Journal Cover – Impact in Agriculture
Impact in Agriculture

Peer-Reviewed • Open Access e-ISSN: 3122-735X

Submit Your Manuscript
Article Open Access

SAH-Net: Species-Aware Hierarchical Learning for Medicinal Plant Disease Recognition

Wang Hao Lin 1 ORCID , Mir Muhammad Nizamani 2 ORCID
1 School of Geography, Nanjing Normal University, Jiangsu Province 210023, China
2 Research Group for Lowland Plain and Human Activity, Institute of Marine Sciences, Shantou University, Shantou 513063, China
Journal Impact in Agriculture
Volume 2
Article Number 6
Pages 1–16
Received 13 May 2026
Revised 7 July 2026
Accepted 12 July 2026
Published 21 July 2026
DOI https://doi.org/10.65500/agriculture-2026-006
Views 351
Downloads 111
Download PDF DOI

Abstract

Accurate recognition of medicinal plant diseases is important for maintaining plant health and product quality. Although existing deep learning approaches have achieved high classification accuracy, most formulate disease recognition as a flat multiclass problem without explicitly supervising species-related and disease-related representations. This study proposes a Species-Aware Hierarchical Network (SAH-Net) to investigate the integration of these representations within a unified classification framework. SAH-Net employs an ImageNet-pretrained EfficientNet-B0 backbone with two query-based attention branches for species-aware and disease-aware feature extraction, followed by adaptive gated hierarchical fusion. The model jointly performs three-class species recognition, seven-class disease/condition recognition, and 12-class species–condition classification. Experiments were conducted on 2,547 images of Kalanchoe pinnata, Azadirachta indica, and Ocimum tenuiflorum, using a stratified 70:15:15 training, validation, and test split. On the 383-image test subset, SAH-Net achieved 100% accuracy and macro F1-score across all three tasks, with an AUC of 1.000 for each final classification category. Explainability visualizations provided qualitative insights into the model's spatial attention patterns. SAH-Net required 6.019 million parameters and 0.893 GFLOPs, achieving 138.29 images/s using MPS acceleration on an Apple M5 Pro MacBook Pro. Although the results demonstrate the feasibility of hierarchical learning, external validation remains necessary to establish generalization beyond the evaluated acquisition conditions.

Keywords

Medicinal plants plant disease recognition hierarchical learning attention mechanism deep learning explainable artificial intelligence SAH-Net.

Funding

This research received no external funding.

