Morchid et al. (2025) Innovative applications of internet of things and machine learning in sustainable agricultural irrigation management: Benefits and challenges

Identification

• Journal: Smart Agricultural Technology
• Year: 2025
• Date: 2025-11-21
• Authors: Abdennabi Morchid, Zafar Said, Hamid Tairi
• DOI: 10.1016/j.atech.2025.101661

Research Groups

• LIMAS Laboratory, Faculty of Sciences, Dhar El Mahraz, Sidi Mohamed Ben Abdellah (SMBA) University, Fes, Morocco
• Mechanical and Aerospace Engineering Department, College of Engineering, United Arab Emirates University, Al Ain, United Arab Emirates
• L3IA Laboratory, Faculty of Sciences Dhar El Mahraz, Sidi Mohamed Ben Abdellah (SMBA) University, Fes, Morocco

Short Summary

This systematic review analyzes the integration of Internet of Things (IoT) and Machine Learning (ML) in smart agricultural irrigation, identifying their benefits in water conservation, irrigation efficiency, and productivity, alongside associated challenges and future research directions.

Objective

• To systematically review and analyze the integration of Internet of Things (IoT) and Machine Learning (ML) technologies in smart irrigation systems for optimizing crop water use, identifying their benefits, challenges, and future research directions.

Study Configuration

• Spatial Scale: Global (systematic review of studies worldwide)
• Temporal Scale: Publications from 2017 to 2025

Methodology and Data

• Models used: The reviewed studies utilize various Machine Learning algorithms (e.g., Linear Regression, Random Forests, Artificial Neural Networks (ANN), Deep Learning (CNN, LSTM), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naïve Bayes, Adaptive Neuro-Fuzzy Inference System (ANFIS), reinforcement learning, fuzzy logic) and IoT architectures.
• Data sources: The reviewed studies primarily use data from IoT sensors (e.g., soil moisture, temperature, humidity, salinity, pH, solar radiation, wind speed, water level, rainfall), satellite imagery (e.g., Sentinel-2, Landsat-8), and weather forecasts. The review itself used scientific databases (IEEE Xplore, ScienceDirect, SpringerLink, MDPI, Wiley).

Main Results

• The systematic review analyzed 108 studies selected from an initial 1340 publications using the PRISMA methodology.
• IoT systems provide real-time information on environmental and soil conditions, while ML techniques enable data-driven decision-making for optimized irrigation.
• Key benefits include enhanced water conservation, improved irrigation efficiency, and increased agricultural productivity.
• Quantitative findings from reviewed studies demonstrate significant improvements:
  • Water consumption reductions of up to 42% in olive groves and 71.8% in general agricultural settings.
  • Irrigation efficiency increases of 12.05% and energy savings of up to 57%.
  • Predictive systems achieved high accuracy, with some reaching 99% in irrigation status prediction and 97.5% in classification efficiency.
  • Runoff minimization in turfgrass irrigation by 74%.
• Identified challenges include high initial implementation costs, issues with equipment durability and maintenance, cybersecurity risks for agricultural data, and limited access to training and adequate network infrastructure in rural areas.
• A three-layer conceptual framework for smart irrigation (IoT Infrastructure, Data Intelligence, System Optimization/Sustainability/Efficiency) and a future research roadmap (short, medium, and long-term) are proposed.

Contributions

• Provides a comprehensive systematic review of the integration of IoT and ML technologies in smart irrigation systems using the PRISMA methodology.
• Offers an in-depth analysis of the current applications, benefits (e.g., water efficiency, sustainability, productivity), and challenges (e.g., technical, financial, infrastructural) of these technologies in agriculture.
• Presents a holistic conceptual framework for smart irrigation systems, outlining the dynamic interplay between IoT infrastructure, data intelligence, and system optimization.
• Proposes a future research roadmap, identifying emerging scientific and technological trends, including quantum sensors and quantum computing, to advance autonomous, efficient, and environmentally sustainable irrigation systems.
• Addresses existing problems in smart irrigation and introduces new trends for future innovation in the field.

Funding

Not explicitly stated in the paper.

Citation

@article{Morchid2025Innovative,
  author = {Morchid, Abdennabi and Said, Zafar and Tairi, Hamid},
  title = {Innovative applications of internet of things and machine learning in sustainable agricultural irrigation management: Benefits and challenges},
  journal = {Smart Agricultural Technology},
  year = {2025},
  doi = {10.1016/j.atech.2025.101661},
  url = {https://doi.org/10.1016/j.atech.2025.101661}
}