“Explainable AI for Plant Leaf Disease Classification: Enhancing Transparency and Trust in Deep Learning Models”
Keywords:
Explainable Artificial Intelligence (XAI); Plant Leaf Disease Classification; Deep Learning; Convolutional Neural Networks; Grad-CAM; LIME; SHAP; Precision Agriculture; Model InterpretabilityAbstract
Plant diseases pose a serious challenge to global agricultural productivity, food security, and sustainable farming practices. In recent years, deep learning models—particularly Convolutional Neural Networks (CNNs)—have demonstrated remarkable success in automatically identifying and classifying plant leaf diseases from image data. Despite their high predictive accuracy, most deep learning systems function as “black boxes,” offering little insight into how decisions are made. This lack of transparency limits trust, adoption, and practical deployment among farmers, agronomists, and agricultural policymakers.
The present study explores the integration of Explainable Artificial Intelligence (XAI) techniques into deep learning–based plant leaf disease classification systems to enhance transparency, interpretability, and user trust. The research systematically evaluates popular CNN architectures for plant disease detection and applies post-hoc explainability methods such as Gradient-weighted Class Activation Mapping (Grad-CAM), Local Interpretable Model-agnostic Explanations (LIME), and SHapley Additive exPlanations (SHAP) to interpret model predictions.
Through comparative experimentation on benchmark plant leaf image datasets, this study demonstrates that explainable models can maintain high classification accuracy while providing meaningful visual and feature-based explanations of disease predictions. The findings highlight the importance of explainability in bridging the gap between advanced AI models and real-world agricultural decision-making. This research contributes to the development of trustworthy, transparent, and farmer-centric AI solutions for precision agriculture.
References
Abade, A. S., Ferreira, P. A., & Vidal, F. (2021). Plant disease identification using convolutional neural networks. Computers and Electronics in Agriculture, 184, 106078.
Adadi, A., & Berrada, M. (2018). Peeking inside the black-box: A survey on explainable artificial intelligence. IEEE Access, 6, 52138–52160.
Barbedo, J. G. A. (2019). Plant disease identification from individual lesions using deep learning. Biosystems Engineering, 180, 96–107.
Bock, C. H., Poole, G. H., Parker, P. E., & Gottwald, T. R. (2010). Plant disease severity estimation using image analysis. Plant Disease, 94(8), 940–950.
Chattopadhay, A., et al. (2018). Grad-CAM++: Improved visual explanations for CNNs. WACV, 839–847.
Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608.
Ferentinos, K. P. (2018). Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, 145, 311–318.
Ghorbani, A., Abid, A., & Zou, J. (2019). Interpretation of neural networks is fragile. AAAI, 3681–3688.
Guidotti, R., et al. (2019). A survey of methods for explaining black box models. ACM Computing Surveys, 51(5), 1–42.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. CVPR, 770–778.
Hooker, S., et al. (2019). A benchmark for interpretability methods in deep neural networks. NeurIPS, 9737–9748.
Howard, A. G., et al. (2017). MobileNets: Efficient CNNs for mobile vision applications. arXiv preprint arXiv:1704.04861.
Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 147, 70–90.
Krizhevsky, A., Sutskever, I., & Hinton, G. (2012). ImageNet classification with deep CNNs. NeurIPS, 1097–1105.
LIME: Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). Why should I trust you? KDD, 1135–1144.
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. NeurIPS, 4765–4774.
Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in Plant Science, 7, 1419.
Nguyen, T. T., et al. (2022). Deep CNN-based plant disease detection using transfer learning. Artificial Intelligence Review, 55, 3671–3694.
Selvaraju, R. R., et al. (2017). Grad-CAM: Visual explanations from deep networks. ICCV, 618–626.
Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. ICLR.
Tan, M., & Le, Q. (2019). EfficientNet: Rethinking model scaling for CNNs. ICML, 6105–6114.
Too, E. C., et al. (2019). Fine-tuning deep learning models for plant disease identification. Computers and Electronics in Agriculture, 161, 272–279.
Tjoa, E., & Guan, C. (2020). A survey on explainable artificial intelligence. IEEE Transactions on Neural Networks, 32(11), 4793–4813.
Zhang, Q., Zhu, S. C. (2018). Visual interpretability for deep learning. Frontiers of Information Technology, 1–14.
Zhou, B., et al. (2016). Learning deep features for discriminative localization. CVPR, 2921–2929.
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
