Edge AI for Real-Time Crop Disease Detection: A Lightweight Deep Learning Framework with Knowledge Distillation for Resource-Constrained Environments
Received: 28 January 2026; Revised: 10 March 2026; Accepted: 21 March 2026; Published: 8 April 2026
Abstract
Plant diseases threaten global food security, causing over 20% annual yield losses and approximately USD 220 billion in economic damage worldwide. While deep convolutional neural networks (CNNs) have shown remarkable efficacy in automated plant disease diagnosis, their deployment on resource-constrained edge devices is hindered by computational demands, memory footprints, and energy consumption. This study introduces AgriNet-Lite, a lightweight deep learning architecture synergistically integrating depthwise separable convolutions, an efficient channel attention mechanism, and knowledge distillation from a high-capacity teacher network. The framework was evaluated on the PlantVillage benchmark dataset (54,305 images, 38 disease classes, 14 crop species). AgriNet-Lite achieved 98.72% classification accuracy with macro-averaged precision of 0.986, recall of 0.984, and F1-score of 0.985, while maintaining a compact model size of 2.1 million parameters (8.1 MB). Edge deployment on Raspberry Pi 4 demonstrated inference latency of 28 ms per image (35.7 FPS). Ablation studies confirmed individual contributions of channel attention (+2.30% accuracy) and knowledge distillation (+1.70% accuracy), with cumulative improvement of 3.92 percentage points. Field validation under natural conditions using a custom-collected tomato leaf dataset (n = 1,247) achieved 94.2% accuracy despite substantial domain shift. Comparative analysis against MobileNetV2, EfficientNet-B0, Tiny-LiteNet, and CNN-SEEIB demonstrated superior accuracy-efficiency trade-offs. AgriNet-Lite establishes a pragmatic, deployable solution for on-device plant disease diagnosis, particularly suited for smallholder farmers in regions with limited computational infrastructure and intermittent internet connectivity.
Keywords
References
- 1. Lal, R. Crop health management for food and nutritional security and soil health. Crop Health 2026, 4, 22. DOI: https://doi.org/10.1007/s44297-026-00083-6
- 2. Barbedo, J.G.A. Factors Influencing the Use of Deep Learning for Plant Disease Recognition. Biosyst. Eng. 2018, 172, 84–91.
- 3. Gill, S.S.; Golec, M.; Hu, J.; et al. Edge AI: A taxonomy, systematic review and future directions. Cluster Comput. 2025, 28, 18. DOI: https://doi.org/10.1007/s10586-024-04686-y
- 4. Kaler, B.; Kaur, A. A systematic survey on explainable artificial intelligence (XAI) for plant health monitoring: Challenges and opportunities. Appl. Intell. 2025, 55, 889. DOI: https://doi.org/10.1007/s10489-025-06790-x
- 5. Salka, T.D.; Hanafi, M.; Abdul Rahman, S.M.; et al. State-of-the-Art CNN Models for Plant Disease Classification: A Comparative Study. Pertanika J. Sci. Technol. 2025, 33, 2541–2563.
- 6. Ahamed, M.F.; Salam, A.; Nahiduzzaman, M.; et al. Streamlining plant disease diagnosis with convolutional neural networks and edge devices. Neural Comput. Appl. 2024, 36, 18445–18477. DOI: https://doi.org/10.1007/s00521-024-10152-y
- 7. Rana, A. Architectural overview of edge AI processing in smart connected devices: From embedded hardware to real-time inference. J. Comput. Sci. Technol. Stud. 2025, 7, 377–384.
- 8. Sandler, M.; Howard, A.; Zhu, M.; et al. MobileNetV2: Inverted Residuals and Linear Bottlenecks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 4510–4520.
- 9. Tan, M.; Le, Q.V. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In Proceedings of the 36th International Conference on Machine Learning, Long Beach, CA, USA, 9–15 June 2019; pp. 6105–6114.
- 10. Hinton, G.; Vinyals, O.; Dean, J. Distilling the Knowledge in a Neural Network. arXiv preprint 2015, arXiv:1503.02531.
- 11. Chang, S. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Available online: https://aapm.confex.com/aapm/2024am/meetingapp.cgi/Paper/13897 (accessed on 7 September 2025).
- 12. Xu, Y.; Li, D.; Li, C.; et al. LiSA-MobileNetV2: An extremely lightweight deep learning model with Swish activation and attention mechanism for accurate rice disease classification. Front. Plant Sci. 2025, 16, 1619365. DOI: https://doi.org/10.3389/fpls.2025.1619365
- 13. Gunasekaran, H.; Rajkumar, S.; Kirubhadharsini B, L. Lightweight deep learning for tomato disease detection: trends, challenges, and edge AI perspectives. Front. Plant Sci. 2025, 16, 1737208. DOI: https://doi.org/10.3389/fpls.2025.1737208
- 14. Yang, X.; Wang, H.; Zhou, Q.; et al. A Lightweight and Efficient Plant Disease Detection Method Integrating Knowledge Distillation and Dual-Scale Weighted Convolutions. Algorithms 2025, 18, 433.