References

  1. Manisha, M.; Babu, R.; Begam, A.M.; Shakya Chahal, K.; Ashok Harale, A. Medicinal Plants and Traditional Uses and Modern Applications. Journal of Neonatal Surgery 2025, 14, 162–175 https://doi.org/10.52783/JNS.V14.2210.
  2. Kussmann, M.; Abe Cunha, D.H.; Berciano, S. Bioactive Compounds for Human and Planetary Health. Frontiers in Nutrition 2023, 10, 1193848 https://doi.org/10.3389/FNUT.2023.1193848.
  3. Sasidharan, S.P.; Viji, Z.; Sankaran, R.P.; Muraleedharan, S.; K, J.; R, P.; S, B.; S, S.; S, S.; P, A.; et al. Exploring Folklore Herbal Knowledge: A Compilation from Palakkad District, Kerala, India: Exploring Folklore Herbal Knowledge from Palakkad District. Ethnobotany Research and Applications 2024, 27, 1–28 https://doi.org/10.32859/era.27.23.1-28.
  4. Tyagi, A.; Lama Tamang, T.; Kashtoh, H.; Mir, R.A.; Mir, Z.A.; Manzoor, S.; Manzar, N.; Gani, G.; Vishwakarma, S.K.; Almalki, M.A.; et al. A Review on Biocontrol Agents as Sustainable Approach for Crop Disease Management: Applications, Production, and Future Perspectives. Horticulturae 2024, 10, 805 https://doi.org/10.3390/HORTICULTURAE10080805.
  5. Bhattarai, K.; Bhattarai, R.; Pandey, R.D.; Paudel, B.; Bhattarai, H.D. A Comprehensive Review of the Phytochemical Constituents and Bioactivities of Ocimum Tenuiflorum. The Scientific World Journal 2024, 2024, 8895039 https://doi.org/10.1155/2024/8895039.
  6. Mehnaz, S.; Shamsi, Y.; Akhtar, M.W.; Mohanty, S.; Ahmad, S. Therapeutic Applications of Neem (Azadirachta Indica): A Narrative Review. Advances in Mind-body Medicine 2024, 38, 14–18.
  7. Hernández-Caballero, M.E.; Sierra-Ramírez, J.A.; Villalobos-Valencia, R.; Seseña-Méndez, E. Potential of Kalanchoe Pinnata as a Cancer Treatment Adjuvant and an Epigenetic Regulator. Molecules 2022, 27, 6425 https://doi.org/10.3390/MOLECULES27196425.
  8. Pushpanathan, K.; Hanafi, M.; Mashohor, S.; Fazlil Ilahi, W.F. Machine Learning in Medicinal Plants Recognition: A Review. Artificial Intelligence Review 2020, 54, 305–327 https://doi.org/10.1007/S10462-020-09847-0.
  9. Mukherjee, G.; Tudu, B.; Chatterjee, A. A Convolutional Neural Network-Driven Computer Vision System toward Identification of Species and Maturity Stage of Medicinal Leaves: Case Studies with Neem, Tulsi and Kalmegh Leaves. Soft Computing 2021, 25, 14119–14138 https://doi.org/10.1007/s00500-021-06139-9.
  10. Naeem, S.; Ali, A.; Chesneau, C.; Tahir, M.H.; Jamal, F.; Sherwani, R.A.K.; Hassan, M.U. The Classification of Medicinal Plant Leaves Based on Multispectral and Texture Feature Using Machine Learning Approach. Agronomy 2021, 11, 263 https://doi.org/10.3390/AGRONOMY11020263.
  11. Kan, H.X.; Jin, L.; Zhou, F.L. Classification of Medicinal Plant Leaf Image Based on Multi-Feature Extraction. Pattern Recognition and Image Analysis 2017, 27, 581–587 https://doi.org/10.1134/S105466181703018X.
  12. Sachar, S.; Kumar, A. Deep Ensemble Learning for Automatic Medicinal Leaf Identification. International Journal of Information Technology (Singapore) 2022, 14, 3089–3097 https://doi.org/10.1007/s41870-022-01055-z.
  13. Tiwari, V.; Joshi, R.C.; Dutta, M.K. Deep Neural Network for Multi-Class Classification of Medicinal Plant Leaves. Expert Systems 2022, 39 https://doi.org/10.1111/exsy.13041.
  14. Meenakshi Automatic Detection of Diseases in Leaves of Medicinal Plants Using Modified Logistic Regression Algorithm. Wireless Personal Communications 2023, 131, 2573–2597 https://doi.org/10.1007/s11277-023-10555-5.
  15. Blesslin Elizabeth CP, Baulkani S. Novel Network for Medicinal Leaves Identification. IETE Journal of Research 2023, 69, 1772–1782 https://doi.org/10.1080/03772063.2021.2016504.
  16. Kayaalp, K. Classification of Medicinal Plant Leaves for Types and Diseases with Hybrid Deep Learning Methods. Information Technology and Control 2024, 53, 19–36 https://doi.org/10.5755/j01.itc.53.1.34345.
  17. Azadnia, R.; Noei-Khodabadi, F.; Moloudzadeh, A.; Jahanbakhshi, A.; Omid, M. Medicinal and Poisonous Plants Classification from Visual Characteristics of Leaves Using Computer Vision and Deep Neural Networks. Ecological Informatics 2024, 82, 102683 https://doi.org/10.1016/J.ECOINF.2024.102683.
  18. Dey, B.; Ferdous, J.; Ahmed, R.; Hossain, J. Assessing Deep Convolutional Neural Network Models and Their Comparative Performance for Automated Medicinal Plant Identification from Leaf Images. Heliyon 2024, 10, e23655 https://doi.org/10.1016/j.heliyon.2023.e23655.
  19. Kavitha, S.; Kumar, T.S.; Naresh, E.; Kalmani, V.H.; Bamane, K.D.; Pareek, P.K. Medicinal Plant Identification in Real-Time Using Deep Learning Model. SN Computer Science 2023, 5, 73- https://doi.org/10.1007/S42979-023-02398-5.
  20. Panchal, A. V.; Patel, S.C.; Bagyalakshmi, K.; Kumar, P.; Khan, I.R.; Soni, M. Image-Based Plant Diseases Detection Using Deep Learning. Materials Today: Proceedings 2023, 80, 3500–3506 https://doi.org/10.1016/J.MATPR.2021.07.281.
  21. Kini, A.S.; Prema, K. V.; Pai, S.N. Early Stage Black Pepper Leaf Disease Prediction Based on Transfer Learning Using ConvNets. Scientific Reports 2024, 14, 1404- https://doi.org/10.1038/s41598-024-51884-0.
