A Multi-Model Deep Learning Framework for Precise Detection of Potato Leaf Diseases

A variety of leaf diseases that can negatively impact crop output and quality present major problems to the development of potatoes. In this paper, a multi-model deep learning approach utilizing single convolutional neural networks (SCNN), long short-term memory networks (LSTM), and convolutional neural networks (CNN) is presented for the detection of potato leaf disease. The CNN classifies diseases in potato leaves based on RGB images, the LSTM analyzes temporal patterns, and the SCNN focuses on spatial features. Trained on a diverse dataset, the models are evaluated using performance metrics and compared with traditional methods, showcasing the effectiveness of deep learning. The CNN model is deployed as a user-friendly application for real-time disease prediction, enhancing practical usability in agriculture. This comprehensive approach offers a versatile solution for automated potato leaf disease detection, benefiting farmers in crop health management.