Adaptive Precision Agriculture Through Iot And Reinforced Machine Learning (Q-Learning): A Sustainable Approach For Optimized Plant Growth
DOI:
https://doi.org/10.29284/ijasis.11.6s.2025.9-22Keywords:
Sentiment Analysis, Social Media, Feature Extraction, Machine Learning, NLP, XGBoost, SVM, Naïve Bayes.Abstract
The convergence of the Internet of Things (IoT) and machine learning is transforming precision agriculture by enabling data-driven optimization of plant growth in varying environments. This study explores the integration of IoT-based sensing with reinforcement learning, specifically Q-learning, to enhance plant growth management in both controlled and natural field conditions. The primary aim is to derive actionable insights that boost crop productivity while conserving resources. An IoT-enabled system was designed to capture real-time information from sensors monitoring soil temperature, soil moisture, air temperature, humidity, and growth parameters. Controlled experiments simulated ideal growth settings, whereas on-field trials reflected natural variability. These datasets were analysed using a Q-learning algorithm, allowing the system to make adaptive decisions and optimize plant development. Iterative learning enabled the framework to establish links between environmental factors and plant responses, dynamically adjusting irrigation and environmental controls based on feedback. Experimental results demonstrated that the controlled setup yielded greater consistency in growth and higher resource efficiency due to its stability. In contrast, the on-field system underscored adaptability by generating strategies to cope with environmental uncertainty. This dual evaluation highlights the combined potential of IoT and reinforcement learning to support sustainable agriculture. The findings validate IoT-based adaptive monitoring as a practical tool for optimizing plant growth. The proposed approach offers pathways to improve crop yields, minimize input use, and promote long-term sustainability. Future research will extend the framework to diverse crops, enhance Q-learning models for complex decision- making, and integrate additional environmental parameters for comprehensive analysis.
References
1. Ahmed, F., Ali, S., & Kumar, V. (2022). Design and Implementation of IoT-Enhanced Plant Growth Analysis System Using Machine Learning. IEEE Transactions on Automa- tion Science and Engineering, 19(2), 489-499.
2. Gupta, P., Mehta, S., & Choudhury, B. (2021). IoT and Deep Reinforcement Learning for Automated Plant Growth Analysis in Open Fields. Computers and Electronics in Agricul- ture, 190, 106471.
3. Centorame, L., Gasperini, T., Ilari, A., Del Gatto, A., & Foppa Pedretti, E. (2024). An Overview of Machine Learning Applications on Plant Phenotyping, with a Focus on Sun- flower. Agronomy, 14(4), 719.
4. Cao, X., Yao, Y., Li, L., Zhang, W., An, Z., Zhang, Z., Xiao, L., Guo, S., Cao, X., Wu, M.,
& Luo, D. (2021). IGrow: A Smart Agriculture Solution to Autonomous Greenhouse Con- trol. arXiv preprint arXiv:2107.05464.
5. Azimi, S., Wadhawan, R., & Gandhi, T. K. (2021). Intelligent Monitoring of Stress In- duced by Water Deficiency in Plants using Deep Learning. arXiv preprint arXiv:2104.07911.
6. Drees, L., Junker-Frohn, L. V., Kierdorf, J., & Roscher, R. (2021). Temporal Prediction and Evaluation of Brassica Growth in the Field using Conditional Generative Adversarial Networks. arXiv preprint arXiv:2105.07789.
7. Amacker, J., Kleiven, T., Grigore, M., Albrecht, P., & Horn, C. (2022). A Learned Simula- tion Environment to Model Plant Growth in Indoor Farming. arXiv preprint arXiv:2212.03155.
8. Gourshettiwar, P., & Reddy, K. T. V. (2024). A Comprehensive Analysis with Machine Learning Algorithm and IoT Integration in Hydroponic Vegetable System for Nutrition Management of Plants/Crops. Preprints, 202409.0279.
9. Patra, S., & Sahoo, S. (2024). Plant Growth Analysis using IoT and Statistical Machine Learning Techniques for Broccoli Plants. International Journal of Advanced Research in Science, Engineering and Technology, 11(3), 1234-1240.
10. Balaji, G., & Kumar, R. (2022). IoT-enabled smart monitoring system for plant growth us- ing predictive analytics. Journal of Sensor Technology and Applications, 5(2), 145-153.
11. Nandhini, S., & Rajesh, S. (2023). A machine learning approach for analyzing crop health and growth using IoT sensors. International Journal of Agricultural Technology and Inno- vation, 7(1), 29-38.
12. Zhang, W., Liu, Y., & He, J. (2021). Predicting plant growth in smart agriculture using IoT-based data and ML algorithms. Computers in Agriculture and Natural Resources, 10(4), 202-212.
13. Verma, P., & Chauhan, D. (2023). Deep learning-based phenotyping for plant growth in precision agriculture. Agricultural Data Science Journal, 15(3), 334-350.
14. Singh, K., & Sharma, R. (2022). IoT and machine learning-based framework for early de- tection of plant diseases and growth monitoring. International Journal of IoT Applications in Agriculture, 8(2), 102-115.
15. Yadav, N., & Gupta, A. (2024). IoT-integrated plant growth monitoring system using hy- brid machine learning models. Applied Computing in Agriculture, 12(1), 56-70.
16. Park, J., & Kim, H. (2022). Smart farming with IoT and AI: Enhancing plant growth and yield prediction. Artificial Intelligence in Agriculture, 6(3), 123-135.
17. Patel, R., & Kumar, M. (2023). IoT-based growth monitoring of medicinal plants using decision tree algorithms. International Journal of Medicinal Plant Studies, 9(2), 86-94.
18. Fernandes, L., & Das, S. (2021). IoT and deep learning techniques for predicting optimal growth conditions for plants. Computers in Sustainable Agriculture, 5(3), 99-112.
19. Wang, Z., & Lee, K. (2023). Using IoT-enabled devices and random forests for monitoring plant growth stages. Precision Agriculture Research Journal, 9(1), 45-60.
20. Singh, A., & Tiwari, R. (2022). ML-based analysis of plant growth under different envi- ronmental conditions using IoT sensors. International Journal of Agricultural Data Sci- ence, 5(3), 67-81.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
