MODEL ARCHITECTURE AND PERSPECTIVES OF FEDERATED LEARNING FOR SUSTAINABLE AGRICULTURE IN BULGARIA: MODEL ARCHITECTURE AND PERSPECTIVES OF FEDERATED LEARNING FOR SUSTAINABLE AGRICULTURE IN BULGARIA

Desislava  Ivanova; Iliyana  Ivanova

doi:10.46687/jsar.v29i1.470

Authors

Desislava Ivanova DEPARTMENT OF COMMUNICATION AND COMPUTER ENGINEERING AND SECURITY TECHNOLOGIES, FACULTY OF TECHNICAL SCIENCES, KONSTANTIN PRESLAVSKY UNIVERSITY OF SHUMEN, SHUMEN 9712,115, UNIVERSITETSKA STR., E-MAIL: d.n.ivanova@shu.bg
Iliyana Ivanova DEPARTMENT OF COMMUNICATION AND COMPUTER ENGINEERING AND SECURITY TECHNOLOGIES, FACULTY OF TECHNICAL SCIENCES, KONSTANTIN PRESLAVSKY UNIVERSITY OF SHUMEN, SHUMEN 9712,115, UNIVERSITETSKA STR., E-MAIL: i.s.ivanova@shu.bg

DOI:

https://doi.org/10.46687/jsar.v29i1.470

Keywords:

Federated learning, Sustainable agriculture, Data privacy, Model aggregation, Decentralized model training

Abstract

This paper presents a review of the application of Federated Learning (FL) in sustainable agriculture, with a specific focus on its potential integration within the Bulgarian agricultural sector. FL is a decentralized machine learning technology that enables multiple data sources to collaboratively train models without sharing raw data, thus preserving privacy and improving data security. The approach supports optimization of irrigation, fertilization, and pest control through locally adapted models and predictive analytics. The study analyzes the architecture, advantages, and limitations of FL, reviewing international case studies and exploring its relevance to Bulgarian conditions, such as regional climate variability and diverse soil types. Emphasis is placed on the potential role of FL in enhancing decision-making, reducing environmental impact, and supporting digital transformation in agriculture. Recommendations for implementation in Bulgarian farms and research institutions are also provided.

Author Biographies

Desislava Ivanova, DEPARTMENT OF COMMUNICATION AND COMPUTER ENGINEERING AND SECURITY TECHNOLOGIES, FACULTY OF TECHNICAL SCIENCES, KONSTANTIN PRESLAVSKY UNIVERSITY OF SHUMEN, SHUMEN 9712,115, UNIVERSITETSKA STR., E-MAIL: d.n.ivanova@shu.bg

DEPARTMENT OF COMMUNICATION AND COMPUTER ENGINEERING AND SECURITY TECHNOLOGIES, FACULTY OF TECHNICAL SCIENCES, KONSTANTIN PRESLAVSKY UNIVERSITY OF SHUMEN, SHUMEN 9712,115, UNIVERSITETSKA STR., E-MAIL: d.n.ivanova@shu.bg

Iliyana Ivanova, DEPARTMENT OF COMMUNICATION AND COMPUTER ENGINEERING AND SECURITY TECHNOLOGIES, FACULTY OF TECHNICAL SCIENCES, KONSTANTIN PRESLAVSKY UNIVERSITY OF SHUMEN, SHUMEN 9712,115, UNIVERSITETSKA STR., E-MAIL: i.s.ivanova@shu.bg

DEPARTMENT OF COMMUNICATION AND COMPUTER ENGINEERING AND SECURITY TECHNOLOGIES, FACULTY OF TECHNICAL SCIENCES, KONSTANTIN PRESLAVSKY UNIVERSITY OF SHUMEN, SHUMEN 9712,115, UNIVERSITETSKA STR., E-MAIL: i.s.ivanova@shu.bg

References

B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-efficient learning of deep networks from decentralized data,” Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), 2017. Available: https://arxiv.org/abs/1602.05629.

A. M. Elbir, S. Coleri, A. K. Papazafeiropoulos, P. Kourtessis, and S. Chatzinotas, “A Hybrid Architecture for Federated and Centralized Learning,” IEEE Transactions on Cognitive Communications and Networking, vol. 8, no. 3, pp. 1529–1542, Sep. 2022.

H. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data,” in Proc. of AISTATS, pp. 1273–1282, 2017.

A. Lalitha, O. C. Kilinc, T. Javidi, and F. Koushanfar, “Peer to Peer Federated Learning on Graphs,” arXiv preprint arXiv:1901.11173, 2019.

A. M. Elbir, S. Coleri, and K. V. Mishra, “Hybrid Federated and Centralized Learning,” arXiv preprint arXiv:2011.06892, 2020.

Human-Centered AI, “Theory of Federated Learning, Profiling and Personalization,” https://humancentered-ai.eu/hcaim/lecture-theory-of-federated-learning-profiling-and-personalization-_BG.htm, accessed July 2025.

R. Dembani, I. Karvelas, N. A. Akbar, S. Rizou, D. Tegolo, and S. Fountas, “Agricultural data privacy and federated learning: A review of challenges and opportunities,” Computers and Electronics in Agriculture, vol. 203, p. 107509, 2023.

Dimanova, D., Kuzmanov, Z., Real-time gis for monitoring and security, Journal Scientific and Applied Research, Vol. 27 No. 1 (2024), DOI: https://doi.org/10.46687/jsar.v27i1.408.

MODEL ARCHITECTURE AND PERSPECTIVES OF FEDERATED LEARNING FOR SUSTAINABLE AGRICULTURE IN BULGARIA