  22. Lanjewar, M.G.; Morajkar, P.; P, P. Modified Transfer Learning Frameworks to Identify Potato Leaf Diseases. Multimedia Tools and Applications 2023 83:17 2023, 83, 50401–50423 https://doi.org/10.1007/S11042-023-17610-0.
  23. Panchbhai, K.G.; Lanjewar, M.G. Enhancement of Tea Leaf Diseases Identification Using Modified SOTA Models. Neural Computing and Applications 2024 37:4 2024, 37, 2435–2453 https://doi.org/10.1007/S00521-024-10758-2.
  24. Sharma, S.; Vardhan, M. AELGNet: Attention-Based Enhanced Local and Global Features Network for Medicinal Leaf and Plant Classification. Computers in Biology and Medicine 2025, 184 https://doi.org/10.1016/j.compbiomed.2024.109447.
  25. Sharma, S.; Vardhan, M. MTJNet: Multi-Task Joint Learning Network for Advancing Medicinal Plant and Leaf Classification. Knowledge-Based Systems 2024, 299, 112147 https://doi.org/10.1016/J.KNOSYS.2024.112147.
  26. Pushpa, B.R.; Jyothsna, S.; Lasya, S. HybNet: A Hybrid Deep Models for Medicinal Plant Species Identification. MethodsX 2025, 14, 103126 https://doi.org/10.1016/J.MEX.2024.103126.
  27. Diwedi, H.K.; Misra, A.; Tiwari, A.K. CNN-Based Medicinal Plant Identification and Classification Using Optimized SVM. Multimedia Tools and Applications 2023 83:11 2023, 83, 33823–33853 https://doi.org/10.1007/S11042-023-16733-8.
  28. Talaat, F.M.; Shams, M.Y.; Gamel, S.A.; ZainEldin, H. DeepLeaf: An Optimized Deep Learning Approach for Automated Recognition of Grapevine Leaf Diseases. Neural Computing and Applications 2025 37:15 2025, 37, 8799–8823 https://doi.org/10.1007/S00521-025-11038-3.
  29. Mohanty, S.P.; Hughes, D.P.; Salathé, M. Using Deep Learning for Image-Based Plant Disease Detection. Frontiers in plant science 2016, 7, 1419.
  30. Arnal Barbedo, J.G. Plant Disease Identification from Individual Lesions and Spots Using Deep Learning. Biosystems Engineering 2019, 180, 96–107 https://doi.org/10.1016/J.BIOSYSTEMSENG.2019.02.002.
  31. Upadhyay, A.; Chandel, N.S.; Singh, K.P.; Chakraborty, S.K.; Nandede, B.M.; Kumar, M.; Subeesh, A.; Upendar, K.; Salem, A.; Elbeltagi, A. Deep Learning and Computer Vision in Plant Disease Detection: A Comprehensive Review of Techniques, Models, and Trends in Precision Agriculture. Artificial Intelligence Review 2025 58:3 2025, 58, https://doi.org/10.1007/S10462-024-11100-X.
  32. Khan, A.; Rauf, Z.; Sohail, A.; Khan, A.R.; Asif, H.; Asif, A.; Farooq, U. A Survey of the Vision Transformers and Their CNN-Transformer Based Variants. Artificial Intelligence Review 2023 56:3 2023, 56, 2917–2970 https://doi.org/10.1007/S10462-023-10595-0.
  33. Shao, R.; Bi, X.J.; Chen, Z. Hybrid ViT-CNN Network for Fine-Grained Image Classification. IEEE Signal Processing Letters 2024, 31, 1109–1113 https://doi.org/10.1109/LSP.2024.3386112.
  34. Chamola, V.; Hassija, V.; Sulthana, A.R.; Ghosh, D.; Dhingra, D.; Sikdar, B. A Review of Trustworthy and Explainable Artificial Intelligence (XAI). IEEE Access 2023, 11, 78994–79015 https://doi.org/10.1109/ACCESS.2023.3294569.
  35. Ribeiro, M.T.; Singh, S.; Guestrin, C. “Why Should i Trust You?” Explaining the Predictions of Any Classifier. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2016, 13-17-August-2016, 1135–1144 https://doi.org/10.1145/2939672.2939778.
  36. Selvaraju, R.R.; Cogswell, M.; Das, A.; Vedantam, R.; Parikh, D.; Batra, D. Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization. In Proceedings of the IEEE International Conference on Computer Vision (ICCV); 2017; pp. 618–626.
  37. Van Der Maaten, L.; Hinton, G. Visualizing Data Using T-SNE. Journal of Machine Learning Research 2008, 9, 2579–2605.
  38. Leelavathi, R.; Kalamani, M. Medicinal Plant Leaf Disease Classification Using Optimal Weighted Features with Dilated Adaptive DenseNet and Attention Mechanism. Scientific Reports 2025 15:1 2025, 15, 36852 https://doi.org/10.1038/s41598-025-20629-y.
  39. Ahmmed, J.; Kabir, M.A.; Rehman, A. ur; Bermak, A. A Lightweight Hybrid CNN and Transformer Model for Medicinal Leaf Disease Classification with Explainable AI. Scientific Reports 2026, 16, 8243 https://doi.org/10.1038/s41598-026-39182-3.
  40. Ahmmed, J.; Kabir, M.A.; Rehman, A. ur; Bermak, A. Medicinal Plant Leaf Disease Dataset. 2025, 1 https://doi.org/10.17632/NCG7KK3GWX.1.
  41. Padmanabha Reddy; Poojith, J.; Sidhartha, P.; Rama Devi; Kishan Babu, K. BiFPNet: Bidirectional Feature Pyramid Network for Medicinal Leaf Identification with Therapeutic Usage. International Journal of Computers and Applications 2026, 48, 127–143 https://doi.org/10.1080/1206212X.2025.2608641.

Copyright: © 2026 by the authors. Licensee: Impaxon Sdn. Bhd., Malaysia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY 4.0) License .

Disclaimer: All views, interpretations, and data presented in Impaxon publications are the sole responsibility of the respective authors. These do not necessarily reflect the opinions of Impaxon or its editorial team.

Publisher’s Note: Impaxon remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

✓ Email copied