Deep Learning for Early Disease Detection in Sugarcane: Advancing Agricultural Productivity and Sustainability

Abstract

A vital revenue crop for many agricultural economies throughout the world, sugarcane is used extensively in both industrial and food production.  However, a number of illnesses that negatively impact crop output and quality frequently make it difficult to cultivate.  For efficient crop management and to reduce losses, early and precise detection of these diseases is crucial.  In order to detect and categorize sugarcane leaf illnesses using image data, this study proposes a hybrid deep learning model that combines Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. While the CNN component effectively collects spatial characteristics from the pictures, the LSTM layer models contextual information to improve classification performance and capture sequential relationships.  The suggested hybrid model is compared to conventional deep learning techniques after being trained and assessed using an extensive dataset of photos of sugarcane leaves.  Based on experimental results, the hybrid CNN-LSTM model is a dependable option for intelligent agriculture management and real-time disease monitoring as it provides greater accuracy, precision, and resilience.