Utilizing Deep Learning Techniques for the Automated Diagnosis and Management of Diseases Affecting Wheat Plants

The need for automated diagnosis and management of wheat plant diseases is increasingly recognized by agricultural professionals. Accurate identification of foliar diseases in wheat is essential for effective crop management strategies. This research introduces the Wheat Leaf Convolutional (WLC) model, an enhancement of the VGG16 architecture, aimed at detecting and classifying six distinct types of foliar diseases through deep learning methodologies. The model is trained on a dataset of wheat leaf images, which has been augmented using generative adversarial networks (GANs) to enhance its generalization capabilities. The WLC model achieved an impressive accuracy of 94.88%, significantly surpassing traditional CNN models like ResNet-50, AlexNet, and MobileNet. Performance metrics such as recall, precision, and F1 score were assessed across six disease categories: leaf rust, black scale, powdery mildew, wheat streak, Septoria, and healthy plants. The experimental findings indicate that the WLC model effectively and accurately detects diseases, positioning it as a valuable resource for real-time applications in precision agriculture. This research advances the field of wheat disease diagnosis, facilitating prompt interventions and improved farming practices.