Department of Computer Science And Engineering, School of Computing, Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology, Chennai, Tamil Nadu, India.
Department of Computer Science And Engineering, School of Computing, Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology, Chennai, Tamil Nadu, India.
The usage of autonomous greenhouses has become essential in meeting the food demands of the world's expanding population. Finding the right optimization strategy to sustain growth, yield, and profit is one of the major issues with greenhouse production. Addressing this issue effectively requires a combination of advanced technologies, data-driven insights, and innovative management practices. The overarching goal is to maximize crop yield and quality while minimizing input costs and environmental impact. The automated optimizations, which are often implemented using reinforcement learning algorithms, encounter issues with sample efficiency and robustness due to the time-consuming nature of the real-world simulation. Therefore, the goal of this research is to solve these issues by combining the SAC and Q learning algorithms to create an ensemble method. To properly optimize the worst-case inefficient samples, a discrete randomization and dropout module is included. The problem of sample efficiency and resilience is treated as a Mismatch Markov Decision Optimisation problem. The suggested model outperforms the current methods in handling the robustness and sample efficiency issues, according to an experimental evaluation. Additionally, this improvement increased production and maximized net profit.
Keywords
Mismatch Markov Decision Optimization Problem (MMDP), Discrete Randomization, Dropout, Ensembled Q and SAC Reinforcement Algorithm (EQSACRL).
J. Guo et al., “Revolutionizing Agriculture: Real-Time Ripe Tomato Detection with the Enhanced Tomato-YOLOv7 System,” IEEE Access, vol. 11, pp. 133086–133098, 2023, doi: 10.1109/access.2023.3336562.
S. K. Reddy et al., “Early Sensing of Tomato Brown Rugose Fruit Virus in Tomato Plants via Electrical Measurements,” IEEE Sensors Letters, vol. 6, no. 5, pp. 1–4, May 2022, doi: 10.1109/lsens.2022.3161595.
Y.-P. Huang, T.-H. Wang, and H. Basanta, “Using Fuzzy Mask R-CNN Model to Automatically Identify Tomato Ripeness,” IEEE Access, vol. 8, pp. 207672–207682, 2020, doi: 10.1109/access.2020.3038184.
T. Kojic, M. Simic, M. Pojic, and G. M. Stojanovic, “Detecting Freshness of Fruit and Vegetable Without and With Edible Protein-Based Foil,” IEEE Sensors Journal, vol. 22, no. 16, pp. 15698–15705, Aug. 2022, doi: 10.1109/jsen.2022.3188388.
S. Hemming, F. de Zwart, A. Elings, I. Righini, and A. Petropoulou, “Remote Control of Greenhouse Vegetable Production with Artificial Intelligence—Greenhouse Climate, Irrigation, and Crop Production,” Sensors, vol. 19, no. 8, p. 1807, Apr. 2019, doi: 10.3390/s19081807.
I. Jebril et al., “Deep Learning based DDoS Attack Detection in Internet of Things: An Optimized CNN-BiLSTM Architecture with Transfer Learning and Regularization Techniques,” Infocommunications journal, vol. 16, no. 1, pp. 2–11, 2024, doi: 10.36244/icj.2024.1.1.
A. Ramírez-Arias, F. Rodríguez, J. L. Guzmán, and M. Berenguel, “Multiobjective hierarchical control architecture for greenhouse crop growth,” Automatica, vol. 48, no. 3, pp. 490–498, Mar. 2012, doi: 10.1016/j.automatica.2012.01.002.
A. Elings et al., “Feed-Forward Control of Water and Nutrient Supply in Greenhouse Horticulture: Development of A System,” Acta Horticulturae, no. 654, pp. 195–202, Aug. 2004, doi: 10.17660/actahortic.2004.654.21.
V. K. Perumal, S. T, S. P R, and D. S, “CNN based plant disease identification using PYNQ FPGA,” Systems and Soft Computing, vol. 6, p. 200088, Dec. 2024, doi: 10.1016/j.sasc.2024.200088.
M. Rahnemoonfar and C. Sheppard, “Deep Count: Fruit Counting Based on Deep Simulated Learning,” Sensors, vol. 17, no. 4, p. 905, Apr. 2017, doi: 10.3390/s17040905.
Bac, C. W. (2015). Improving obstacle awareness for robotic harvesting of sweet-pepper. [internal PhD, WU, Wageningen University]. Wageningen University. https://doi.org/10.18174/327202 [13] Nieuwenhuizen, A.T.; Kool, J.; Suh, H.K.; Hemming, J. Automated spider mite damage detection on tomato leaves in greenhouses. ActaHortic. 2020, 1268, 165–172.
H. K. Suh, J. IJsselmuiden, J. W. Hofstee, and E. J. van Henten, “Transfer learning for the classification of sugar beet and volunteer potato under field conditions,” Biosystems Engineering, vol. 174, pp. 50–65, Oct. 2018, doi: 10.1016/j.biosystemseng.2018.06.017.
L. F. M. Marcelis, A. Elings, P. H. B. de Visser, and E. Heuvelink, “SIMULATING GROWTH AND DEVELOPMENT OF TOMATO CROP,” Acta Horticulturae, no. 821, pp. 101–110, Mar. 2009, doi: 10.17660/actahortic.2009.821.10.
