Artificial Intelligence of Things (AIoT) for Precision Irrigation: A Comprehensive Review of Applications, Challenges, and Future Directions

• Iyanda M. ANIMASHAUN

  Author

• Abubakar S. MOHAMMED

  Author

• Ibrahim A. KUTI

  Author

• Peter A. OBASA

  Author

• Rashidat ANIYIKAYE

  Author

• Yahaya MOHAMMED

  Author

• Yusuf M. OTACHE

  Author

The convergence of Artificial Intelligence (AI) and the Internet of Things (IoT) has given rise to the Artificial Intelligence of Things (AIoT), a paradigm that is fundamentally reshaping agricultural water management. This review synthesises current AIoT applications in precision irrigation, examining how sensor networks, edge and cloud computing infrastructures, and machine learning algorithms are being deployed to optimise water utilisation in agricultural systems. Through a systematic examination of recent literature, it analyses the technological enablers, implementation architectures, machine learning models, and decision-support frameworks that constitute modern AIoT irrigation systems. The evidence indicates that AIoT-driven systems can substantially reduce water consumption while simultaneously improving crop yields through real-time soil moisture monitoring, predictive analytics, and autonomous irrigation scheduling. Machine learning models—including Random Forest, Support Vector Machines, Artificial Neural Networks, and Long Short-Term Memory networks—have demonstrated considerable efficacy in modelling the complex, non-linear relationships among soil properties, climatic variables, and crop characteristics that underpin accurate irrigation forecasting. Deep learning approaches, particularly Convolutional Neural Networks and hybrid architectures, have achieved high precision in predicting evapotranspiration and soil moisture dynamics. Reinforcement learning is emerging as a promising approach for autonomous irrigation optimisation, wherein an AI agent develops optimal irrigation strategies through iterative environmental interaction. However, these advances are accompanied by substantial implementation challenges, including prohibitive upfront costs, inadequate rural connectivity, inconsistent sensor reliability, cybersecurity vulnerabilities, and limited scalability for smallholder farming systems. This review argues that AIoT can support climate-smart, sustainable agriculture by transforming raw data into actionable decisions that enhance resilience, food security, and environmental outcomes, provided that persistent technical, economic, and institutional barriers are systematically addressed.

• 49_Animashaun et al. (2026)

Copyright (c) 2026 Iyanda M. ANIMASHAUN, Abubakar S. MOHAMMED, Ibrahim A. KUTI, Peter A. OBASA, Rashidat ANIYIKAYE, Yahaya MOHAMMED, Yusuf M. OTACHE (Author)

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.