Loading...
Adaptive Multi Agent Intelligence for Coordinated Resource Management in Sustainable Farming Systems


Journal of Smart and Sustainable Farming

Received On : 23 April 2026

Revised On : 26 August 2026

Accepted On : 15 September 2026

Published On : 03 October 2026

Volume 02, 2026

Pages : 225-238


Abstract

Farms must share scarce resources, groundwater, pumping capacity, solar energy and irrigation labour, among fields that differ in crop, soil and economic value, under weather and market conditions that change from season to season. Centralised optimisation requires complete information and a single decision maker, whereas uncoordinated, field-by-field decisions can waste capacity at peak demand. This paper develops an adaptive multi-agent system for farm resource management in which parcel agents learn irrigation policies by Q-learning, resource agents (water, energy, crew) publish adaptive prices that reflect congestion and the pace of seasonal water use, and requests are allocated within pump, crew and seasonal caps. The system was evaluated on a simulated 16-parcel farm with three crops, a seasonal groundwater allocation of 70 % of unconstrained demand and a limited pump and crew capacity, in six scenarios (normal, dry, wet, pump failure, price shock and a combined dry–failure–shock case) with three independent training seeds. The proposed system achieved 95 % of the net value of an omniscient central planner in a normal year and 84 % in a dry year, with a yield Gini of 0.025 against 0.085 for the planner and a lowest parcel yield of 0.82 against 0.66, while independent Q-learners reached only 80 % with large variation between training runs. Ablation showed that the adaptive price signal was the essential component (net value fell to 75 % without it) whereas the bid-based priority ranking added nothing. Simple heuristics were competitive when capacity was not scarce, and the central planner remained clearly better in dry years. After a severe combined shock, continued learning with drift-triggered exploration did not outperform the frozen policy, so most of the robustness came from the daily price adaptation.

Keywords

Multi-Agent Systems, Reinforcement Learning, Resource Coordination, Irrigation, Water–Energy Nexus, Adaptive Pricing, Sustainable Farming.

