Explainable Deep Learning for Multi-Class Plant Disease Classification Using ResNet and EfficientNet with Grad-CAM Analysis
DOI:
https://doi.org/10.52958/iftk.v22i2.14396Keywords:
Plant Disease Classification, Convolutional Neural Network, ResNet50, EfficientNetB0, Grad-CAMAbstract
Plant diseases can reduce crop quality and productivity, making early detection an important aspect of modern agriculture. Recent advances in deep learning, particularly Convolutional Neural Networks (CNN), have shown promising performance in image-based plant disease classification. This study proposes an explainable deep learning approach for multi-class plant disease classification using ResNet50 and EfficientNetB0 combined with Grad-CAM visualization. The experiments were conducted using the PlantVillage dataset consisting of 15 classes of healthy and diseased plant leaves.The research process included image preprocessing, data augmentation, transfer learning, model training, performance evaluation, and explainability analysis. The dataset was divided into training and validation sets with a ratio of 80:20. Model performance was evaluated using accuracy, loss, confusion matrix, precision, recall, and f1-score metrics. Experimental results showed that ResNet50 achieved the best performance with an accuracy of 92% and a validation loss of 0.19, outperforming EfficientNetB0 which obtained 76% accuracy and 0.82 validation loss. The classification report demonstrated that ResNet50 provided more stable and consistent predictions across most disease classes. Furthermore, Grad-CAM visualization successfully highlighted disease-relevant regions such as lesions, discoloration, and damaged leaf areas, improving the interpretability of the CNN model. The findings indicate that the combination of ResNet50 and Grad-CAM is effective for plant disease classification and provides better explainability for deep learning-based agricultural applications.
References
M. G. Pradana, H. Khoirunnisa, and I. W. R. Pinastawa, “Evaluation of Convolutional Neural Network Model Architecture Performance,” pp. 628–632, 2023, doi: https://doi.org/10.1109/icimcis60089.2023.10349075
M. G. Pradana, “YOLOv8-Based Microplastic Detection and Quantification in River Water Microscopic Images,” Journal of Applied Data Sciences, vol. 7, no. 2, pp. 1533–1544, May 2026, doi: https://doi.org/10.47738/jads.v7i2.1262
D. R. Maulana, M. G. Pradana, and M. P. Muslim, “Handwriting Classification of Sundanese Script Using LBP Feature Extraction and CNN,” in 2024 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), IEEE, Nov. 2024, pp. 1079–1084. doi: https://doi.org/10.1109/ICIMCIS63449.2024.10956206
D. Arisandi, A. Khoerunnisa, R. Subekti, A. Eko Setiawan, and C. Ramdani, “Performance Evaluation of CLAHE-Enhanced Edge Detection on Low-Light Faces,” Journal of Computing Innovations and Emerging Technologies, vol. 1, no. 1, pp. 7–10, Jul. 2025, doi: https://doi.org/10.64472/jciet.v1i1.2
I. W. R. Pinastawa, M. G. Pradana, and K. Khoironi, “Edge Detection Model Performance Using Canny, Prewitt and Sobel in Face Detection,” Sinkron, vol. 8, no. 2, pp. 623–631, Mar. 2024, doi: https://doi.org/10.33395/sinkron.v8i2.13497
L. Qiao et al., “UAV-based chlorophyll content estimation by evaluating vegetation index responses under different crop coverages,” Comput. Electron. Agric., vol. 196, p. 106775, May 2022, doi: https://doi.org/10.1016/j.compag.2022.106775
I. Pacal et al., “A systematic review of deep learning techniques for plant diseases,” Artif. Intell. Rev., vol. 57, no. 11, p. 304, Sep. 2024, doi: https://doi.org/10.1007/s10462-024-10944-7
T. D. Salka, M. B. Hanafi, S. M. S. A. A. Rahman, D. B. M. Zulperi, and Z. Omar, “Plant leaf disease detection and classification using convolution neural networks model: a review,” Artif. Intell. Rev., vol. 58, no. 10, p. 322, Jul. 2025, doi: https://doi.org/10.1007/s10462-025-11234-6
U. Mishra, A. Pandey, L. G, and T. K, “Deep learning-based disease detection in potato and mango leaves: a comparative study of CNN, AlexNet, ResNet, and EfficientNet,” Sci. Rep., vol. 16, no. 1, p. 2788, Dec. 2025, doi: https://doi.org/10.1038/s41598-025-32607-5
