EUVIMEDEUVIMED entdecken
Open Access

PSO ‐Optimized Ensemble Learning with SHAP for Seasonal Groundwater Quality Prediction

Tahar Selmane, Yacine Hasnaoui iD, Nadir Aloui, Senna Lachehab, Lakhdar Seraiche, Mostafa Dougha

Groundwater · 2026-09 · 64 (5) · 576-593

DOI: 10.1111/gwat.70090 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Groundwater, online erschienen am 07.07.2026. Verfasst von Tahar Selmane und 5 weiteren Autor:innen. Beteiligte Einrichtung: VEHDD Laboratory, Faculty of Technology, University of M'sila 28000, Algeria; Department of Hydraulics and Civil Engineering, Université de Ghardaïa,…. Hauptthemen laut MEDLINE: Groundwater, Water Quality, Environmental Monitoring, Machine Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Groundwater is the principal source of freshwater in hyper‐arid regions such as the Algerian Sahara, making reliable groundwater quality assessment essential for sustainable water resource management. This study developed an interpretable hybrid modeling framework for predicting the groundwater WQI in the Ghardaia region by integrating Particle Swarm Optimization (PSO) with ensemble machine learning algorithms. A total of 540 groundwater samples were collected from 67 artesian boreholes during the dry/wet seasons over the period 2021 to 2025. To ensure robust model evaluation and minimize data leakage, a spatially independent validation strategy. Based on borehole locations were adopted. Three ensemble algorithms, namely Random Forest (RF), Adaptive Boosting (AdaBoost), and Extreme Gradient Boosting (XGBoost), were optimized using PSO and trained separately for the dry/wet‐season datasets. Among the evaluated models, PSO‐AdaBoost achieved the best predictive performance during the dry season, with R 2 = 0.976, whereas PSO‐XGBoost performed best during the wet season, with R 2 = 0.985. Hydrochemical variables' contribution to WQI predictions was quantified by investigating model interpretability using SHapley Additive exPlanations (SHAP). SHAP analysis revealed that potassium (K + ) was the most influential predictor during the dry season, reflecting strong evapoconcentration and water–rock interaction processes. pH and magnesium (Mg 2+ ) became relatively more influential during wet‐period sampling campaigns, suggesting temporal hydrochemical variability potentially associated with physicochemical equilibrium changes and indirect hydrodynamic influences. The proposed PSO‐ensemble‐SHAP framework provides an accurate and interpretable approach for groundwater quality prediction and supports efficient monitoring and management of groundwater resources in arid aquifer systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GroundwaterWater QualityEnvironmental MonitoringMachine LearningSeasonsParticle Swarm OptimizationBoosting Machine Learning AlgorithmsPrediction AlgorithmsRandom ForestAlgeriaModels, TheoreticalPredictive Learning Models

Autor:innen und Institutionen

  • VEHDD Laboratory, Faculty of Technology, University of M'sila 28000, Algeria; Department of Hydraulics and Civil Engineering, Université de Ghardaïa, Ghardaïa, 47000, Algeria.
  • Department of Hydraulics, Laboratoire de Recherche des Sciences de l'eau, National Polytechnic School, 10 Rue des Frères OUDEK, El Harrach, Algiers, 16200, Algeria.
  • Department of Hydraulics and Civil Engineering, Université de Ghardaïa, Ghardaïa, 47000, Algeria.
  • VEHDD Laboratory, Faculty of Technology, University of M'sila, M'sila, 28000, Algeria.

ORCID-Profile: Yacine Hasnaoui

Zitieren

APA

Selmane, T., Hasnaoui, Y., Aloui, N., Lachehab, S., Seraiche, L., & Dougha, M. (2026). PSO ‐Optimized Ensemble Learning with SHAP for Seasonal Groundwater Quality Prediction. Groundwater, 64(5), 576-593. https://doi.org/10.1111/gwat.70090

Vancouver

Selmane T, Hasnaoui Y, Aloui N, Lachehab S, Seraiche L, Dougha M. PSO ‐Optimized Ensemble Learning with SHAP for Seasonal Groundwater Quality Prediction. Groundwater. 2026;64(5):576-593. doi:10.1111/gwat.70090

BibTeX
@article{Selmane2026,
  author = {Selmane, Tahar and Hasnaoui, Yacine and Aloui, Nadir and Lachehab, Senna and Seraiche, Lakhdar and Dougha, Mostafa},
  title = {PSO ‐Optimized Ensemble Learning with SHAP for Seasonal Groundwater Quality Prediction},
  journal = {Groundwater},
  year = {2026},
  volume = {64},
  number = {5},
  pages = {576--593},
  doi = {10.1111/gwat.70090}
}
Kostenlos starten →