- 15. Nyakuri, J.P.; Nkundineza, C.; Gatera, O.; et al. AI and IoT-powered edge device optimized for crop pest and disease detection. Sci. Rep. 2025, 15, 22905. DOI: https://doi.org/10.1038/s41598-025-06452-5
- 16. Maeda-Gutiérrez, V.; Galvan-Tejada, C.E.; Zanella-Calzada, L.A.; et al. Comparison of convolutional neural network architectures for classification of tomato plant diseases. Appl. Sci. 2020, 10, 1245. DOI: https://doi.org/10.3390/app10041245
- 17. Sharma, V.; Pal, R. Distilling Deep Learning for the Field: Lightweight Plant Disease Diagnosis via ResNet-50 to MobileNetV2 Transfer. In Data Science and Applications; Nanda, S.J., Yadav, R.P., Prasad, M., et al., Eds.; Springer: Cham, Switzerland, 2026. DOI: https://doi.org/10.1007/978-3-032-15410-1_17
- 18. Karthikeyan, S.; Charan, R.; Narayanan, S.; et al. Enhanced plant disease classification with attention-based convolutional neural network using squeeze and excitation mechanism. Front. Artif. Intell. 2025, 8, 1640549. DOI: https://doi.org/10.3389/frai.2025.1640549
- 19. El-Saber, N.A.S.; Mohamed, I.S. A Systematic Review of Lightweight and Robust Deep Learning Approaches for Tomato Leaf Disease Detection. Eng. Res. J. (Shoubra) 2026, 55, 119–131.
- 20. Zhang, S.; Liu, R. Multi-scale feature fusion-based vision mamba for robust plant disease image classification on field-acquired plantdoc data. Front. Plant Sci. 2026, 17, 1842426. DOI: https://doi.org/10.3389/fpls.2026.1842426
- 21. Abou Ali, M.; Dornaika, F.; Charafeddine, J. Edge artificial intelligence: Past advances, current paradigms, and emerging horizons. Eng. Appl. Artif. Intell. 2026, 181, 115635. DOI: https://doi.org/10.1016/j.engappai.2026.115635
- 22. Talaat, F.M.; Tawfik, M.; Shaban, W.M. GreenAid: A confidence-weighted ensemble deep learning system for real-time plant disease detection and management. Sci. Rep. 2026, 16, 19193. DOI: https://doi.org/10.1038/s41598-026-57979-0
- 23. Sathya, K.; Balakrishnan, A.; Baskaran, P.; et al. Enhancing plant disease detection using Attention-Augmented residual networks and faster Region–Convolutional networks. IEEE Access 2025, 13, 48625–48642. DOI: https://doi.org/10.1109/ACCESS.2025.3551242
- 24. Boukhlifa, G.; Chibani, Y. A Lightweight CNN Supported by Partially Skip-Connected CAE for Plant Disease Identification across Multiple Agricultural Environments. Appl. Soft Comput. 2026, 201, 115515.
- 25. Zeeshan, M.; Baghini, M.S.; Pandey, A. EdgePlantNet: Lightweight edge-aware cyber–physical system for plant disease detection using enhanced attention CNNs. Pervasive Mob. Comput. 2025, 110, 102059. DOI: https://doi.org/10.1016/j.pmcj.2025.102059
- 26. Burman, S.; Pandey, N.; Srivastava, C.; et al. MBConvNet-CNS: A Lightweight Convolutional Neural Network Architecture for Plant Disease Detection. In Proceedings of the 2024 12th International Conference on Intelligent Systems and Embedded Design (ISED), Rourkela, India, 20–22 December 2024.
- 27. Shahade, A.K.; Deshmukh, P.V. Edge-Enhanced Dual Branch CNN with Adaptive Attention for Robust Apple Leaf Disease Detection. BMC Plant Biol. 2026, 26, 39.
- 28. Mahapatra, P.; Panda, M.; Dash, S.K.; et al. Advancing plant disease classification using an attention-based CNN for intra-dataset and cross-dataset training. Sci. Rep. 2026, 16, 10925. DOI: https://doi.org/10.1038/s41598-026-45464-7
- 29. Papanikolaou, A.; Tziouvaras, A.; Floros, G.; et al. Distributed Deep Learning in IoT Sensor Network for the Diagnosis of Plant Diseases. Sensors 2025, 25, 7646.