AI-Enabled Precision Irrigation for Water-Efficient and Sustainable Agriculture

Abstract

The diminishing availability of water for agriculture, sub optimal irrigation methods, climate uncertainty and rising food demands have led to a demand for intelligent and sustainable solutions to water management problems. This research introduces an AI Driven Arduino and Raspberry Pi irrigation system that maximizes agricultural water use by real time sensing, intelligent decision making, and automated irrigation control. The proposed system comprises soil moisture, soil temperature, soil relative humidity, rainfall, and water level sensors to continuously monitor the field conditions. Arduino is used for interfacing with sensors and actuators, Raspberry Pi for data processing, AI based analysis, monitoring and data logging. The sensor data collected is preprocessed and analyzed with an AI/ML model to calculate the irrigation needs depending on soil and environmental conditions. The water pump or irrigation valve is automatically turned on or off with a relay mechanism, based on the decision generated. The experimental results show the effectiveness of the proposed method in reducing unnecessary irrigation and the utilization of the resources. With a representative prototype set of results, the AI model was able to identify 94.2% of the events correctly, whereas the automated system was able to detect around 98.6% of events, with a mean response time of 2.4 seconds. About 35% less water was used than traditional irrigation methods and still kept the soil moisture level appropriate. The proposed system uses minimal manual intervention, it facilitates real time monitoring and offers adaptive irrigation management. The research shows the potential of the integration of artificial intelligence with low cost embedded platforms to create scalable, water efficient and sustainable smart agriculture solutions.

Introduction

The text presents an AI-based precision irrigation system using Arduino and Raspberry Pi to improve water efficiency and automate agricultural irrigation. Traditional irrigation methods often rely on fixed schedules or manual observation, which can cause over-irrigation, water and nutrient loss, soil degradation, and unnecessary energy consumption. Precision irrigation addresses these problems by supplying water according to real-time soil, crop, and environmental conditions.

The proposed system combines IoT sensors, Arduino, Raspberry Pi, and Artificial Intelligence (AI). Sensors continuously measure parameters such as soil moisture, soil temperature, humidity, rainfall, water level, and light intensity. Arduino collects sensor data and controls devices such as pumps and valves, while Raspberry Pi performs data processing, storage, communication, and AI-based decision making. The AI model analyzes multiple environmental factors to determine whether irrigation is required and how long it should operate, rather than relying only on a fixed soil-moisture threshold.

The system also supports real-time monitoring and remote access through a web or mobile interface. Alerts can notify farmers about low soil moisture, low water levels, abnormal sensor readings, or maintenance requirements. This reduces manual intervention and allows farmers to make timely decisions without constantly visiting the field.

Research Objectives

The study aims to:

• Develop an AI-enabled precision irrigation system using Arduino and Raspberry Pi.
• Automatically monitor soil and environmental conditions and control irrigation.
• Reduce unnecessary water consumption and improve irrigation efficiency.
• Support sustainable agricultural practices.

Research Gap

Previous studies have explored IoT monitoring, machine learning, cloud-based systems, edge computing, and automated irrigation separately or in combinations. However, the study identifies a lack of low-cost integrated systems that combine Arduino-based sensing and actuation, Raspberry Pi edge computing, real-time monitoring, AI-based irrigation prediction, and automatic water delivery in one platform.

Methodology

The research follows an experimental and prototype-based design. The system operates through four main stages:

1. Sensing – Sensors collect real-time agricultural and environmental data.
2. Data Processing – Arduino and Raspberry Pi clean, calibrate, normalize, and store the sensor data.
3. AI Decision Making – A lightweight machine-learning model predicts irrigation requirements.
4. Irrigation Control – Arduino activates or deactivates pumps and valves according to the AI decision.

The AI model is evaluated using accuracy, precision, recall, F1-score, prediction error, and response time. The prototype is also compared with conventional and threshold-based irrigation using water consumption, soil-moisture control, irrigation frequency, response time, reliability, and manual intervention.

