A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model

B Johnson; T Chandrakumar

doi:10.15832/ankutbd.1837705

A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model

Abstract

The correct and prompt detection of leaf diseases in paddy crops remains essential for protecting agricultural output and yield stability and reducing major losses that occur during severe disease outbreaks. The widespread use of conventional centralized machine learning techniques becomes impractical for real-world agricultural applications, as their effectiveness diminishes under three main conditions: data privacy limitations, delayed transmission of information, along with reduced performance accuracy from non-independent and identically distributed (non-IID) data properties across different agro-climatic regions. This research develops a decentralized diagnostic system which combines Federated Learning with an Enhanced Pretrained Novel EfficientNet-Lite4 model designed for paddy leaf disease classification. The Paddy Doctor dataset served as training material for the system which contained 16,225 RGB images that classified 12 disease types alongside healthy categories. The proposed model reached 98.7% classification accuracy and 98.5% precision and 98.6% F1-score while maintaining a final loss of 0.21 after 100 communication rounds. The system underwent field testing which demonstrated its ability to generate accurate diagnostic results in real time in various working conditions. The study demonstrates how privacy preserving AI-based paddy disease management works in practice and recommends local agricultural institutions to build decentralized learning systems. The suggested system will give farmers direct access to field level decision support and facilitate the creation of sustainable digital pest management systems required to ensure food supply.

Keywords

Supporting Institution

Thiagarajar College of Engineering, Madurai, Tamilnadu, India.

Ethical Statement

No human or animal subjects were involved; ethical issues are not applicable.

Thanks

The authors thank the institution and field collaborators for their support.

References

Aggarwal M, Khullar V, Goyal N, Gautam R, Alblehai F, Elghatwary M & Singh A (2023). Federated transfer learning for rice-leaf disease classification across multiclient cross-silo datasets. Agronomy 13(10): 2483. doi.org/10.3390/agronomy13102483. Aggarwal M, Khullar V, Goyal N, Alammari A, Albahar M A & Singh A (2023). Lightweight federated learning for rice leaf disease classification using non independent and identically distributed images. Sustainability 15(16): 12149. doi.org/10.3390/su151612149
Aggarwal M, Khullar V, Goyal N & Prola T A (2024). Resource-efficient federated learning over IoAT for rice leaf disease classification. Computers and Electronics in Agriculture 221: 109001. doi.org/10.1016/j.compag.2024.109001.
Akgül İ, Kaya V & Zencir Tanır Ö (2023). A novel hybrid system for automatic detection of fish quality from eye and gill color characteristics using transfer learning technique. PLoS ONE 18(4): e0284804. doi.org/10.1371/journal.pone.0284804.
Anh P T & Duc H T M (2021). A benchmark of deep learning models for multi-leaf diseases for edge devices. In 2021 International Conference on Advanced Technologies for Communications (ATC): 318-323. doi.org/10.1109/ATC52653.2021.9598196.
Aristan T & Kusuma G P (2023). Evaluation of CNN models in identifying plant diseases on a mobile device. Revue d'Intelligence Artificielle 37(2): 441-449. doi.org/10.18280/ria.370221.
Asvitha S, Dhivya T, Dhivyasree H & Bhavadharini R M (2023). Paddy Pro: A MobileNetV3-based app to identify paddy leaf diseases. In Proceedings of Fourth International Conference on Computing, Communications, and Cyber-Security: 203-216. doi.org/10.1007/978-981-99-1479-1_16.
Bi C, Xu S, Hu N, Zhang S, Zhu Z & Yu H (2023). Identification method of corn leaf disease based on improved MobileNetV3 model. Agronomy 13(2): 300. doi.org/10.3390/agronomy13020300.
Castrillo J, Valle R & Baumela L (2024). Efficiency evaluation of mobile vision transformers. In Information Technology and Systems: 3-11. doi.org/10.1007/978-3-031-54256-5_1.

