IoT-Enabled ML for Smart Agriculture: A Predictive Approach to Crop Irrigation

Abstract

Modern agriculture is being redefined by the convergence of Machine Learning (ML) and the IOT, which makes it possible to make intelligent, data-driven decisions and continuously monitor the environment. In order to optimize water usage across five distinct crop kinds, this study discusses the construction of a smart irrigation prediction framework that makes use of data gathered by the IOT, such as measurements of soil moisture, ambient temperature, humidity, pH levels, and crop health indicators. To attain more accuracy and flexibility, our approach includes a wider variety of environmental variables than prior systems, such as those that used a simplified website to apply ML to only three crops. Early tests using traditional ML classifiers produced very encouraging results. Building on this, we expanded our research to include more sophisticated ensemble and boosting techniques, such as Gradient Boosting, Random Forest, Decision Tree, and AdaBoost. In terms of prediction accuracy, these models performed better than others such as Support Vector Machine and K-Nearest Neighbors. We used cutting-edge oversampling techniques including SMOTE, ADASYN, and Random Oversampling to address class imbalance in the training data. According to the experimental findings, boosting and ensemble approaches significantly enhance irrigation schedule prediction performance. By providing a scalable, high-performing solution that takes into consideration a wider range of crop and environmental parameters, our work advances the field of precision farming. To improve prediction skills and agricultural resource efficiency, future developments will use real-time sensor data and investigate deep learning systems.

Introduction

The integration of IoT (Internet of Things) and Machine Learning (ML) technologies is revolutionizing agriculture, particularly in enhancing irrigation efficiency to address water scarcity, climate change, and food security challenges. Traditional irrigation methods, relying on fixed schedules or manual inspection, often lead to water overuse and environmental risks.

IoT enables real-time monitoring of key environmental factors like soil moisture, temperature, and humidity. ML, especially advanced techniques such as deep learning and ensemble methods, analyzes this data to accurately predict crop water needs, improving irrigation scheduling and crop productivity. Edge computing further boosts efficiency by reducing reliance on cloud processing, leading to faster and more reliable irrigation responses.

Despite progress, challenges remain, including data imbalance, model scalability, and quality. The paper proposes a systematic approach combining IoT data collection with robust ML models to improve irrigation demand predictions. Key steps include data preprocessing, normalization, and handling class imbalance through oversampling methods like SMOTE and ADASYN.

Multiple ML algorithms were tested—Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), Decision Trees, and AdaBoost—with ensemble methods generally outperforming simpler models in accuracy and stability. Random Forest and AdaBoost showed particular promise due to their handling of noisy, imbalanced data and interpretability, important for practical farming applications.

The study enhances previous work by incorporating diverse crop types, richer environmental data, and more scalable predictive models, aiming for intelligent, sustainable irrigation systems that optimize water use and support precision agriculture.

Conclusion

This study concentrated on using ML with the IOT to improve precision irrigation in agriculture. Several ML techniques were evaluated to forecast irrigation requirements using sensor-gathered environmental data. Oversampling techniques including SMOTE, ADASYN, and Random Oversampling were employed to balance the data and increase prediction accuracy because of the dataset\'s unequal distribution of irrigation classes. Findings indicate that ensemble-based models like Random Forest and Decision Tree delivered superior accuracy and reliability in classifying irrigation needs. The use of oversampling techniques improved recall and F1-scores for minority classes, mitigating the negative impact of imbalanced data. However, models like Support Vector Machine (SVM) were less effective in handling class distribution disparities, emphasizing the importance of data preprocessing in precision agriculture applications. The study demonstrates that IoT-integrated ML frameworks can significantly contribute to efficient water management by automating irrigation scheduling, reducing excessive water usage, and promoting higher crop productivity. The results underscore the potential of data-driven agricultural solutions in supporting sustainable farming practices and resource optimization.

