Sensor-Driven Irrigation Scheduling Using Deep Reinforcement Learning: A Water-Efficient Decision Framework for Precision Agriculture
Devesh Dwivedi
1Student, Department of CSE, KIPM-CET Gorakhpur, India
Author
Dr. Rakesh Kumar Pandey
Associate Professor, Department of CSE, KIPM-CET Gorakhpur, India.
Author
📌 DOI: https://doi.org/10.63920/tjths.201026008
🔑 Keywords:Smart irrigation, reinforcement learning, soil-moisture sensors, precision agriculture, Internet of Things, water use efficiency, proximal policy optimization
📅 Publication Date: 25 September 2026
📜 License:
This work is licensed under a Creative Commons Attribution 4.0 International License
- Share — Copy and Redistribute the material
- Adapt — Remix, Transform, and build upon the material
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Abstract:
Agriculture accounts for roughly 70% of global freshwater withdrawals, yet much irrigation is still scheduled by fixed calendars or farmer intuition, which wastes water, energy and nutrients and can stress the crop at critical growth stages. This paper presents a sensor-driven irrigation scheduling framework, the Sensor-based Reinforcement-learning Irrigation Scheduler (SRIS), that learns when and how much to irrigate from multi-depth soil-moisture readings, short-range weather forecasts and crop growth stage. Irrigation is modelled as a Markov decision process and solved with Proximal Policy Optimization (PPO) inside a soil-water-balance simulator calibrated and noise-corrupted with field sensor data. The reward couples a water-stress-based yield proxy with penalties for water use, deep percolation and pumping energy. In simulated seasons, SRIS reduced irrigation water by about 27% compared with calendar-based scheduling while increasing relative yield by about 4%, improving water use efficiency by about 34%. It also outperformed threshold-based, FAO-56 evapotranspiration-based and DQN baselines, and remained robust to sensor noise and forecast error. The learned policy is compact enough to run on a low-power edge controller, supporting precision and sustainable agriculture.
Download Full PDF Paper
📖 How to Cite
Devesh D. and Rakesh Kumar P.(2026). Sensor-Driven Irrigation Scheduling Using Deep Reinforcement Learning: A Water-Efficient Decision Framework for Precision Agriculture. TEJAS J. Technol. Humanit. Sci.,, Vol. 05, Issue 03. https://doi.org/10.63920/tjths.201026008
📊 Article Metrics
References
[1] J. A. Foley et al., “Solutions for a cultivated planet,” Nature, vol. 478, pp. 337–342, 2011.
[2] S. Wolfert, L. Ge, C. Verdouw, and M.-J. Bogaardt, “Big data in smart farming – a review,” Agricultural Systems, vol. 153, pp. 69–80, 2017.
[3] A. Goap, D. Sharma, A. K. Shukla, and C. R. Krishna, “An IoT based smart irrigation management system using machine learning and open source technologies,” Computers and Electronics in Agriculture, vol. 155, pp. 41–49, 2018.
[4] R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. Cambridge, MA, USA: MIT Press, 2018.
[5] V. Mnih et al., “Human-level control through deep reinforcement learning,” Nature, vol. 518, pp. 529–533, 2015.
[6] J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal policy optimization algorithms,” arXiv:1707.06347, 2017.
[7] R. G. Allen, L. S. Pereira, D. Raes, and M. Smith, “Crop evapotranspiration: Guidelines for computing crop water requirements,” FAO Irrigation and Drainage Paper 56, Rome, Italy, 1998.
[8] K. G. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis, “Machine learning in agriculture: A review,” Sensors, vol. 18, no. 8, art. 2674, 2018.
[9] A. Kamilaris and F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70–90, 2018.
[10] T. Haarnoja, A. Zhou, P. Abbeel, and S. Levine, “Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor,” in Proc. 35th Int. Conf. Machine Learning (ICML), 2018, pp. 1861–1870.
[11] M. T. van Genuchten, “A closed-form equation for predicting the hydraulic conductivity of unsaturated soils,” Soil Science Society of America Journal, vol. 44, no. 5, pp. 892–898, 1980.
[12] J. Doorenbos and A. H. Kassam, “Yield response to water,” FAO Irrigation and Drainage Paper 33, Rome, Italy, 1979.
[13] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proc. Int. Conf. Learning Representations (ICLR), 2015.
[14] G. Brockman et al., “OpenAI Gym,” arXiv:1606.01540, 2016.
[15] S. Srivastava, A. Prajapati, M. K. Tiwari, and A. K. Srivastava, “Real time AI-driven threat detection with the integration of Zero Trust security framework,” TEJAS J. Technol. Humanit. Sci., vol. 4, no. 4, 2025, doi: 10.63920/tjths.44004.
[16] Shahnawaz, A. Singh, A. Gupta, and R. K. Dubey, “Ride Sight ML: Mobility analytics and forecasting,” TEJAS J. Technol. Humanit. Sci., vol. 4, no. 4, 2025, doi: 10.63920/tjths.44006.
[17] S. K. Patel, S. B. Verma, B. K. Gupta, et al., “Advances in authentication and security protocols for 5G networks: A comprehensive survey,” Discover Applied Sciences, vol. 7, Art. no. 743, 2025, doi: 10.1007/s42452-025-07317-2.
[18] A. Raffin et al., “Stable-Baselines3: Reliable reinforcement learning implementations,” Journal of Machine Learning Research, vol. 22, no. 268, pp. 1–8, 2021.