Meta-Learning Based Stacking of CNN, SVM, and Random Forest for Multi-Species Crop Leaf Pathology Recognition

Abstract

Accurate identification of crop leaf diseases is essential for sustainable agriculture, yet variations in leaf morphology and disease symptoms across species remain challenging for traditional machine learning approaches. This study proposes a meta-learning–based stacking ensemble that integrates Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and Random Forest Classifiers (RFC) for multi-species leaf pathology recognition, evaluated on apple and tomato datasets. Each base model independently learns discriminative visual features, and their class-probability outputs are fused through an RBF-SVM meta-learner. Experimental results show that individual models achieve accuracies of 89% (CNN), 88% (SVM), and 85% (RFC), while the proposed stacking ensemble significantly outperforms them with an accuracy of 98% and macro and weighted F1-scores of 0.975. These results demonstrate the effectiveness of heterogeneous meta-learning ensembles in enhancing robustness and generalization for multi-species crop disease classification.