<p>Diseases affecting plant leaves pose a major challenge to agricultural output and global food supply, highlighting the urgent need for reliable and precise identification techniques. Traditional techniques often suffer from overfitting, high computational complexity, and limited real-world applicability. To address these challenges, this article develops a novel hybrid model named Weighted Kernel Random Support Vector-based Random update Greylay Goose algorithm. This approach integrates Kernel Support Vector Machine for extracting complex features from leaf images and Random Forest for robust classification, combined through a weighted ensemble mechanism. To improve both accuracy and generalization, the model’s parameters were fine-tuned using the GreylayGoose Optimization algorithm. Comprehensive experiments were carried out on five benchmark datasets. The results demonstrated the superior performance of the proposed method in comparison with existing techniques. The model attained a high classification accuracy of 98.76%, accompanied by low error metrics and a strong Matthews Correlation Coefficient of 0.938, reflecting its robustness and reliability in identifying plant leaf diseases. These results confirm the Weighted Kernel Random Support Vector-based Random update Greylay Goose algorithm model’s effectiveness in real world plant disease identification, contributing significantly to smart agriculture and sustainable crop management.</p>