Key Results

The AI model achieved strong performance:

• Accuracy: 94.2%
• Precision: 93.5%
• Recall: 95.0%
• F1-score: 94.2%
• Prediction error: 5.8%
• Average response time: 2.4 seconds

The proposed AI-based system also significantly reduced water consumption:

• Conventional irrigation: 1,200 L
• Threshold-based irrigation: 980 L
• AI-based irrigation: 780 L
• Water saved compared with conventional irrigation: 420 L (35%)

Soil-moisture results showed that the system adapted irrigation duration to the initial soil condition. Across four trials, initial moisture ranged from 25% to 30%, irrigation lasted 7–10 minutes, and final moisture reached approximately 47–51%, with an average of about 49%.

Conclusion

The research is successful in introducing an Arduino and Raspberry Pi based precision irrigation system with AI capabilities, which helps in achieving a better water resource management and is beneficial for sustainable agricultural practices. The system proposed involves real time measurement, embedded control, artificial intelligence, and self-control irrigation, which will provide soil and environmental data to assist in determining the water demand. Arduino offers an efficient way to interface sensors and control actuators, and Raspberry Pi can process data, analyze intelligently, monitor and log data. The system minimizes manual irrigation and allows watering to take place at the appropriate time as needed in the field. The AI decision accuracy of the system was approximately 94.2% based on the representative experimental results, and the water consumption was reduced by approximately 35%, the overall operational reliability was 98.6%, and the average response time was 2.4 seconds. The results show that it is possible to use water more efficiently by using an intelligent irrigation system and at the same time keep the soil moisture level at the right level. AI can also be a practical and scalable approach to smart farming, thanks to its integration with low cost embedded devices. The system as a whole shows great promise in water saving, water use efficiency, reduction of manual labor, and the sustainable use of the environment in agricultural production. It lays the groundwork for future research and innovation in intelligent, connected and data driven agricultural management systems.

