Cambra et al. (2025) Edge-Computing Smart Irrigation Controller Using LoRaWAN and LSTM for Predictive Controlled Deficit Irrigation

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Sensors
• Year: 2025
• Date: 2025-11-20
• Authors: Carlos Cambra, Rogério Dionísio, Fernando Ribeiro, José Metrôlho
• DOI: 10.3390/s25227079

Research Groups

Not specified in the provided text.

Short Summary

This study presents an IoT-enabled edge computing model utilizing hybrid machine learning to predict soil moisture and manage Controlled Deficit Irrigation (CDI) strategies in high-density almond fields, achieving a 35% reduction in crop evapotranspiration (ETc) and enabling real-time water management without cloud dependency.

Objective

• To develop and present an IoT-enabled edge computing model for smart irrigation systems that uses hybrid machine learning to predict soil moisture and manage Controlled Deficit Irrigation (CDI) strategies in high-density almond tree fields.

Study Configuration

• Spatial Scale: High-density almond tree fields.
• Temporal Scale: Real-time (for irrigation management and anomaly identification).

Methodology and Data

• Models used: Hybrid machine learning algorithms, soft ML model.
• Data sources: IoT sensors, meteorological data, soil humidity data, crop data.

Main Results

• An IoT-enabled edge computing model for smart irrigation systems was developed, integrating hybrid machine learning for precision agriculture.
• The model successfully managed Controlled Deficit Irrigation (CDI) strategies in high-density almond tree fields, achieving a 35% reduction in crop evapotranspiration (ETc).
• A soft ML model was developed to enhance irrigation practices and identify crop anomalies in real-time, operating without cloud computing.
• The methodology demonstrated potential for precise and efficient water management, even in remote locations with limited internet access.

Contributions

• Presents an innovative IoT-enabled edge computing model for precision agriculture, integrating hybrid machine learning for real-time soil moisture prediction and CDI management.
• Enables significant water savings (35% ETc reduction) in almond cultivation through automated, data-driven irrigation.
• Offers a solution for smart irrigation in remote areas by eliminating the dependency on cloud computing for real-time operations.
• Represents an initial step towards implementing ML algorithms for irrigation CDI strategies, providing a foundation for future advancements.

Funding

Not specified in the provided text.

Citation

@article{Cambra2025EdgeComputing,
  author = {Cambra, Carlos and Dionísio, Rogério and Ribeiro, Fernando and Metrôlho, José},
  title = {Edge-Computing Smart Irrigation Controller Using LoRaWAN and LSTM for Predictive Controlled Deficit Irrigation},
  journal = {Sensors},
  year = {2025},
  doi = {10.3390/s25227079},
  url = {https://doi.org/10.3390/s25227079}
}