A Pilot Study on Predicting Groundwater Mineralization Using ANN with Limited Well Data: a Case Study from Algerian Hyper-Arid Zone

Abstract Groundwater quality assessment in arid environments remains a critical challenge due to data scarcity and the complex interactions among chemical constituents. This study presents a pilot investigation aimed at identifying the key chemical elements influencing groundwater quality in southeastern Algeria through the application of Artificial Neural Networks. Hydrochemical data from nine wells within the Namurian aquifer were analyzed to evaluate the relationships between major ions and electrical conductivity. A Multilayer Perceptron model was developed to predict EC and to determine the most influential chemical parameters contributing to groundwater mineralization. The model exhibited strong predictive performance R2 = 0.96, demonstrating its robustness even with a limited dataset. The results indicated that magnesium, sodium, sulfate, and chloride are the principal contributors to groundwater salinity. The salinity hazard, expressed through the Sodium Adsorption Ratio, revealed that most groundwater samples are unsuitable for irrigation. The close agreement between predictions and classic hydrochemical interpretations confirms the reliability and efficiency of the approach for hydrogeochemical analysis. Overall, this integrative methodology highlights the potential of artificial intelligence tools to enhance groundwater quality assessment and management in data-limited arid regions.

Authors

Institutions

Publication Details

Journal
Water Resources
Published
2026-11-18
DOI
https://doi.org/10.1134/s0097807825604431
Primary Topic
Water Quality and Pollution Assessment
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Pilot Study on Predicting Groundwater Mineralization Using ANN with Limited Well Data: a Case Study from Algerian Hyper-Arid Zone

Omar Elahcene, Mohamed Yacine Bendjedou, Badr Eddine Rahmani, Toufik Djebassi et al.
4 links
Water Resources
Water Quality and Pollution Assessment
article

A Pilot Study on Predicting Groundwater Mineralization Using ANN with Limited Well Data: a Case Study from Algerian Hyper-Arid Zone

Omar Elahcene, Mohamed Yacine Bendjedou, Badr Eddine Rahmani, Toufik Djebassi, Houria Kada, Djamel Chehili
article en

Abstract

Abstract Groundwater quality assessment in arid environments remains a critical challenge due to data scarcity and the complex interactions among chemical constituents. This study presents a pilot investigation aimed at identifying the key chemical elements influencing groundwater quality in southeastern Algeria through the application of Artificial Neural Networks. Hydrochemical data from nine wells within the Namurian aquifer were analyzed to evaluate the relationships between major ions and electrical conductivity. A Multilayer Perceptron model was developed to predict EC and to determine the most influential chemical parameters contributing to groundwater mineralization. The model exhibited strong predictive performance R2 = 0.96, demonstrating its robustness even with a limited dataset. The results indicated that magnesium, sodium, sulfate, and chloride are the principal contributors to groundwater salinity. The salinity hazard, expressed through the Sodium Adsorption Ratio, revealed that most groundwater samples are unsuitable for irrigation. The close agreement between predictions and classic hydrochemical interpretations confirms the reliability and efficiency of the approach for hydrogeochemical analysis. Overall, this integrative methodology highlights the potential of artificial intelligence tools to enhance groundwater quality assessment and management in data-limited arid regions.

Water ResourcesVol. 53(6)
Sonatrach (Algeria) (DZ), Universidad de Granada (ES), University Ferhat Abbas of Setif (DZ), Ziane Achour University of Djelfa (DZ), Université Larbi Tébessi (DZ)
Clean water and sanitation
Water Quality and Pollution Assessment
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon