agricultural operations. This study aims to create a strong Convolutional Neural Network (CNN) model that can accurately classify sugarcane leaf diseases. The model will focus on five categories: Healthy, Mosaic, Red Rot, Rust, and Yellow. The proposed model utilizes large datasets and sophisticated computational techniques to identify complex patterns related to these diseases. This improves disease management practices, reduces the need for manual inspections, and ultimately supports the long-term viability and profitability of sugarcane farming. The results indicate that the model attains a high level of accuracy in categorizing various sugarcane leaf diseases, highlighting its capacity to enhance agricultural productivity and guarantee food security significantly. This study adds to the expanding pool of information on the utilization of deep learning in agriculture and emphasizes the significance of interdisciplinary cooperation in creating inventive solutions for real-world issues in crop management.