Advanced Deep Learning Techniques for Red Rot Disease Prediction in Sugarcane

Red rot disease poses a significant threat to sugarcane production worldwide, impacting crop yield and quality Agriculture. In this study, we propose a Convolutional Neural Network (CNN) approach for accurate prediction of red rot disease based on image analysis of sugarcane leaves. The dataset, comprising 1030 images sourced from Kaggle and other repositories, underwent preprocessing to standardize image quality and format. The CNN model architecture involves three pairs of convolutional and max pooling layers for feature extraction, followed by dense layers for classification. The model was trained using 70% of the dataset and evaluated on the remaining 30%. Results demonstrate the CNN’s efficacy, achieving an overall accuracy of 93.5%. Comparative analysis with traditional machine learning classifiers such as SVM and KNN reveals superior performance, with CNN outperforming these methods by achieving 93.75% accuracy on testing images. The study highlights CNN’s capability in automated detection of red rot disease in sugarcane, providing a robust tool for agricultural disease management and crop protection.