Northern Corn Leaf Blight Disease Detection Using CNN-Based Deep Learning Model

In the new digital era and information age, agriculture automation is essential. Early identification of plant diseases is crucial since it plays an important role in the plant's yield and the farmers’ well-being. In South Africa, two commercially significant maize diseases are Fusarium ear rot and Northern Corn Leaf Blight (NCLB), both caused by Exserohilum turcicum. In corn cultivation, the disease northern corn leaf blight causes up to 50% loss in the yield. The detection of NCLB must be automated with high accuracy to help the farmers. The detection and classification of plant diseases, such as the northern corn leaf blight (NCLB), has become a focal point of research in agricultural plant protection. The study of NCLB has emerged as a significant area for investigating methods and techniques related to plant disease detection. By incorporating and applying deep learning techniques for plant disease recognition, we can alleviate the adverse consequences of manually selecting disease spot features. This approach enhances the precision of extracting plant disease features, fosters rapid technological advancement, and brings significant benefits to the farming community. By leveraging cutting-edge deep learning techniques, the paper discusses the current trends and challenges in recognizing plant leaf diseases. Notably, the study employs a deep learning model based on convolutional neural networks (CNN) to effectively detect northern corn leaf blight (NCLB).