References

[1] Kashyap, P. K., Kumar, S., Jaiswal, A., Prasad, M., & Gandomi, A. H. (2021). Towards precision agriculture: IoT-enabled intelligent irrigation systems using deep learning neural network. IEEE Sensors Journal, 21(16), 17479-17491. [2] Saha, G., Shahrin, F., Khan, F. H., Meshkat, M. M., & Azad, A. A. M. (2025). Smart IoT-driven precision agriculture: Land mapping, crop prediction, and irrigation system. PloS one, 20(3), e0319268. [3] Z Premkumar, S., & Sigappi, A. N. (2022). IoT-enabled edge computing model for smart irrigation system. Journal of Intelligent Systems, 31(1), 632-650. [4] Aldossary, M., Alharbi, H. A., & Hassan, C. A. U. (2024). IOT-Enabled ML Models for Efficient Monitoring of Smart Agriculture. IEEE Access. [5] BP, U. R., Sattar, K. N. A., & Elngar, A. A. (2024). A SMART IRRIGATION SYSTEM USING THE IOT AND ADVANCED ML MODEL. Journal of Smart Internet of Things (JSIoT), 2024(02), 13-25. [6] Ramachandran, V., Ramalakshmi, R., Kavin, B. P., Hussain, I., Almaliki, A. H., Almaliki, A. A., ... & Hussein, E. E. (2022). Exploiting IoT and its enabled technologies for irrigation needs in agriculture. Water, 14(5), 719. [7] Bakthavatchalam, K., Karthik, B., Thiruvengadam, V., Muthal, S., Jose, D., Kotecha, K., & Varadarajan, V. (2022). IoT framework for measurement and precision agriculture: predicting the crop using ML algorithms. Technologies, 10(1), 13. [8] Lakshmi, G. P., Asha, P. N., Sandhya, G., Sharma, S. V., Shilpashree, S., & Subramanya, S. G. (2023). An intelligent IOT sensor coupled precision irrigation model for agriculture. Measurement: Sensors, 25, 100608. [9] Syed, L. (2024). Smart agriculture using ensemble ML techniques in IoT environment. Procedia Computer Science, 235, 2269-2278. [10] Islam, M. R., Oliullah, K., Kabir, M. M., Alom, M., & Mridha, M. F. (2023). ML enabled IoT system for soil nutrients monitoring and crop recommendation. Journal of Agriculture and Food Research, 14, 100880. [11] Lephondo, I., Telukdarie, A., Munien, I., Onkonkwo, U., & Vermeulen, A. (2024). The outcomes of smart irrigation system using ML to minimize water usage within the agriculture sector. Procedia Computer Science, 237, 525-532. [12] Mohyuddin, G., Khan, M. A., Haseeb, A., Mahpara, S., Waseem, M., & Saleh, A. M. (2024). Evaluation of ML approaches for precision farming in Smart Agriculture System-A comprehensive Review. IEEE Access. [13] Gaddam, S., Singh, A., Srinivasan, A., Prakash, B., Prabagaran, S., & Maranan, R. (2025). IoT-driven ML for precision agriculture for revolutionizing crop management. In Hybrid and Advanced Technologies (pp. 84-89). CRC Press. [14] Kadiyala, S., Potluri, C. S., Birke, A. H., Mehra, A., Rajput, S., & Padmavathi, K. (2024, March). An Intelligent and Cost-Effective IoT-Based Irrigation System Using ML. In 2024 2nd International Conference on Disruptive Technologies (ICDT) (pp. 380-385). IEEE. [15] Suresh, P., Aswathy, R. H., Arumugam, S., Albraikan, A. A., Al-Wesabi, F. N., Hilal, A. M., & Alamgeer, M. (2022). IoT with evolutionary algorithm based deep learning for smart irrigation system. Computers, Materials & Continua, 71(1), 1713-1728. [16] Rahu, M. A., Chandio, A. F., Aurangzeb, K., Karim, S., Alhussein, M., & Anwar, M. S. (2023). Toward design of internet of things and ML-enabled frameworks for analysis and prediction of water quality. IEEE Access, 11, 101055-101086. [17] Quy, V. K., Hau, N. V., Anh, D. V., Quy, N. M., Ban, N. T., Lanza, S., ... & Muzirafuti, A. (2022). IoT-enabled smart agriculture: architecture, applications, and challenges. Applied Sciences, 12(7), 3396. [18] Chaudhary, R. R., Jain, S., & Gupta, S. (2024). A critical review on hybrid framework for precise farming with application of ML (ML) and IOT. Journal of Integrated Science and Technology, 12(2), 730-730. [19] Quy, V. K., Hau, N. V., Anh, D. V., Quy, N. M., Ban, N. T., Lanza, S., ... & Muzirafuti, A. (2022). IoT-enabled smart agriculture: architecture, applications, and challenges. Applied Sciences, 12(7), 3396. [20] Rahu, M. A., Shaikh, M. M., Karim, S., Soomro, S. A., Hussain, D., & Ali, S. M. (2024). Water quality monitoring and assessment for efficient water resource management through internet of things and ML approaches for agricultural irrigation. Water Resources Management, 38(13), 4987-5028. [21] Kancharagunta, K. B., Akkem, Y., Vembadi, M., Garalapati, S. T., Hari Pratap Varma, A., & Ruha Jessica, M. (2024, February). Crop Recommendation System Using ML and IoT: A Survey. In International Conference On Innovative Computing And Communication (pp. 63-86). Singapore: Springer Nature Singapore. [22] Ajith, S., Vijayakumar, S., & Elakkiya, N. (2025). Yield prediction, pest and disease diagnosis, soil fertility mapping, precision irrigation scheduling, and food quality assessment using ML and deep learning algorithms. Discover Food, 5(1), 1-23. [23] Del-Coco, M., Leo, M., & Carcagnì, P. (2024). ML for smart irrigation in agriculture: How far along are we?. Information, 15(6), 306. [24] Josephine, M. S., & Jeyabalaraja, V. (2024). IOT-BASED CROP RECOMMENDATION SYSTEM FOR PRECISION AGRICULTURE. Journal of Data Acquisition and Processing, 39(2), 16. [25] Bhoi, A., Nayak, R. P., Bhoi, S. K., Sethi, S., Panda, S. K., Sahoo, K. S., & Nayyar, A. (2021). IoT-IIRS: Internet of Things based intelligent-irrigation recommendation system using ML approach for efficient water usage. PeerJ Computer Science, 7, e578. [26] Rokade, A., Singh, M., Malik, P. K., Singh, R., & Alsuwian, T. (2022). Intelligent data analytics framework for precision farming using IoT and regressor ML algorithms. Applied Sciences, 12(19), 9992. [27] Ahmed, R. M. (2024). Integration of Wireless Sensor Networks, Internet of Things, Artificial Intelligence, and Deep Learning in Smart Agriculture: A Comprehensive Survey: Integration of Wireless Sensor Networks, Internet of Things. Journal of Innovative Intelligent Computing and Emerging Technologies (JIICET), 1(01), 8-19.

Copyright

Copyright © 2025 Bodapati Jaswanth Venkata Ratna Rao, Sunkari Guru Naidu, Lingala Chandra Sekhar, V Karthik, Abrar Ahmed Raza. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.