Al-Sammarraie et al. (2025) From data to decision: How wearable plant sensors help improving proactive irrigation strategies and water use efficiency

Identification

• Journal: CABI Reviews
• Year: 2025
• Date: 2025-12-16
• Authors: Mustafa A.J. Al-Sammarraie, Ali Irfan Ilbas, Zeki Gokalp
• DOI: 10.1079/cabireviews.2025.0084

Research Groups

• University of Baghdad, College of Agricultural Engineering Sciences, Baghdad, Iraq
• Faculty of Agriculture, Erciyes University, Kayseri, Türkiye

Short Summary

This review synthesizes the role of wearable plant sensors, Internet of Things (IoT), and Artificial Intelligence (AI) in transforming agricultural irrigation strategies. It concludes that these integrated technologies provide accurate, real-time plant physiological and environmental data, enabling proactive water management, significantly improving water use efficiency, and enhancing agricultural sustainability.

Objective

• To examine how wearable sensors and Artificial Intelligence (AI) technologies, which provide accurate measurements of factors such as plant water content, soil and air moisture, temperature, and light, can be utilized for improved water resource management in agriculture.

Study Configuration

• Spatial Scale: This review synthesizes findings from various studies covering applications from individual plant parts (leaves, stems, roots) to agricultural fields.
• Temporal Scale: This review covers studies demonstrating real-time and long-term monitoring capabilities of wearable sensors, often over periods of weeks to months.

Methodology and Data

• Models used: The review discusses the application of various Artificial Intelligence (AI) and Machine Learning (ML) algorithms for irrigation management, including:
  • Artificial Neural Networks (ANN) for generating moisture maps.
  • Machine learning algorithms for water quality improvement and soil moisture estimation.
  • AI modeling for predicting transpiration and optimizing water use.
  • IoT data analysis for predicting future irrigation needs.
• Data sources: This review synthesizes information from multiple scientific databases, including Web of Science, Scopus, IEEE Xplore, Google Scholar, and ScienceDirect. The reviewed studies primarily utilize data collected from:
  • Wearable plant sensors (measuring plant water content, leaf/air humidity, stem flow, plant/air temperature, light, vapor pressure deficit).
  • Soil moisture sensors (e.g., Time Domain Reflectometry (TDR), Frequency Domain Reflectometry (FDR), Capacitive sensors).
  • Environmental sensors (e.g., air temperature, air humidity, light, rainfall).
  • IoT platforms for data transmission and cloud-based management.

Main Results

• Wearable plant sensors offer accurate, real-time, and continuous monitoring of critical plant physiological parameters (e.g., water content, leaf/stem flow, temperature, humidity, VPD) and micro-environmental conditions (e.g., air temperature, humidity, light).
• These sensors overcome limitations of traditional methods by providing direct, continuous measurements with high sensitivity (e.g., temperature differences of -1.25 to -0.33 °C, humidity sensitivity up to 1.6% relative humidity, light response time of 4 ms), reduced environmental interference, and longer operational lifespans.
• Integration with Internet of Things (IoT) technologies enables wireless data transmission (Wi-Fi, Bluetooth, LoRa) and cloud-based data management, facilitating real-time access and analysis.
• Artificial Intelligence (AI) applications, such as machine learning and artificial neural networks, analyze sensor data to accurately predict plant water needs, optimize irrigation schedules, and automate irrigation systems.
• The combined use of wearable sensors, IoT, and AI leads to significant improvements in water use efficiency (e.g., reducing daily water and energy consumption by up to 38%), increased agricultural productivity (e.g., winter wheat yield increases of 10.3% and 4.4%), and enhanced agricultural sustainability.
• Despite the benefits, challenges remain, including sensor robustness in harsh field conditions, interpretability of AI models for farmers, high costs, lack of training, digital literacy gaps, and data security concerns.

Contributions

• Provides a comprehensive and timely review synthesizing the advancements and synergistic potential of wearable plant sensors, IoT, and AI in revolutionizing proactive irrigation strategies and water resource management in agriculture.
• Highlights the critical shift from traditional, calendar-based irrigation to data-driven, anticipatory approaches enabled by real-time plant and environmental monitoring.
• Systematically details the types of wearable sensors, their measured parameters, and their advantages over conventional methods in terms of accuracy, sensitivity, and operational life.
• Emphasizes the role of AI in analyzing complex sensor data for precise water need prediction, irrigation scheduling, and automation, demonstrating quantitative benefits in water saving and yield improvement.
• Identifies key technical, economic, and social challenges hindering widespread adoption and proposes pathways for future development, including user-friendly technologies, financial support, and improved digital infrastructure.

Funding

There are no funds received for the preparation, submission, or publication of the manuscript. The authors have no financial interest to disclose.

Citation

@article{AlSammarraie2025From,
  author = {Al-Sammarraie, Mustafa A.J. and Ilbas, Ali Irfan and Gokalp, Zeki},
  title = {From data to decision: How wearable plant sensors help improving proactive irrigation strategies and water use efficiency},
  journal = {CABI Reviews},
  year = {2025},
  doi = {10.1079/cabireviews.2025.0084},
  url = {https://doi.org/10.1079/cabireviews.2025.0084}
}