Cheng Z, Liu M, Qian R, Huang R & Dong W (2022). Development of a lightweight crop disease image identification model based on attentional feature fusion. Sensors 22(15): 5550. doi.org/10.3390/s22155550.
Ebenezer J, Krishna P G, Poojitha M & Krishna A V (2023). Plant leaf disease detection and classification with CNN and federated learning approach. In Intelligent Manufacturing Systems in Industry 4.0: 513-523. doi.org/10.1007/978-981-99-1665-8_44.
Eladl S G, Haikal A Y, Saafan M M & ZainEldin H Y (2024). A proposed plant classification framework for smart agricultural applications using UAV images and artificial intelligence techniques. Alexandria Engineering Journal 109: 466-481. doi.org/10.1016/j.aej.2024.08.076.
Fahim-Ul-Islam M, Chakrabarty A, Ahmed S T, Rahman R, Kwon H H & Piran M J (2024). A comprehensive approach toward wheat leaf disease identification leveraging transformer models and federated learning. IEEE Access 12: 109128-109156. doi.org/10.1109/ACCESS.2024.3438544.
Hasan H S (2024). Federated machine learning and TinyML inference for crop disease and pest classification on smartphones. Doctoral dissertation, American University of Beirut.
Haque M A, Deb C K, Marwaha S, Dutta S, Shah M U D, Saikia A & Shukla A (2024). Rice disease identification using vision transformer (ViT) based network. In The Future of Artificial Intelligence and Robotics: 732-741. doi.org/10.1007/978-3-031-60935-0_63.
Kaya V (2023). A perspective on transfer learning in computer vision. In Advances in Engineering Sciences: 332-359. doi.org/10.5281/zenodo.1002474.
Kaya V, Akgül İ & Tanır Ö Z (2023). IsVoNet8: A proposed deep learning model for classification of some fish species. Journal of Agricultural Sciences 29(1): 298-307. doi.org/10.15832/ankutbd.1031130.
Khan A T, Jensen S M, Khan A R & Li S (2023). Plant disease detection model for edge computing devices. Frontiers in Plant Science 14: 1308528. doi.org/10.3389/fpls.2023.1308528 . Kunduracioglu I & Pacal I (2024). Advancements in deep learning for accurate classification of grape leaves and diagnosis of grape diseases. Journal of Plant Diseases and Protection 131(3): 1061-1080. doi.org/10.1007/s41348-024-00896-z.
Kuriakose B, Shrestha R & Sandnes F E (2023). DeepNAVI: A deep learning based smartphone navigation assistant for people with visual impairments. Expert Systems with Applications 212: 118720. doi.org/10.1016/j.eswa.2022.118720.
Leema A A & Balakrishnan P (2024). Detection and categorization of rice leaf diseases through federated learning and improved vision transformer models. Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications 15(4): 370-379. doi.org/10.58346/JOWUA.2024.I4.025.
Li G, Wang Y, Zhao Q, Yuan P & Chang B (2023). PMVT: A lightweight vision transformer for plant disease identification on mobile devices. Frontiers in Plant Science 14: 1256773. doi.org/10.3389/fpls.2023.1256773.
Liang C M, Liu Z Q, Li Y W & Yang H (2023). Variety identification of grape based on MobileNetV3-Large model.
Maaz M, Shaker A, Cholakkal H, Khan S, Zamir S W, Anwer R M & Shahbaz Khan F (2022). EdgeNeXt: Efficiently amalgamated CNN-transformer architecture for mobile vision applications. In Computer Vision – ECCV 2022 Workshops: 3-20. doi.org/10.1007/978-3-031-25082-8_1.
Mamba Kabala D, Hafiane A, Bobelin L & Canals R (2023). Image-based crop disease detection with federated learning. Scientific Reports 13(1): 19220. doi.org/10.1038/s41598-023-46218-5.
Manoj T, Makkithaya K & Narendra V G (2022). A federated learning-based crop yield prediction for agricultural production risk management. In 2022 IEEE Delhi Section Conference (DELCON): 1-7
Mehta S & Rastegari M (2021). MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer. arXiv arXiv:2110.02178. doi.org/10.48550/arXiv.2110.02178.
Meng Y, Wu P, Feng J & Zhang X (2024). MixMobileNet: A mixed mobile network for edge vision applications. Electronics 13(3): 519. doi.org/10.3390/electronics13030519.
Muhammed D, Ahvar E, Ahvar S, Trocan M, Montpetit M J & Ehsani R (2024). Artificial Intelligence of Things (AIoT) for smart agriculture: A review of architectures, technologies and solutions. Journal of Network and Computer Applications: 103905. doi.org/10.1016/j.jnca.2024.103905.
Parez S, Dilshad N, Alghamdi N S, Alanazi T M & Lee J W (2023). Visual intelligence in precision agriculture: Exploring plant disease detection via efficient vision transformers. Sensors 23(15): 6949. doi.org/10.3390/s23156949.