T. Morimoto and Y. Hashimoto, “AI approaches to identification and control of total plant production systems,” Control Engineering Practice, vol. 8, no. 5, pp. 555–567, May 2000, doi: 10.1016/s0967-0661(99)00176-8.
B. Ban and S. Kim, “Control of nonlinear, complex and black-boxed greenhouse system with reinforcement learning,” 2017 International Conference on Information and Communication Technology Convergence (ICTC), pp. 913–918, Oct. 2017, doi: 10.1109/ictc.2017.8190813.
John E. Preece and Paul E. Read. The Biology of Horticulture: An introductory textbook. John Wiley & Sons, 2005. 5, 6, 7, 27, 83.
P. Ponce, A. Molina, P. Cepeda, E. Lugo, and B. MacCleery, Greenhouse Design and Control. CRC Press, 2014. doi: 10.1201/b17391.
M.-H. Huang and R. T. Rust, “Artificial Intelligence in Service,” Journal of Service Research, vol. 21, no. 2, pp. 155–172, Feb. 2018, doi: 10.1177/1094670517752459.
K. Jha, A. Doshi, P. Patel, and M. Shah, “A comprehensive review on automation in agriculture using artificial intelligence,” Artificial Intelligence in Agriculture, vol. 2, pp. 1–12, Jun. 2019, doi: 10.1016/j.aiia.2019.05.004.
WouterJacobus Peter Kuijpers. Model Selection and Optimal Control Design for Automatic Greenhouse Climate Control. PhD thesis, Mechanical Engineering, March 2021. Proefschrift. 2, 10.
Z. An et al., “A Simulator-based Planning Framework for Optimizing Autonomous Greenhouse Control Strategy,” Proceedings of the International Conference on Automated Planning and Scheduling, vol. 31, pp. 436–444, May 2021, doi: 10.1609/icaps.v31i1.15989.
FH de Zwart. Simulatiemodelkaspro, 2022. URL: https://www.wur.nl/nl/show/Simulatiemodel-KASPRO-1.htm. 10.
L. Wang, X. He, and D. Luo, “Deep Reinforcement Learning for Greenhouse Climate Control,” 2020 IEEE International Conference on Knowledge Graph (ICKG), pp. 474–480, Aug. 2020, doi: 10.1109/icbk50248.2020.00073.
Kurtland Chua, Roberto Calandra, Rowan McAllister, and Sergey Levine. Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models. Advances in Neural Information Processing Systems, 2018-Decem(NeurIPS):4754–4765, 2018. ISSN10495258.
Michael Janner, Justin Fu, Marvin Zhang, and Sergey Levine. When to trust your model:Model-based policy optimization. In Advances in Neural Information Processing Systems,pages 12519–12530, 2019.
Kimin Lee, Michael Laskin, AravindSrinivas, and Pieter Abbeel. SUNRISE: A simple unified framework for ensemble learning in deep reinforcement learning. CoRR, abs/2007.04938, 2020.
TuomasHaarnoja, Haoran Tang, Pieter Abbeel, and Sergey Levine. Reinforcement learning with deep energy-based policies. CoRR, abs/1702.08165, 2017.
R. S. Sutton, “Dyna, an integrated architecture for learning, planning, and reacting,” ACM SIGART Bulletin, vol. 2, no. 4, pp. 160–163, Jul. 1991, doi: 10.1145/122344.122377.
A. Tamar, Y. Glassner, and S. Mannor, “Optimizing the CVaR via Sampling,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 29, no. 1, Feb. 2015, doi: 10.1609/aaai. v29i1.9561.
G Parameswaran and K Sivaprasath. Arduino based smart drip irrigation system using internet of things. International Journal of Engineering Science and Computing, 6(5):5518–5521, 2016.
CRediT Author Statement
The authors confirm contribution to the paper as follows:
Conceptualization: Gandhimathi S, Senthilkumaran B, Jude Moses Anto Devakanth J, Nithya K V and Jayaprakash Chinnadurai;
Methodology: Gandhimathi S, Senthilkumaran B and Jude Moses Anto Devakanth J;
Writing- Original Draft Preparation: Gandhimathi S, Senthilkumaran B, Jude Moses Anto Devakanth J, Nithya K V and Jayaprakash Chinnadurai;
Visualization: Gandhimathi S, Senthilkumaran B and Jude Moses Anto Devakanth J;
Investigation: Nithya K V and Jayaprakash Chinnadurai;
Supervision: Gandhimathi S, Senthilkumaran B and Jude Moses Anto Devakanth J;
Writing- Reviewing and Editing: Gandhimathi S, Senthilkumaran B, Jude Moses Anto Devakanth J, Nithya K V and Jayaprakash Chinnadurai;
All authors reviewed the results and approved the final version of the manuscript.
Acknowledgements
The author(s) received no financial support for the research, authorship, and/or publication of this article.
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
Senthilkumaran B
Department of Computer Science And Engineering, School of Computing, Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology, Chennai, Tamil Nadu, India.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Gandhimathi S, Senthilkumaran B, Jude Moses Anto Devakanth J, Nithya K V and Jayaprakash Chinnadurai, “Robust Ensembled Model Based Reinforcement Learning for Better Tomato Yield in Greenhouse”, Journal of Machine and Computing, pp. 1140-1151, April 2025, doi: 10.53759/7669/jmc202505090.
