AIOT in Predictive Agriculture - IoT and AI Integration for Real-Time Soil Monitoring and Smart Irrigation in Predictive Agriculture

Abstract

Modern agriculture faces severe challenges due to climate volatility, accelerating groundwater depletion, and the global imperative to maximize crop production on diminishing arable land. Traditional irrigation frameworks rely predominantly on static schedules or reactive threshold switching, leading to substantial water waste, energy inefficiencies, and suboptimal crop yields. To overcome these limitations, this paper proposes an end-to-end Artificial Intelligence of Things (AIoT) framework designed for real-time multi-parameter soil tracking and predictive smart irrigation. The system architecture deploys low-power IoT field nodes driven by ESP32 microcontrollers, integrated with capacitive soil moisture sensors, environmental sensors, and soil pH probes that stream telemetry data over lightweight MQTT protocols. To transition from reactive monitoring to proactive resource allocation, a cloud-based predictive engine utilizes Long Short-Term Memory (LSTM) neural networks to forecast 24-to-48-hour soil moisture depletion dynamics based on historical moisture profiles and localized meteorological factors. Experimental validation across a 90-day testbed demonstrates that the proposed predictive framework achieves a to reduction in total water consumption while maintaining optimal volumetric soil water content. Furthermore, deep-sleep dynamic power profiling confirms node energy autonomy of up to 219 days on a single battery charge, presenting a scalable, sustainable, and economically viable solution for precision agriculture.

Introduction

The text presents an AIoT-based smart irrigation system designed to make agriculture more efficient, sustainable, and data-driven.

• Problem: Traditional irrigation methods, such as manual flooding and fixed timers, cannot respond to changing soil and weather conditions. Over-irrigation wastes water and energy, causes nutrient loss and soil erosion, while under-irrigation causes drought stress and reduces crop yields.

• Proposed Solution: The paper combines IoT sensors with Artificial Intelligence (AI) to create an autonomous, closed-loop irrigation system. IoT continuously collects field data, while AI analyzes the data and predicts future soil moisture conditions.

• Main Contributions:

  1. A low-power, multi-sensor IoT node suitable for outdoor agricultural environments.
  2. An LSTM neural network that predicts soil-moisture dry-down 24–48 hours in advance.
  3. Improved water and energy efficiency through predictive irrigation and solar-powered, deep-sleep operation.

• System Architecture: The system has three main tiers:

  • Perception Tier: ESP32, capacitive soil-moisture sensors, DHT22 temperature/humidity sensor, DS18B20 soil-temperature sensor, and pH sensor.
  • Network Tier: Sensor data is transmitted using lightweight MQTT to an EMQX cloud broker.
  • Intelligence/Application Tier: An LSTM model predicts soil moisture and automatically controls irrigation valves or pumps.

• Evolution from Previous Systems: Earlier systems used fixed moisture thresholds, while newer IoT systems mainly provide remote monitoring. Standalone machine-learning systems can make predictions but are not necessarily connected to real-time automated irrigation. The proposed AIoT framework integrates sensing, communication, prediction, and actuation into one autonomous loop.

• Performance: The proposed system claims approximately 28–35% water-use reduction, a 24–48 hour prediction horizon, and high field energy autonomy through deep-sleep operation and solar power.

• Implementation: A prototype was tested for 90 days on a multi-zone agricultural testbed. The firmware used C++/Arduino, while the AI pipeline used Python with TensorFlow/Keras, Pandas, and Scikit-Learn.

Conclusion

This paper presented an integrated end-to-end AIoT framework combining low-power hardware sensor nodes, lightweight MQTT communications, and cloud-based LSTM predictive neural networks for precision agriculture. By transitioning from reactive irrigation to data-driven proactive forecasting, the system addresses key agricultural water and energy management challenges.

References

[1] S. P. Sudha and J. B. Shajilin Loret, “A review on machine learning-based precision agriculture techniques for crop farming monitoring with IOT,” Discover Environment, vol. 4, article 10, 2026. [2] A. Goap, D. Sharma, A. K. Shukla, and C. Rama Krishna, “An IoT based smart irrigation management system using Machine learning and open source technologies,” Computers and Electronics in Agriculture, vol. 155, pp. 41–49, 2018. DOI: 10.1016/j.compag.2018.09.040. [3] A. E. G. Anoop and G. Josemin Bala, “IoT and ML-based automatic irrigation system for smart agriculture system,” Agronomy Journal, 2023. DOI: 10.1002/agj2.21344. [4] “Artificial intelligence of things (AIoT) for precision agriculture: applications in smart irrigation, nutrient and disease management,” Smart Agricultural Technology, vol. 12, article 101629, 2025. DOI: 10.1016/j.atech.2025.101629. [5] “Advances in soil moisture measurement techniques and prediction using artificial intelligence: An extensive and systematic review,” Smart Agricultural Technology, vol. 12, article 101613, 2025. DOI: 10.1016/j.atech.2025.101613.

Copyright

Copyright © 2026 Gowri M., Boomika M., Rakshana S., Rubali R.. 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.