Answers are grounded in this paper and cite their sources.
Proper identification of apple leaf diseases is an important issue towards safeguarding crop production as well as the management sustainability of orchards. Manual diagnosis is widely used but is not efficient, is subjective, and cannot easily support large-scale monitoring. This paper presents a Hybrid Deep Learning and Sparse Classification Framework, which combines YOLOv8-based deep feature extraction with L1-regularized machine learning models to achieve efficient and interpretable disease recognition. A dataset of 4,006 high-resolution apple leaf images covering 9 classes Alternaria leaf spot, Brown spot, Frogeye leaf spot, gray spot, Healthy, Mosaic, Powdery mildew, Rust, and Scab was used. After 60 epochs, YOLOv8 attained a mean Average Precision (mAP) of 98.10% at IoU 0.5, a precision of 95.16%, and a recall of 95.97%. The resulting 3,648-dimensional feature space was narrowed down to 319 dimensions using Lasso feature selection, achieving 13.48% sparsity without losing important discriminatory information. The Lasso model achieved the best test accuracy of 97.50% and the highest cross-validation accuracy of 98.78%, outperforming the L1-regularized Logistic Regression and Random Forest baselines among the compared classifiers. Sparse regularization not only reduced overfitting but also improved model interpretability by forcing the model to focus on the visual patterns of the diseases. The proposed model is a computationally efficient, scalable, and interpretable AI solution for real-time agricultural diagnostics. It offers a promising direction for precision farming systems that can detect diseases early, protect yields, and support better decision-making based on interpretable hybrid intelligence.
No takes yet. Share an insight, caveat, or question.
Neware et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: