Optimized intelligent learning for groundwater quality prediction in diverse aquifers of arid and semi-arid regions of India

Ensuring access to safe, affordable drinking water while implementing sustainable management practices is vital for achieving the United Nations Sustainable Development Goals-2030. Accurate groundwater (GW) quality assessment plays a crucial role in enhancing water management strategies. This study...

Full description

Saved in:
Bibliographic Details
Main Authors: Imran Khan, Sarwar Nizam, Apoorva Bamal, Abdul Majed Sajib, Mir Talas Mahammad Diganta, Mohd Azfar Shaida, S.M. Ashekuzzaman, Stephen Nash, Agnieszka I. Olbert, Md Galal Uddin
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:Cleaner Engineering and Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666790825001077
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849321304708087808
author Imran Khan
Sarwar Nizam
Apoorva Bamal
Abdul Majed Sajib
Mir Talas Mahammad Diganta
Mohd Azfar Shaida
S.M. Ashekuzzaman
Stephen Nash
Agnieszka I. Olbert
Md Galal Uddin
author_facet Imran Khan
Sarwar Nizam
Apoorva Bamal
Abdul Majed Sajib
Mir Talas Mahammad Diganta
Mohd Azfar Shaida
S.M. Ashekuzzaman
Stephen Nash
Agnieszka I. Olbert
Md Galal Uddin
author_sort Imran Khan
collection DOAJ
description Ensuring access to safe, affordable drinking water while implementing sustainable management practices is vital for achieving the United Nations Sustainable Development Goals-2030. Accurate groundwater (GW) quality assessment plays a crucial role in enhancing water management strategies. This study evaluates GW resources across the diverse aquifer systems of arid and semi-arid regions of northwest India using the recently developed Root Mean Squared-Water Quality Index (RMS-WQI) model, optimized with machine learning (ML) techniques. A total of 772 GW samples from 36 districts of state Rajasthan were analyzed for 16 water quality (WQ) indicators/parameters, including pH, Electrical Conductivity (EC), Total Dissolved Solids (TDS), major cations (Ca2+, Mg2+, Na+, K+), anions (Cl−, CO32−, HCO3−, SO42−, NO3−, F−, PO43−), Alkalinity (ALK), and Total Hardness (TH). The results indicate slightly alkaline GW (average pH 7.9), with elevated concentrations of Na+, Cl−, SO42− and NO3− exceeding Bureau of Indian Standards (BIS). This study employs the eXtreme Gradient Boosting (XGB) algorithm, demonstrating strong predictive capabilities within the RMS-WQI model across diverse aquifers of Rajasthan. This marks the first application of RMS-WQI at a state-wide scale in India. Model performance assessment indicated groundwater quality ranging from ‘fair’ to ‘marginal’, generally meeting BIS standards, with high sensitivity and low uncertainty. Statistical metrics (Root Mean Square Error-RMSE, Mean Squared Error-MSE, Mean Absolute Error-MAE, and Percentage of Absolute Bias Error-PABE) validated the model's efficiency, with minimal error and high sensitivity. Optimization using “Optuna” further enhanced model performance, confirmed by Tukey's Honest Significant Difference (HSD) test. Sensitivity analysis demonstrated robust goodness-of-fit, while uncertainty analysis indicated minimal discrepancies, with overall uncertainty below 2 %. Spatial analysis revealed varying WQ across districts, ranging from marginal to poor, while efficiency metrics demonstrated the model's effectiveness in providing accurate assessments. The configured WQI model could substantially contribute to informing aquatic managers and strategic planners for sustainable water resource management and policy development aimed at enhancing GW quality.
format Article
id doaj-art-36f82dcd2cae4ae2ba1dc9d5418054ed
institution Kabale University
issn 2666-7908
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series Cleaner Engineering and Technology
spelling doaj-art-36f82dcd2cae4ae2ba1dc9d5418054ed2025-08-20T03:49:46ZengElsevierCleaner Engineering and Technology2666-79082025-05-012610098410.1016/j.clet.2025.100984Optimized intelligent learning for groundwater quality prediction in diverse aquifers of arid and semi-arid regions of IndiaImran Khan0Sarwar Nizam1Apoorva Bamal2Abdul Majed Sajib3Mir Talas Mahammad Diganta4Mohd Azfar Shaida5S.M. Ashekuzzaman6Stephen Nash7Agnieszka I. Olbert8Md Galal Uddin9Department of Geology, Aligarh Muslim University, Aligarh, 202002, India; Corresponding author. Department of Geology, Aligarh Muslim University, Aligarh, 202002, India.Geomorphology, GFZ German Research Centre for Geosciences, Potsdam, GermanySchool of Engineering, University of Galway, Ireland; Ryan Institute, University of Galway, Ireland; MaREI Research Centre, University of Galway, Ireland; Eco-HydroInformatics Research Group (EHIRG), Civil Engineering, University of Galway, IrelandSchool of Engineering, University of Galway, Ireland; Ryan Institute, University of Galway, Ireland; MaREI Research Centre, University of Galway, Ireland; Eco-HydroInformatics Research Group (EHIRG), Civil Engineering, University of Galway, IrelandSchool of Engineering, University of Galway, Ireland; Ryan Institute, University of Galway, Ireland; MaREI Research Centre, University of Galway, Ireland; Eco-HydroInformatics Research Group (EHIRG), Civil Engineering, University of Galway, IrelandDepartment of Industrial Chemistry, Aligarh Muslim University, Aligarh, 202002, IndiaDepartment of Civil, Structural and Environmental Engineering, Sustainable Infrastructure Research & Innovation Group, Munster Technological University, Bishopstown, Cork, IrelandSchool