Abd-Elmaboud et al. (2026) A novel hybrid Elk-Eel and grouper optimizer coupled with machine learning for integrated irrigation water quality index prediction and Pareto-optimal monitoring cost reduction

Identification

• Journal: Journal of Hydrology Regional Studies
• Year: 2026
• Date: 2026-09-28
• Authors: Mahmoud E. Abd-Elmaboud, Youssef M. Youssef, Mohamed Abdellatief, Mohamed Elkollaly, Mohsen M. Sherif, Ahmed El-Shafie, Ahmed M. Saqr
• DOI: 10.1016/j.ejrh.2026.104014

Research Groups

• National Water and Energy Center, United Arab Emirates University
• Irrigation & Hydraulics Department, Faculty of Engineering, Mansoura University
• Geological and Geophysical Engineering Department, Faculty of Petroleum and Mining Engineering, Suez University
• Department of Civil Engineering, Higher Future Institute of Engineering and Technology in Mansoura

Short Summary

This study develops a novel Hybrid Elk-Eel and Grouper Optimizer (HEEGO) to improve prediction accuracy for the Integrated Irrigation Water Quality Index (IIWQI) in the Eastern Nile Delta aquifer system. The HEEGO framework reduces laboratory cost by 79.5% while preserving predictive accuracy.

Objective

• Investigate the feasibility of machine learning-based IIWQI prediction using a hybrid metaheuristic optimization framework.
• Develop an accurate and interpretable decision-support tool for irrigation groundwater management in resource-constrained water authorities.

Study Configuration

• Spatial Scale: Regional scale, covering approximately 12,284 km² of cultivated land in the Eastern Nile Delta aquifer system.
• Temporal Scale: Long-term monitoring (10 years) to assess the impact of seawater intrusion and upward leakage on groundwater quality.

Methodology and Data

• Models used: Ten standalone machine learning algorithms, including tree-based ensemble methods and gradient-boosting variants.
• Data sources: Hydrochemical data from 501 groundwater wells distributed across three aquifer systems in the Eastern Nile Delta.

Main Results

• The HEEGO framework improves prediction accuracy by a mean 12.9% in RMSE compared to standalone machine learning algorithms.
• The Cost-Accuracy Pareto Optimization Framework identifies a four-parameter monitoring subset (EC, Na⁺, Ca²⁺, and Mg²⁺) that preserves predictive accuracy while maximizing laboratory cost savings.

Contributions

• Original value of the article lies in the development of a hybrid metaheuristic optimization framework for IIWQI prediction.
• The study provides a practical route toward more frequent and sustainable groundwater surveillance in resource-constrained water authorities.

Funding

• This research was funded by the National Water and Energy Center, United Arab Emirates University (project code: NWEC-2022-001).
• Additional support was provided by the Irrigation & Hydraulics Department, Faculty of Engineering, Mansoura University (project code: IHDF-2022-002).

Citation

@article{AbdElmaboud2026novel,
  author = {Abd-Elmaboud, Mahmoud E. and Youssef, Youssef M. and Abdellatief, Mohamed and Elkollaly, Mohamed and Sherif, Mohsen M. and El-Shafie, Ahmed and Saqr, Ahmed M.},
  title = {A novel hybrid Elk-Eel and grouper optimizer coupled with machine learning for integrated irrigation water quality index prediction and Pareto-optimal monitoring cost reduction},
  journal = {Journal of Hydrology Regional Studies},
  year = {2026},
  doi = {10.1016/j.ejrh.2026.104014},
  url = {https://doi.org/10.1016/j.ejrh.2026.104014}
}