Mitigating Mustard Downy Mildew Disease: Early Detection and Prevention through a Hybrid CNN-SVM Model

Mustard Mustard (Brassica spp.) crops are threatened all over the world by Downy Mildew Disease, brought on by the fungus Hyaloperonospora parasitica. By combining the strengths of a Convolutional Neural Network (CNN) and a Support Vector Machine (SVM), the proposed study provides a novel approach to illness prevention. The investigation begins with a large collection of over 33,000 high-resolution photos depicting mustard plants in varying stages of infection by Downy Mildew. The hybrid model harnesses the feature extraction skills of the CNN and the classification power of the SVM, attaining an amazing accuracy of 96.1%, with precision, recall, and F1-Score measures proving its proficiency. In particular, the model’s early detection capabilities allow for preventative measures to be taken, as Downy Mildew can often be detected before any outward signs appear. Disease rates are lowered and crop yields are increased after practical implementation into agricultural operations. Its versatility is demonstrated by its robust generalization across different regions. Analyses showing the model’s advantage over conventional disease detection approaches are presented. The consequences of this study go far beyond the development of mustard, ushering in a new era in agriculture in which farmers move from reactive to proactive disease management. It lays out a strategy for applying cutting-edge AI-driven models to agriculture to improve sustainability, raise yields, and decrease monetary losses.