Advances in Machine Learning and Deep Learning for Automated Banana Disease Detection: A Comprehensive Survey

Banana plants are a crucial agricultural crop worldwide, yet they are vulnerable to various diseases that can drastically impact yield and quality. Traditional methods of disease detection in banana cultivation rely heavily on manual inspection, which is labor-intensive, error-prone, and lacks scalability. In recent years, machine learning (ML) and deep learning (DL) models have shown significant potential in automating and enhancing disease detection in agriculture. This survey explores the application of ML and DL models for banana disease detection, reviewing techniques such as supervised learning, feature engineering, convolutional neural networks (CNNs), and transfer learning. A comparative analysis of these approaches reveals differences in performance metrics such as accuracy, precision, and scalability. Additionally, we address challenges in data acquisition, model generalization across varied environmental conditions, and computational limitations. This survey aims to provide insights into the current state of ML and DL in agricultural disease detection, highlighting opportunities for future research to improve model robustness and practical deployment in banana farming.