Precision Diagnosis of Wheat Bunt Disease: A Hybrid CNN-RNN Model for Multi Classification

Wheat bunt disease may have a significant influence on crop productivity, thus it's important to accurately categorize its severity so that the disease's effects can be mitigated and food security can be maintained. For the multi-classification of wheat bunt disease depending on severity levels, this study provides a hybrid deep learning (DL) model that incorporates a convolutional neural network (CNN) and recurrent neural network (RNN). The model is trained and evaluated using a dataset of 12,000 photos that depict varying degrees of severity. The suggested model achieves better results than the current state-of-the-art models, with an overall accuracy of 93.97%. High precision for severe illness symptoms is revealed, with 96.25% to 95.48% for severity levels 1 and 3, respectively, in the study's full investigation of the model's performance. There is, however, potential for improvement, since accuracy for severity level 4. This hybrid CNN-RNN model has shown promise for early disease detection and classification in wheat crops, as seen by its successful application. This study demonstrates the revolutionary impact of DL algorithms in precision agriculture and crop management, and it makes an important contribution to the field of agricultural disease control.