AI-Driven Deep Learning Models for Efficient Sugarcane Leaf Disease Diagnosis

This study explores the application of deep learning techniques to identify and classify the health status of sugarcane leaves, focusing on three categories: healthy, rust, and yellow leaf disease. A convolutional neural network (CNN) was developed and trained on a dataset of sugarcane leaf images, achieving an accuracy of 97%. The model's performance was compared with traditional machine learning algorithms, including Support Vector Machine (SVM) and K-Nearest Neighbors (KNN), which achieved accuracies of 95% and 90%, respectively. The CNN model's superior accuracy underscores its effectiveness in disease prediction and classification, offering a valuable tool for farmers to manage sugarcane crop health. The study suggests future work to further refine the model by experimenting with various learning rates, optimizers, and additional models to enhance predictive performance.