Internet of Things-enabled smart irrigation systems for precision water management: A systematic review
- 1University of Bari Aldo Moro, Department of Soil, Plant and Food Sciences, Via Amendola 165/A, Bari 70126, Italy
Abstract
Background Global agriculture faces unprecedented water scarcity challenges, with irrigation accounting for approximately 70% of freshwater withdrawals worldwide. Smart irrigation technologies integrating Internet of Things (IoT), wireless sensor networks (WSN), and decision support systems (DSS) offer promising solutions for optimizing water use efficiency while maintaining crop productivity. Objective This systematic review examines the current state of IoT-based smart irrigation systems, focusing on technologies that integrate real-time sensing, data-driven decision support, and precision irrigation scheduling to reduce water consumption without compromising crop yields. Methods Following PRISMA guidelines, we searched Scopus database using predefined inclusion criteria. From an initial pool of 323 articles, rigorous filtering based on technological focus, application domain, and methodological relevance yielded 50 articles (2018–2025) for comprehensive analysis. Results The reviewed studies demonstrate an exponential growth in smart irrigation research, with 71% published between 2021 and 2024. Across the reviewed studies, IoT-based systems achieved water savings of approximately 9–50% relative to conventional irrigation. In most cases these savings were accompanied by maintained or improved yields (commonly 5–25%); however, the outcomes were not uniform, and a subset of studies reported water savings achieved at the expense of yield or water productivity, particularly under more severe deficit regimes. We therefore distinguish three outcome categories—water saving with yield increase, water saving with yield maintenance, and water saving with yield reduction—rather than presenting a single generalized benefit. India, Italy, and the USA emerged as leading contributors, with experimental and prototype studies dominating the research landscape. Key technologies included soil moisture sensors, weather stations, cloud computing platforms, and machine learning algorithms integrated with evapotranspiration (ET) calculations and vegetation indices (NDVI, LAI). Conclusions IoT-enabled smart irrigation represents a paradigm shift from reactive to predictive water management. However, significant gaps remain in long-term field validation, scalability to smallholder farms, standardization of sensor calibration, and integration of multi-source data streams. Future research should prioritize farmer-centric design, economic feasibility, and interoperability frameworks to accelerate widespread adoption.
Related
- A MATLAB-based AI-IoT simulation framework for LSTM-driven smart solar irrigation and renewable energy management
- Predicting forage yield and water use efficiency using machine learning across diverse forage species under varying irrigation and fertilizer management in the Ethiopian highlands
- Epidemiological trends of Fusarium wilt in chickpea and its management through ICT-enabled surveillance in Maharashtra
- Integrating biomarkers and artificial intelligence for precision diagnostics in cattle health and herd management: a review
- Advances in Artificial Intelligence-Enabled Crop Pest and Disease Detection: A Systematic Review
BibTeX
@article{moustafa2026internet,
title = {{Internet of Things-enabled smart irrigation systems for precision water management: A systematic review}},
author = {AHMED MOUSTAFA and Ossama M. M. Abdelwahab and Giovanni Francesco Ricci and Francesco Gentile},
journal = {Agricultural Water Management},
year = {2026},
month = jul,
doi = {10.1016/j.agwat.2026.110615},
url = {https://doi.org/10.1016/j.agwat.2026.110615},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Internet of Things-enabled smart irrigation systems for precision water management: A systematic review
AU - AHMED MOUSTAFA
AU - Ossama M. M. Abdelwahab
AU - Giovanni Francesco Ricci
AU - Francesco Gentile
PY - 2026
DA - 2026/07/06
JO - Agricultural Water Management
DO - 10.1016/j.agwat.2026.110615
UR - https://doi.org/10.1016/j.agwat.2026.110615
AB - Background Global agriculture faces unprecedented water scarcity challenges, with irrigation accounting for approximately 70% of freshwater withdrawals worldwide. Smart irrigation technologies integrating Internet of Things (IoT), wireless sensor networks (WSN), and decision support systems (DSS) offer promising solutions for optimizing water use efficiency while maintaining crop productivity. Objective This systematic review examines the current state of IoT-based smart irrigation systems, focusing on technologies that integrate real-time sensing, data-driven decision support, and precision irrigation scheduling to reduce water consumption without compromising crop yields. Methods Following PRISMA guidelines, we searched Scopus database using predefined inclusion criteria. From an initial pool of 323 articles, rigorous filtering based on technological focus, application domain, and methodological relevance yielded 50 articles (2018–2025) for comprehensive analysis. Results The reviewed studies demonstrate an exponential growth in smart irrigation research, with 71% published between 2021 and 2024. Across the reviewed studies, IoT-based systems achieved water savings of approximately 9–50% relative to conventional irrigation. In most cases these savings were accompanied by maintained or improved yields (commonly 5–25%); however, the outcomes were not uniform, and a subset of studies reported water savings achieved at the expense of yield or water productivity, particularly under more severe deficit regimes. We therefore distinguish three outcome categories—water saving with yield increase, water saving with yield maintenance, and water saving with yield reduction—rather than presenting a single generalized benefit. India, Italy, and the USA emerged as leading contributors, with experimental and prototype studies dominating the research landscape. Key technologies included soil moisture sensors, weather stations, cloud computing platforms, and machine learning algorithms integrated with evapotranspiration (ET) calculations and vegetation indices (NDVI, LAI). Conclusions IoT-enabled smart irrigation represents a paradigm shift from reactive to predictive water management. However, significant gaps remain in long-term field validation, scalability to smallholder farms, standardization of sensor calibration, and integration of multi-source data streams. Future research should prioritize farmer-centric design, economic feasibility, and interoperability frameworks to accelerate widespread adoption.
SN - 0378-3774
SN - 1873-2283
ER -