References

[1] 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,” Comput. Electron. Agric., vol. 155, pp. 41–49, 2018, doi: 10.1016/j.compag.2018.09.040. [2] A. Goldstein, L. Fink, A. Meitin, S. Bohadana, O. Lutenberg, and G. Ravid, “Applying machine learning on sensor data for irrigation recommendations: Revealing the agronomist’s tacit knowledge,” Precis. Agric., vol. 19, no. 3, pp. 421–444, 2018, doi: 10.1007/s11119-017-9527-4. [3] N. K. Nawandar and V. R. Satpute, “IoT based low cost and intelligent module for smart irrigation system,” Comput. Electron. Agric., vol. 162, pp. 979–990, 2019, doi: 10.1016/j.compag.2019.05.027. [4] P. Kanade, M. Akhtar, F. David, and S. Kanade, “Agricultural mobile robots in weed management and control,” Int. J. Adv. Netw. Appl., vol. 13, no. 3, pp. 5001–5006, 2021. [5] P. Kumar and R. K. Singh, “IoT and machine learning approaches for automation of farm irrigation system,” Procedia Comput. Sci., vol. 167, pp. 1250–1257, 2020, doi: 10.1016/j.procs.2020.03.440. [6] R. R. Shamshiri, C. Weltzien, I. A. Hameed, I. J. Yule, T. E. Grift, S. K. Balasundram, L. Pitonakova, D. Ahmad, and G. Chowdhary, “Research and development in agricultural robotics: A perspective of digital farming,” Int. J. Agric. Biol. Eng., vol. 11, no. 4, pp. 1–14, 2018, doi: 10.25165/j.ijabe.20181104.4278. [7] S. V. Gaikwad, A. D. Vibhute, K. V. Kale, and S. C. Mehrotra, “An innovative IoT based system for precision farming,” Comput. Electron. Agric., vol. 187, Art. no. 106291, 2021, doi: 10.1016/j.compag.2021.106291. [8] S. Sathish Kumar et al., “IoT-based pest classification and automatic irrigation for precision agriculture using wireless sensor networks,” Turkish J. Comput. Math. Educ., vol. 12, no. 2, pp. 3298–3305, 2021. [9] P. Kanade and A. P., “Smart agriculture robot for sowing seed,” Int. J. Eng. Sci. Comput., vol. 11, no. 1, pp. 27563–27565, 2021. [10] Y. A. Rajwade et al., “Development of a smart IoT-based drip irrigation system for precision farming,” Irrig. Drain., vol. 72, pp. 1270–1284, 2023, doi: 10.1002/ird.2757. [11] P. Suresh et al., “IoT with evolutionary algorithm based deep learning for smart irrigation system,” Comput., Mater. Continua, vol. 71, no. 1, pp. 1713–1728, 2022, doi: 10.32604/cmc.2022.021789. [12] E. Prabhu and P. Karthik, “Design of machine learning based smart irrigation system for precision agriculture,” Comput., Mater. Continua, vol. 73, no. 1, pp. 165–181, 2022, doi: 10.32604/cmc.2022.022648. [13] M. Ramakrishnan et al., “Design and implementation of smart hydroponics farming using IoT-based AI controller with mobile application system,” J. Nanomater., vol. 2022, Art. no. 4435591, 2022, doi: 10.1155/2022/4435591. [14] V. Nandhini et al., “IoT-enabled edge computing model for smart irrigation system,” J. Intell. Syst., vol. 31, no. 1, pp. 679–691, 2022, doi: 10.1515/jisys-2022-0046. [15] P. Kanade and J. P. Prasad, “Machine learning techniques in plant conditions classification and observation,” in Proc. 2021 5th Int. Conf. Comput. Methodologies Commun. (ICCMC), 2021, pp. 729–734, doi: 10.1109/ICCMC51019.2021.9418386. [16] E. G. Anoop et al., “IoT and ML-based automatic irrigation system for smart agriculture system,” Agron. J., vol. 115, no. 4, pp. 1978–1995, 2023, doi: 10.1002/agj2.21344. [17] P. Kanade, P. Alva, J. P. Prasad, and S. Kanade, “Smart garbage monitoring system using Internet of Things (IoT),” in Proc. 2021 5th Int. Conf. Comput. Methodologies Commun. (ICCMC), 2021, pp. 330–335, doi: 10.1109/ICCMC51019.2021.9418359. [18] V. P. Kour et al., “Low power IoT electronics in precision irrigation,” Smart Agric. Technol., vol. 5, Art. no. 100310, 2023, doi: 10.1016/j.atech.2023.100310. [19] S. Singh et al., “Experimental performance of smart IoT-enabled drip irrigation system using and controlled through web-based applications,” Smart Agric. Technol., vol. 4, Art. no. 100215, 2023, doi: 10.1016/j.atech.2023.100215. [20] X. Liu et al., “Machine learning for smart irrigation in agriculture: How far along are we?” Information, vol. 15, no. 6, Art. no. 306, 2024, doi: 10.3390/info15060306. [21] K. Taueatsoala, C. Daniels, A. J. Ramsunar, P. Bronkhorst, and A. E. Ezugwu, “TinyML-enabled IoT for sustainable precision irrigation,” arXiv, 2026, doi: 10.48550/arXiv.2601.13054. [22] P. Kanade, “Raspberry Pi based automated garden sprinkler system with integrated weather, humidity, and soil moisture monitoring,” Int. Res. J. Eng. Technol. (IRJET), vol. 12, no. 12, pp. 728–736, 2025, doi: 10.5281/ZENODO.21940827. [23] S. G. Rahul, S. J. Rithikkaa, T. M. Amirthalakshmi, and M. Gayathri, “Sustainable agriculture through IoT-driven smart irrigation with explainable AI,” Front. Sustain. Food Syst., vol. 10, Art. no. 1847041, 2026, doi: 10.3389/fsufs.2026.1847041. [24] N. Addura, S. Silas, J. Anitha, and M. Mythily, “Edge computing for smart irrigation: Deploying an embedded LSTM AI model with HTTP POST communication via Flask on Raspberry Pi 5,” Procedia Comput. Sci., vol. 283, pp. 4340–4349, 2026, doi: 10.1016/j.procs.2026.06.492. [25] M. Nasar, M. Abu Kausar, and M. A. Nayyer, “A machine learning approach to optimize water usage in precision agriculture for environmental sustainability,” Next Res., vol. 8, Art. no. 101644, 2026, doi: 10.1016/j.nexres.2026.101644. [26] P. Kanade and J. P. Prasad, “Arduino based machine learning and IoT smart irrigation system,” Int. J. Soft Comput. Eng. (IJSCE), vol. 10, no. 4, pp. 1–5, 2021.

Copyright

Copyright © 2026 Priyadharshini V, Hemapriya . 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.