AI-Driven Diagnosis of Wheat Leaf Diseases: Integrating CNN and Random Forest

For billions of people globally, wheat (Triticum aestivum) is a staple; so, its health and yield are vital for both food security and a stable economy. Still, wheat crops are vulnerable to many diseases that can seriously lower output and quality. This work intends to establish an automated system for precise and early disease diagnosis in wheat using sophisticated technologies, especially Random Forest classifiers and Convolutional Neural Networks (CNN). Six main diseases—Leaf Rust, Stripe Rust, Stem Rust, Powdery Mildew, Septoria Leaf Blotch, and Tan Spot—have particular emphasis. Combining the capabilities of both techniques to improve detection performance, the proposed hybrid model uses CNNs for feature extraction from wheat leaf pictures and Random Forests for classification. With precision, recall, and F1-scores ranging from 94.70% to 97.66%, 95.96% to 97.10%, and 95.89% to 97.31%, respectively, experimental findings show the great accuracy of the model—classification accuracy of 99%. These results imply that the suggested model is a strong and dependable tool for real-time disease diagnosis, thereby maybe enhancing crop health and disease control in agricultural methods.