EUVIMEDEUVIMED entdecken
Open Access

A Comprehensive Risk Assessment Framework for Groundwater Quality: Integrating Natural Background Levels, Threshold Values, and Machine Learning‐Based Hydrochemical Facies Classification

Vahab Amiri iD, Peiyue Li iD, Mehdi Torabi-Kaveh

Water Environment Research · 2026-08 · 98 (8)

DOI: 10.1002/wer.70521 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water Environment Research, online erschienen am 06.08.2026. Verfasst von Vahab Amiri und 2 weiteren Autor:innen. Beteiligte Einrichtung: Associate Professor of Hydrogeology, Department of Geology, Yazd University, Yazd, Iran. Hauptthemen laut MEDLINE: Groundwater, Machine Learning, Environmental Monitoring, Water Quality. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 122 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Iran National Science Foundation (INSF).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Groundwater is a critical freshwater resource increasingly affected by anthropogenic activities. This study introduces an innovative and integrated framework for assessing the groundwater quality of the Qazvin aquifer, Iran, by combining iterative statistical methods and advanced machine learning (ML) algorithms. Three complementary statistical techniques, i.e., Iterative 2 σ , cumulative distribution function (CDF), and iterative Grubbs test (IGT), were employed to determine natural background levels (NBLs) and threshold values (TVs) for key physicochemical parameters, supported by validation through ProUCL 5.2. The IGT method proved most effective in eliminating anthropogenic outliers and capturing the true geogenic baseline. Temporal and spatial variations of NBLs indicated the combined effects of geological, climatic, and human factors on groundwater chemistry. Hydrochemical facies were subsequently classified using four ML models (SVM‐ and CatBoost‐based) integrated with a compositional log‐ratio (7hlr) transformation. The SVM‐based models achieved the highest classification accuracy (> 93%) and Kappa coefficients (> 0.85), outperforming classical graphical approaches. The key innovation of this study lies in the dual integration of iterative statistical tools and ML‐driven classification, offering a more accurate distinction between geogenic and anthropogenic processes. This framework provides a robust and transferable approach for evaluating groundwater quality and supports evidence‐based strategies for sustainable aquifer management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GroundwaterMachine LearningEnvironmental MonitoringWater QualityRisk AssessmentIranBoosting Machine Learning Algorithms

Stichwörter der Autor:innen

hydrochemical faciesiterative Grubbs testmachine learningnatural background levelthreshold value

Autor:innen und Institutionen

  • Associate Professor of Hydrogeology, Department of Geology, Yazd University, Yazd, Iran.
  • School of Water and Environment, Chang'an University, Xi'an, China.

ORCID-Profile: Vahab Amiri, Peiyue Li

Förderung

  • Iran National Science Foundation (INSF)

Zitieren

APA

Amiri, V., Li, P., & Torabi-Kaveh, M. (2026). A Comprehensive Risk Assessment Framework for Groundwater Quality: Integrating Natural Background Levels, Threshold Values, and Machine Learning‐Based Hydrochemical Facies Classification. Water Environment Research, 98(8). https://doi.org/10.1002/wer.70521

Vancouver

Amiri V, Li P, Torabi-Kaveh M. A Comprehensive Risk Assessment Framework for Groundwater Quality: Integrating Natural Background Levels, Threshold Values, and Machine Learning‐Based Hydrochemical Facies Classification. Water Environment Research. 2026;98(8). doi:10.1002/wer.70521

BibTeX
@article{Amiri2026,
  author = {Amiri, Vahab and Li, Peiyue and Torabi-Kaveh, Mehdi},
  title = {A Comprehensive Risk Assessment Framework for Groundwater Quality: Integrating Natural Background Levels, Threshold Values, and Machine Learning‐Based Hydrochemical Facies Classification},
  journal = {Water Environment Research},
  year = {2026},
  volume = {98},
  number = {8},
  doi = {10.1002/wer.70521}
}
Kostenlos starten →