M. Thanjaivadivel, C. Gobinath, J. Vellingiri, S. Kaliraj, and J. S. Femilda Josephin, “EnConv: enhanced CNN for leaf disease classification,” Journal of Plant Diseases and Protection, vol. 132, no. 1, p. 32, Feb. 2025, doi: https://doi.org/10.1007/s41348-024-01033-6
P. Mahapatra, M. Panda, S. K. Dash, and U. K. Sahu, “Advancing plant disease classification using an attention-based CNN for intra-dataset and cross- dataset training,” Sci. Rep., vol. 16, no. 1, p. 10925, Mar. 2026, doi: https://doi.org/10.1038/s41598-026-45464-7
U. V. Nnamdi and V. Abolghasemi, “Optimised MobileNet for very lightweight and accurate plant leaf disease detection,” Sci. Rep., vol. 15, no. 1, p. 43690, Dec. 2025, doi: https://doi.org/10.1038/s41598-025-27393-z
K. Sahu et al., “Plant disease detection using a hybrid dilated CNN with attention mechanisms and optimized mask RCNN segmentation,” Sci. Rep., vol. 15, no. 1, p. 42008, Nov. 2025, doi: https://doi.org/10.1038/s41598-025-26192-w
Md. S. Islam Sobuj, Md. I. Hossen, Md. F. Mahmud, and M. U. Islam Khan, “Leveraging Pre-trained CNNs for Efficient Feature Extraction in Rice Leaf Disease Classification,” in 2024 International Conference on Advances in Computing, Communication, Electrical, and Smart Systems (iCACCESS), IEEE, Mar. 2024, pp. 01–06. doi: https://doi.org/10.1109/iCACCESS61735.2024.10499603
K. Gopalan, S. Srinivasan, . P., M. Singh, S. K. Mathivanan, and U. Moorthy, “Corn leaf disease diagnosis: enhancing accuracy with resnet152 and grad-cam for explainable AI,” BMC Plant Biol., vol. 25, no. 1, p. 440, Apr. 2025, doi: https://doi.org/10.1186/s12870-025-06386-0
Md. J. Karim, Md. O. F. Goni, Md. Nahiduzzaman, M. Ahsan, J. Haider, and M. Kowalski, “Enhancing agriculture through real-time grape leaf disease classification via an edge device with a lightweight CNN architecture and Grad-CAM,” Sci. Rep., vol. 14, no. 1, p. 16022, Jul. 2024, doi: https://doi.org/10.1038/s41598-024-66989-9
F. S. A. M. and K. B. R., “Enhancing multiclass plant disease classification using GAN-boosted vision transformer with XAI insights,” Front. Plant Sci., vol. 16, Jan. 2026, doi: https://doi.org/10.3389/fpls.2025.1649399
Md. J. Karim, Md. O. F. Goni, Md. Nahiduzzaman, M. Ahsan, J. Haider, and M. Kowalski, “Enhancing agriculture through real-time grape leaf disease classification via an edge device with a lightweight CNN architecture and Grad-CAM,” Sci. Rep., vol. 14, no. 1, p. 16022, Jul. 2024, doi: https://doi.org/10.1038/s41598-024-66989-9
S. Murugesan, J. Chinnadurai, S. Srinivasan, S. K. Mathivanan, R. R. Chandan, and U. Moorthy, “Robust multiclass classification of crop leaf diseases using hybrid deep learning and Grad-CAM interpretability,” Sci. Rep., vol. 15, no. 1, p. 29955, Aug. 2025, doi: https://doi.org/10.1038/s41598-025-14847-7
M. J. Hoque and Md. S. Islam, “An Explainable and Lightweight CNN Framework for Robust Potato Leaf Disease Classification Using Grad-CAM Visualization,” Applied AI Letters, vol. 7, no. 1, Feb. 2026, doi: https://doi.org/10.1002/ail2.70011
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Wahyuni Zalmi, Rahmi Putri Kurnia, Dyah Listianing Tyas
This work is licensed under a Creative Commons Attribution 4.0 International License.
KEBIJAKAN YANG DIAJUKAN UNTUK JURNAL YANG MENAWARKAN AKSES TERBUKA
Syarat yang harus dipenuhi oleh Penulis sebagai berikut:
- Penulis menyimpan hak cipta dan memberikan jurnal hak penerbitan pertama naskah secara simultan dengan lisensi di bawah Creative Commons Attribution License yang mengizinkan orang lain untuk berbagi pekerjaan dengan sebuah pernyataan kepenulisan pekerjaan dan penerbitan awal di jurnal ini.
- Penulis bisa memasukkan ke dalam penyusunan kontraktual tambahan terpisah untuk distribusi non ekslusif versi kaya terbitan jurnal (contoh: mempostingnya ke repositori institusional atau menerbitkannya dalam sebuah buku), dengan pengakuan penerbitan awalnya di jurnal ini.
- Penulis diizinkan dan didorong untuk mem-posting karya mereka online (contoh: di repositori institusional atau di website mereka) sebelum dan selama proses penyerahan, karena dapat mengarahkan ke pertukaran produktif, seperti halnya sitiran yang lebih awal dan lebih hebat dari karya yang diterbitkan. (Lihat Efek Akses Terbuka).
