Actor–Critic Deep Reinforcement Learning for Multi-Objective Intelligent Irrigation Scheduling: Algorithm and Edge-Cloud Management System

Peng Huang

Abstract


Against the backdrop of increasingly prominent climate fluctuations and water scarcity, the demand for precision and intelligence in agricultural irrigation continues to rise. This article focuses on the research of "agricultural irrigation intelligent scheduling algorithm and management system based on deep reinforcement learning", aiming to construct a technical solution that combines decision-making adaptability and resource utilization efficiency. At the algorithmic level, a deep reinforcement learning model is constructed using an improved DQN combined with policy gradient fusion, ensuring consistency between algorithm description and system implementation to map multimodal data such as soil moisture, evapotranspiration, and meteorological predictions collected by field sensing networks into state representations in the irrigation strategy space. The strategy function is optimized using the Time Difference (TD) method to enable the system to continuously update decisions in a dynamic environment. In order to avoid the limitations of single objective optimization, a multi-objective reward function was designed, which integrates crop yield, water resource utilization rate, and energy consumption into the evaluation indicators, and achieves adaptive balance through normalization and weight adjustment. At the system implementation level, a management platform integrating data collection, edge computing, cloud decision-making and mobile visualization is built to support the automatic generation, real-time adjustment and historical data backtracking analysis of irrigation plans. Field trials on a 35-ha wheat–corn site (12 plots, 4 months) evaluated a DQN–Policy Gradient hybrid, trained for 5000 episodes (200 steps each) with lr=0.0005, batch size=64, and buffer=10,000. Rewards weighted efficiency (0.5), yield (0.3), and energy (0.2).The system achieved 88.1% ± 1.7% water use (n=30, p<0.01), representing a 12.7% improvement in water resource utilization, and 8.3% ± 1.2% yield gain (n=30, p<0.05), outperforming thresholds.The research results provide a scalable technical path for intelligent management of agricultural water conservancy, and provide practical verification for the application of deep reinforcement learning in complex resource scheduling scenarios.


Full Text:

PDF

References


Saikai Y, Peake A, Chenu K. Deep reinforcement learning for irrigation scheduling using high-dimensional sensor feedback[J]. PLOS Water, 2023, 2(9): e0000169.https://doi.org/10.1371/journal.pwat.0000169.

Alibabaei K, Gaspar PD, Assunção E, Alirezazadeh S, Lima TM. Irrigation optimization with a deep reinforcement learning model: Case study on a site in Portugal[J]. Agricultural Water Management,2022,263:107480.https://doi.org/10.1016/j.agwat.2022.107480.

Yang X, Hu J, Porter D, Marek T, Heflin K, Kong H. Deep reinforcement learning-based irrigation scheduling[J]. Transactions of the ASABE, 2020, 63(3): 549–556.https://doi.org/10.13031/trans.13633.

Ding X , Du W .Optimizing Irrigation Efficiency using Deep Reinforcement Learning in the Field[J].ACM Transactions on Sensor Networks, 2024, 20(4).https://doi.org/10.1145/3662182.

Chen M, Cui Y, Wang X, et al. A reinforcement learning approach to irrigation decision-making for rice using weather forecasts[J]. Agricultural Water Management,2021,250:106838.https://doi.org/10.1016/j.agwat.2021.106838.

Jimenez AF, Cardenas PF, Jimenez F, et al. A cyber-physical intelligent agent for irrigation scheduling in horticultural crops[J]. Computers and Electronics in Agriculture,2020,178:105777.https://doi.org/10.1016/j.compag.2020.105777.

Alves RG, Maia RF, Lima F. Development of a digital twin for smart farming: Irrigation management system for water saving[J]. Journal of Cleaner Production, 2023,388:135920.https://doi.org/10.1016/j.jclepro.2023.135920.

Zia H, Rehman A, Harris NR, et al. An experimental comparison of IoT-based and traditional irrigation scheduling on a flood-irrigated subtropical lemon farm[J]. Sensors,2021,21(12):4175.https://doi.org/10.3390/s21124175.

Kelly TD, Foster T, Schultz DM. Assessing the value of deep reinforcement learning for irrigation scheduling[J]. Smart Agricultural Technology, 2024, 1: 100403. https://doi.org/10.1016/j.atech.2024.100403.

Liu K,Jiao X,Guo W,Gu Z,Li J. Improving irrigation performance by using adaptive border irrigation with deep reinforcement learning[J].Agronomy,2023,13(12):2907.https://doi.org/10.3390/agronomy13122907.

Mai Z, Zhang L, Li X, et al. Multi-objective modeling and optimization of water-saving irrigation scheduling using deep reinforcement learning[J]. Agricultural Water Management,2024,108959.https://doi.org/10.1016/j.agwat.2024.108959.

Chen Y, Lin M, Yu Z, Sun W, Fu W, He L. Enhancing cotton irrigation with distributional actor–critic reinforcement learning[J]. Agricultural Water Management,2025,307:109194.https://doi.org/10.1016/j.agwat.2024.109194.

Agyeman B T, Nouri M, Appels W M, Liu J, Shah S L. Learning-based multi-agent MPC for irrigation scheduling[J]. Control Engineering Practice, 2024, 147: 105908. https://doi.org/10.1016/j.conengprac.2024.105908.

Agyeman B T, Decard-Nelson B, Liu J, Shah S L. A semi-centralized multi-agent RL framework for efficient irrigation scheduling[J]. arXiv preprint, 2024, arXiv:2408.08442.https://doi.org/10.48550/arXiv.2408.08442.

Madondo M, Azmat M, Dipietro K, et al. A SWAT-based reinforcement learning framework for crop management[J]. arXiv preprint,2023,arXiv:2302.04988.https://doi.org/10.48550/arXiv.2302.04988.

Liu J, Yang J, Jie X, Chang F, Ma L, Su H. Optimizing irrigation scheduling using deep reinforcement learning and crop growth model[J]. ASABE Annual InternationalMeeting,2025:1–9.https://doi.org/10.13031/aim.202500569.

Kåge L, Milić V, Andersson M, Wallén M. Reinforcement learning applications in water resource management: a systematic literature review[J]. Frontiers in Water, 2025,7:1537868.https://doi.org/10.3389/frwa.2025.1537868.

Tao R, Zhao P, Wu J, Martin NF, Harrison MT, Ferreira C, Kalantari Z, Hovakimyan N. Optimizing crop management with reinforcement learning and imitation learning[J]. arXiv preprint, 2022, arXiv:2209.09991.https://doi.org/10.48550/arXiv.2209.09991.

Agyeman BT, Liu J, Shah SL. ReLU surrogates in mixed-integer MPC for irrigation scheduling[J]. arXiv preprint, 2024,arXiv:2409.12082.https://doi.org/10.48550/arXiv.2409.12082.

Hajgató G, Paál G, Gyires-Tóth B. Deep reinforcement learning for real-time optimization of pumps in water distribution systems[J]. arXiv preprint, 2020,arXiv:2010.06460.https://doi.org/10.48550/arXiv.2010.06460.




DOI: https://doi.org/10.31449/inf.v49i14.11138

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.