Pérez Arteaga S, Sandoval Orozco A L & García Villalba L J (2023). Analysis of machine learning techniques for information classification in mobile applications. Applied Sciences 13(9): 5438. doi.org/10.3390/app13095438.
Pramudhita D A, Azzahra F, Arfat I K, Magdalena R & Saidah S (2023). Strawberry plant diseases classification using CNN based on MobileNetV3 Large and EfficientNet-B0 architecture. Jurnal Ilmiah Teknik Elektro Komputer dan Informatika 9(3): 522-534. doi.org/10.26555/jiteki.v9i3.26341.
Quan S, Wang J, Jia Z, Yang M & Xu Q (2023). MS-Net: A novel lightweight and precise model for plant disease identification. Frontiers in Plant Science 14: 1276728. doi.org/10.3389/fpls.2023.1276728.
Salamai A A, Ajabnoor N, Khalid W E, Ali M M & Murayr A A (2023). Lesion-aware visual transformer network for paddy diseases detection in precision agriculture. European Journal of Agronomy 148: 126884. doi.org/10.1016/j.eja.2023.126884.
Singh N & Adhikari M (2024). Real-time paddy field irrigation using feature extraction and federated learning strategy. IEEE Sensors Journal. doi.org/10.1109/JSEN.2024.3462496.
Singh N & Adhikari M (2024). Edge-centric collaborative federated learning for irrigation management of paddy fields using agriculture sensor data processing. IEEE Sensors Letters. doi.org/10.1109/LSENS.2024.3422417.
Thakur P S, Chaturvedi S, Khanna P, Sheorey T & Ojha A (2023). Vision transformer meets convolutional neural network for plant disease classification. Ecological Informatics 77: 102245. doi.org/10.1016/j.ecoinf.2023.102245.
Tripathy R, Mandala J, Pappu S R & Gopisetty G K D (2024). Optimization based rice leaf disease classification in federated learning. Multimedia Tools and Applications 83(29): 72491-72517. doi.org/10.1007/s11042-023-18085-9.
Xiao Y, Wu J & Ma C (2024). GA-GhostNet: A lightweight CNN model for identifying pests and diseases using a gated multi-scale coordinate attention mechanism. Engineering Letters 32(7): 1281-1290.
Yan Q, Lin X, Gong W, Wu C & Chen Y (2022). Nutrient deficiency diagnosis of plants based on transfer learning and lightweight convolutional neural networks MobileNetV3-Large. In Proceedings of the 2022 11th International Conference on Computing and Pattern Recognition: 26 33. doi.org/10.1145/3581807.3581812.
Yan Q, Chen Y & Wu C (2023). Identification of plant nutrient deficiency based on improved MobileNetV3-Large model. In Chinese Intelligent Automation Conference: 402-408. doi.org/10.1007/978-981-99-6187-0_40.
Yang G, Kwon Y & Kim H (2023). ExMobileViT: Lightweight classifier extension for mobile vision transformer. arXiv arXiv:2309.01310. doi.org/10.48550/arXiv.2309.01310.
Yang H, Deng X, Shen H, Lei Q, Zhang S & Liu N (2023). Disease detection and identification of rice leaf based on improved detection transformer. Agriculture 13(7): 1361. doi.org/10.3390/agriculture13071361.
Yasukura M, Yoshioka M & Inoue K (2024). Reducing computational cost in MobileViT for edge-oriented models through token merging. Electronics 13(24): 5009. doi.org/10.3390/electronics13245009.
Yu S, Xie L & Huang Q (2023). Inception convolutional vision transformers for plant disease identification. Internet of Things 21: 100650. doi.org/10.1016/j.iot.2022.100650.
Zhang M, Lin Z, Tang S, Lin C, Zhang L, Dong W & Zhong N (2025). Dual-Attention-Enhanced MobileViT Network: A lightweight model for rice disease identification in field-captured images. Agriculture 15(6): 571. doi.org/10.3390/agriculture15060571.
Zhao X & Lu J (2024). ShuffleVITNet: Mobile-friendly vision transformer with less-memory. In 2024 International Joint Conference on Neural Networks (IJCNN): 1-7. doi.org/10.1109/IJCNN60899.2024.10651021.
Zhou F, Hu S, Du X, Wan X & Wu J (2024). A lightweight neural network model for disease risk prediction in edge intelligent computing architecture. Future Internet 16(3): 75. doi.org/10.3390/fi16030075.
Zhou G, Liu W, Zhu Q, Lu Y & Liu Y (2022). ECA-MobileNetV3(Large)+SegNet model for binary sugarcane classification of remotely sensed images. IEEE Transactions on Geoscience and Remote Sensing 60: 1-15. doi.org/10.1109/TGRS.2022.3215802.
Zi J, Hu W, Fan G, Chen F & Chen Y (2025). SFL-MobileNetV3: A lightweight network for weed recognition in tropical cassava fields in China. Expert Systems with Applications 277: 127196. doi.org/10.1016/j.eswa.2025.127196.

