Abbassi et al. (2026) Machine Learning-Based Soil Moisture Prediction Using Meteorological Data for Enhanced Irrigation Management

Identification

• Journal: E3S Web of Conferences
• Year: 2026
• Date: 2026-01-01
• Authors: Taki-Eddine Abbassi, Abdelhakim Sahour, Moncef Benkherrat, Saddam Brai, Islam Boutiouta, Farouk Boumehrez
• DOI: 10.1051/e3sconf/202669903005

Research Groups

• Abbes Laghrour University, Khenchela, Algeria
• Laboratoire Systèmes et Applications des Technologies de l’Information et des Télécommunications (SATIT), Abbes Laghrour University, Khenchela, Algeria
• ECAM-EPMI, LR2E Laboratory, Cergy-Pontoise, France
• Electronics Department, Faculty of Technology, Badji Mokhtar-Annaba University, Annaba, Algeria
• Laboratoire des Télécommunications (LT), Institut des Télécommunications, 8 Mai 1945 – Guelma University, Guelma, Algeria

Short Summary

This research introduces a machine learning-based approach to predict soil moisture levels using meteorological data. The method serves as an alternative to physical sensors, aiming to provide continuous and optimal irrigation management for palm date agriculture.

Objective

• To develop and implement a machine learning-based prediction approach for estimating soil moisture levels using weather forecasting data, serving as a reliable alternative to physical sensors for enhanced irrigation management in palm date agriculture.

Study Configuration

• Spatial Scale: Regional application in Algeria, specifically for palm date cultivation.
• Temporal Scale: Not explicitly defined for the study's data or prediction horizon, but aims for continuous application in irrigation management.

Methodology and Data

• Models used: Machine learning models (specific algorithms not detailed in the abstract).
• Data sources: Meteorological data, weather forecasting data.

Main Results

• The study proposes a machine learning-based method for soil moisture prediction that can function as an effective alternative to traditional sensors.
• This approach is designed to facilitate constant and optimal irrigation techniques, particularly beneficial for palm date agriculture.

Contributions

• Introduction of a machine learning-based soil moisture prediction method that utilizes readily available meteorological data.
• Provision of a viable alternative to physical soil moisture sensors, addressing issues of sensor faults or absence.
• Enhancement of irrigation management strategies, particularly for critical crops like palm dates in regions such as Algeria.

Funding

• Not specified in the provided text.

Citation

@article{Abbassi2026Machine,
  author = {Abbassi, Taki-Eddine and Sahour, Abdelhakim and Benkherrat, Moncef and Brai, Saddam and Boutiouta, Islam and Boumehrez, Farouk},
  title = {Machine Learning-Based Soil Moisture Prediction Using Meteorological Data for Enhanced Irrigation Management},
  journal = {E3S Web of Conferences},
  year = {2026},
  doi = {10.1051/e3sconf/202669903005},
  url = {https://doi.org/10.1051/e3sconf/202669903005}
}