  1. B. Paudel, S. Riaz, S. W. Teng, R. R. Kolluri, and H. Sandhu, “The digital future of farming: A bibliometric analysis of big data in smart farming research,” Cleaner and Circular Bioeconomy, vol. 10, p. 100132, Mar. 2025, doi: 10.1016/j.clcb.2024.100132.
  2. T. Ali et al., “Smart agriculture: utilizing machine learning and deep learning for drought stress identification in crops,” Scientific Reports, vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-74127-8.
  3. E.-S. M. El-Kenawy, A. A. Alhussan, N. Khodadadi, S. Mirjalili, and M. M. Eid, “Predicting Potato Crop Yield with Machine Learning and Deep Learning for Sustainable Agriculture,” Potato Research, Jul. 2024, doi: 10.1007/s11540-024-09753-w.
  4. J. Sang, D. Ma, X. Xie, and X. Hu, “Group-aggregation of Hierarchical Containment Control for Homogeneous Multi-agent Systems in Precision Agriculture,” International Journal of Control, Automation and Systems, vol. 22, no. 4, pp. 1400–1408, Mar. 2024, doi: 10.1007/s12555-022-1071-y.
  5. W. Tao, Q. Sang, C. Chen, and Q. Mao, “Intelligent Agents for Smart Agriculture: Architectures, Applications, and Future Challenges,” Agriculture, vol. 16, no. 17, p. 1808, Aug. 2026, doi: 10.3390/agriculture16171808.
  6. D. Bazzana, J. Foltz, and Y. Zhang, “Impact of climate smart agriculture on food security: An agent-based analysis,” Food Policy, vol. 111, p. 102304, Aug. 2022, doi: 10.1016/j.foodpol.2022.102304.
  7. A. Tzachor et al., “Large language models and agricultural extension services,” Nature Food, vol. 4, no. 11, pp. 941–948, Nov. 2023, doi: 10.1038/s43016-023-00867-x.
  8. S. Bushaj, X. Yin, A. Beqiri, D. Andrews, and İ. E. Büyüktahtakın, “A simulation-deep reinforcement learning (SiRL) approach for epidemic control optimization,” Annals of Operations Research, vol. 328, no. 1, pp. 245–277, Sep. 2022, doi: 10.1007/s10479-022-04926-7.
  9. G. G. Devarajan, S. M. Nagarajan, R. T.V., V. T., U. Ghosh, and W. Alnumay, “DDNSAS: Deep reinforcement learning based deep Q-learning network for smart agriculture system,” Sustainable Computing: Informatics and Systems, vol. 39, p. 100890, Sep. 2023, doi: 10.1016/j.suscom.2023.100890.
  10. M. Aldossary, H. A. Alharbi, and C. Anwar Ul Hassan, “Internet of Things (IoT)-Enabled Machine Learning Models for Efficient Monitoring of Smart Agriculture,” IEEE Access, vol. 12, pp. 75718–75734, 2024, doi: 10.1109/access.2024.3404651.
  11. S. K. S. Durai and M. D. Shamili, “Smart farming using Machine Learning and Deep Learning techniques,” Decision Analytics Journal, vol. 3, p. 100041, Jun. 2022, doi: 10.1016/j.dajour.2022.100041.
  12. N. Marwah, V. K. Singh, G. S. Kashyap, and S. Wazir, “An analysis of the robustness of UAV agriculture field coverage using multi-agent reinforcement learning,” International Journal of Information Technology, vol. 15, no. 4, pp. 2317–2327, Apr. 2023, doi: 10.1007/s41870-023-01264-0.
  13. A. Choudhari, D. Bhoyar, and W. P. Badole, “Design of an IoT based Monitoring System Utilizing Deep Reinforcement Learning and Ensemble Learning for Precision Agriculture,” 2024 2nd International Conference on Sustainable Computing and Smart Systems (ICSCSS), pp. 845–852, Jul. 2024, doi: 10.1109/icscss60660.2024.10625266.
  14. A. S. Assiri, F. k. Alsheref, M. A. Ghamdi, and M. Abbassy, “MADRL-SI: a multi-agent deep reinforcement learning-based swarm intelligence approach for coordinating multiple UAVs in smart agriculture systems,” International Journal of Information Technology, Nov. 2025, doi: 10.1007/s41870-025-02807-3.
  15. A. Din, M. Y. Ismail, B. Shah, M. Babar, F. Ali, and S. U. Baig, “A deep reinforcement learning-based multi-agent area coverage control for smart agriculture,” Computers and Electrical Engineering, vol. 101, p. 108089, Jul. 2022, doi: 10.1016/j.compeleceng.2022.108089.
CRediT Author Statement

The author reviewed the results and approved the final version of the manuscript.

Acknowledgements

The authors acknowledge that this research was supported by the institutional research facilities and resources made available to the research team.

Funding

No funding was received to assist with the preparation of this manuscript.

Ethics Declarations

Conflict of interest

The authors have no conflicts of interest to declare that are relevant to the content of this article.

Availability of Data and Materials

Data sharing is not applicable to this article as no new data were created or analysed in this study.

Author Information

Contributions

All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.

Corresponding Author



Rights and permissions

This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0).
https://creativecommons.org/licenses/by/4.0/.

This license permits unrestricted use, sharing, distribution, reproduction, and adaptation in any medium or format, including for commercial purposes, provided that appropriate credit is given to the original author(s) and the source, a link to the license is provided, and any changes made are indicated.

Copyright

© 2026 Muhammad Farooq. The author(s) retain copyright of the work. The author(s) grant the Journal of Smart and Sustainable Farming (JSSF) and its publisher, Ansis Publications, the right of first publication and the right to identify itself as the original publisher of the article.

Cite this Article

Muhammad Farooq, “Adaptive Multi Agent Intelligence for Coordinated Resource Management in Sustainable Farming Systems”, Journal of Smart and Sustainable Farming, pp. 225-238, 2026, doi: 10.64026/JSSF/2026019.