Details

Primary Language

English

Subjects

Precision Agriculture Technologies, Plant Protection (Other), Agronomy

Journal Section

Research Article

Authors

B Johnson ^*
0009-0009-8281-4051
India

T Chandrakumar
0000-0002-1186-5988
India

Publication Date

October 12, 2026

Submission Date

December 7, 2025

Acceptance Date

May 11, 2026

Published in Issue

Year 2026 Volume: 32 Number: 4

DOI

https://doi.org/10.15832/ankutbd.1837705

IZ

https://izlik.org/JA79CE53DG

Cite

RIS / Bibtex

APA

Johnson, B., & Chandrakumar, T. (2026). A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model. Journal of Agricultural Sciences, 32(4), 988-1007. https://doi.org/10.15832/ankutbd.1837705

AMA

1.Johnson B, Chandrakumar T. A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model. J Agr Sci-Tarim Bili. 2026;32(4):988-1007. doi:10.15832/ankutbd.1837705

Chicago

Johnson, B, and T Chandrakumar. 2026. “A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model”. Journal of Agricultural Sciences 32 (4): 988-1007. https://doi.org/10.15832/ankutbd.1837705.

EndNote

Johnson B, Chandrakumar T (October 1, 2026) A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model. Journal of Agricultural Sciences 32 4 988–1007.

IEEE

[1]B. Johnson and T. Chandrakumar, “A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model”, J Agr Sci-Tarim Bili, vol. 32, no. 4, pp. 988–1007, Oct. 2026, doi: 10.15832/ankutbd.1837705.

ISNAD

Johnson, B - Chandrakumar, T. “A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model”. Journal of Agricultural Sciences 32/4 (October 1, 2026): 988-1007. https://doi.org/10.15832/ankutbd.1837705.

JAMA

1.Johnson B, Chandrakumar T. A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model. J Agr Sci-Tarim Bili. 2026;32:988–1007.

MLA

Johnson, B, and T Chandrakumar. “A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model”. Journal of Agricultural Sciences, vol. 32, no. 4, Oct. 2026, pp. 988-1007, doi:10.15832/ankutbd.1837705.

Vancouver

1.B Johnson, T Chandrakumar. A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model. J Agr Sci-Tarim Bili. 2026 Oct. 1;32(4):988-1007. doi:10.15832/ankutbd.1837705