Ahmed et al. (2025) Evapotranspiration Estimation in the Arab Region: Methodological Advances and Multi-Sensor Integration Framework

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

Identification

• Journal: Water
• Year: 2025
• Date: 2025-09-12
• Authors: Shamseddin Musa Ahmed, Khalid G. Biro Turk, Adam E. Ahmed, Azharia Abdelbagi Elbushra, Anwar Ali Aldhafeeri, Hossam M. Darrag
• DOI: 10.3390/w17182702

Research Groups

Not explicitly stated in the provided text.

Short Summary

This study reviews evapotranspiration (ET) estimation techniques in the Arab world, highlighting the dominance of traditional methods while demonstrating the potential of machine learning (ML)-based fusion for improved ET estimation in data-scarce regions.

Objective

• To map dominant ET estimation techniques and their geographic distribution.
• To demonstrate fusion-based ET estimation under data-scarce conditions.
• To examine the alignment of ET estimation techniques with climate change and food security priorities.

Study Configuration

• Spatial Scale: Arab world (for the review); Saudi Arabia (for the demonstration).
• Temporal Scale: Not explicitly stated for the demonstration, but error metrics are annual (mm/year). The review covers articles indexed in Web of Science, implying a historical range of publications.

Methodology and Data

• Models used:
  • Review: Penman-Monteith (traditional), Machine Learning (ML), Remote Sensing (RS), Artificial Intelligence (AI), hybrid fusion frameworks.
  • Demonstration: Random Forest (for ML-based ET fusion).
• Data sources:
  • Review: 1279 ET-related articles indexed in the Web of Science.
  • Demonstration: Landsat satellite data, FAO Water Productivity (WaPOR) data.

Main Results

• Traditional methods, primarily the Penman-Monteith model, dominate nearly 70% of the reviewed literature on ET estimation.
• Machine learning (ML), remote sensing (RS), and artificial intelligence (AI) collectively account for approximately 30% of studies, with hybrid fusion frameworks appearing in only 2%.
• ML applications are concentrated in Morocco, Egypt, and Iraq, while 50% of Arab countries lack any ML or AI-based research on ET.
• An ML-based ET fusion approach using a Random Forest model outperformed traditional averaging in Saudi Arabia.
• The Random Forest model achieved a mean absolute error (MAE) of 215.08 mm/year, a root mean square error (RMSE) of 531.34 mm/year, and a Pearson correlation coefficient of 0.86.

Contributions

• Provides a comprehensive bibliometric analysis of ET estimation techniques across the Arab world, identifying methodological trends and regional research gaps.
• Demonstrates the practical utility and improved accuracy of ML-based ET fusion in data-scarce environments using satellite and WaPOR data.
• Advocates for increased regional collaboration and support to integrate advanced ET monitoring and ML-based modeling into climate resilience strategies.

Funding

Not explicitly stated in the provided text.

Citation

@article{Ahmed2025Evapotranspiration,
  author = {Ahmed, Shamseddin Musa and Turk, Khalid G. Biro and Ahmed, Adam E. and Elbushra, Azharia Abdelbagi and Aldhafeeri, Anwar Ali and Darrag, Hossam M.},
  title = {Evapotranspiration Estimation in the Arab Region: Methodological Advances and Multi-Sensor Integration Framework},
  journal = {Water},
  year = {2025},
  doi = {10.3390/w17182702},
  url = {https://doi.org/10.3390/w17182702}
}