TLNet: A Novel Model to Detect Wheat Leaf Diseases Using Deep Neural Network Architecture

Wheat crop diseases are a major challenge to food security, significantly impacting agricultural yields worldwide. Timely detection and effective management of these diseases are essential to reduce crop losses. Recent advances in deep learning have demonstrated potential in automating disease identification in crops. This research presents a novel approach for detecting wheat crop diseases using a Convolutional Neural Network (CNN) model. The CNN architecture is designed for optimal efficiency and flexibility, making it well-suited for deployment across various computational platforms, such as mobile and edge devices. By incorporating transfer learning and attention mechanisms, the model achieves high accuracy in disease diagnosis. It has been evaluated using a dataset of wheat leaf images, encompassing diseases like yellow rust, leaf blotch, and powdery mildew. Evaluation of the system on these images, sourced from the Plant Village Repository, shows that the model achieves an accuracy of 87%. This method provides a practical solution for early detection of wheat crop diseases, enabling timely action to reduce yield loss and support food security.