of Engineering, University of Galway, Ireland; Ryan Institute, University of Galway, Ireland; MaREI Research Centre, University of Galway, IrelandSchool of Engineering, University of Galway, Ireland; Ryan Institute, University of Galway, Ireland; MaREI Research Centre, University of Galway, Ireland; Eco-HydroInformatics Research Group (EHIRG), Civil Engineering, University of Galway, IrelandSchool of Engineering, University of Galway, Ireland; Ryan Institute, University of Galway, Ireland; MaREI Research Centre, University of Galway, Ireland; Eco-HydroInformatics Research Group (EHIRG), Civil Engineering, University of Galway, Ireland; Department of Civil, Structural and Environmental Engineering, Sustainable Infrastructure Research & Innovation Group, Munster Technological University, Bishopstown, Cork, Ireland; Corresponding author. Civil Engineering, College of Science and Engineering, University of Galway, Ireland.Ensuring access to safe, affordable drinking water while implementing sustainable management practices is vital for achieving the United Nations Sustainable Development Goals-2030. Accurate groundwater (GW) quality assessment plays a crucial role in enhancing water management strategies. This study evaluates GW resources across the diverse aquifer systems of arid and semi-arid regions of northwest India using the recently developed Root Mean Squared-Water Quality Index (RMS-WQI) model, optimized with machine learning (ML) techniques. A total of 772 GW samples from 36 districts of state Rajasthan were analyzed for 16 water quality (WQ) indicators/parameters, including pH, Electrical Conductivity (EC), Total Dissolved Solids (TDS), major cations (Ca2+, Mg2+, Na+, K+), anions (Cl−, CO32−, HCO3−, SO42−, NO3−, F−, PO43−), Alkalinity (ALK), and Total Hardness (TH). The results indicate slightly alkaline GW (average pH 7.9), with elevated concentrations of Na+, Cl−, SO42− and NO3− exceeding Bureau of Indian Standards (BIS). This study employs the eXtreme Gradient Boosting (XGB) algorithm, demonstrating strong predictive capabilities within the RMS-WQI model across diverse aquifers of Rajasthan. This marks the first application of RMS-WQI at a state-wide scale in India. Model performance assessment indicated groundwater quality ranging from ‘fair’ to ‘marginal’, generally meeting BIS standards, with high sensitivity and low uncertainty. Statistical metrics (Root Mean Square Error-RMSE, Mean Squared Error-MSE, Mean Absolute Error-MAE, and Percentage of Absolute Bias Error-PABE) validated the model's efficiency, with minimal error and high sensitivity. Optimization using “Optuna” further enhanced model performance, confirmed by Tukey's Honest Significant Difference (HSD) test. Sensitivity analysis demonstrated robust goodness-of-fit, while uncertainty analysis indicated minimal discrepancies, with overall uncertainty below 2 %. Spatial analysis revealed varying WQ across districts, ranging from marginal to poor, while efficiency metrics demonstrated the model's effectiveness in providing accurate assessments. The configured WQI model could substantially contribute to informing aquatic managers and strategic planners for sustainable water resource management and policy development aimed at enhancing GW quality.http://www.sciencedirect.com/science/article/pii/S2666790825001077HydrochemistryMachine learningeXtreme gradient boostingOptunaWater quality index (WQI)Rajasthan
spellingShingle Imran Khan
Sarwar Nizam
Apoorva Bamal
Abdul Majed Sajib
Mir Talas Mahammad Diganta
Mohd Azfar Shaida
S.M. Ashekuzzaman
Stephen Nash
Agnieszka I. Olbert
Md Galal Uddin
Optimized intelligent learning for groundwater quality prediction in diverse aquifers of arid and semi-arid regions of India
Cleaner Engineering and Technology
Hydrochemistry
Machine learning
eXtreme gradient boosting
Optuna
Water quality index (WQI)
Rajasthan
title Optimized intelligent learning for groundwater quality prediction in diverse aquifers of arid and semi-arid regions of India
title_full Optimized intelligent learning for groundwater quality prediction in diverse aquifers of arid and semi-arid regions of India
title_fullStr Optimized intelligent learning for groundwater quality prediction in diverse aquifers of arid and semi-arid regions of India
title_full_unstemmed Optimized intelligent learning for groundwater quality prediction in diverse aquifers of arid and semi-arid regions of India
title_short Optimized intelligent learning for groundwater quality prediction in diverse aquifers of arid and semi-arid regions of India
title_sort optimized intelligent learning for groundwater quality prediction in diverse aquifers of arid and semi arid regions of india
topic Hydrochemistry
Machine learning
eXtreme gradient boosting
Optuna
Water quality index (WQI)
Rajasthan
url http://www.sciencedirect.com/science/article/pii/S2666790825001077
work_keys_str_mv AT imrankhan optimizedintelligentlearningforgroundwaterqualitypredictionindiverseaquifersofaridandsemiaridregionsofindia
AT sarwarnizam optimizedintelligentlearningforgroundwaterqualitypredictionindiverseaquifersofaridandsemiaridregionsofindia
AT apoorvabamal optimizedintelligentlearningforgroundwaterqualitypredictionindiverseaquifersofaridandsemiaridregionsofindia
AT abdulmajedsajib optimizedintelligentlearningforgroundwaterqualitypredictionindiverseaquifersofaridandsemiaridregionsofindia
AT mirtalasmahammaddiganta optimizedintelligentlearningforgroundwaterqualitypredictionindiverseaquifersofaridandsemiaridregionsofindia
AT mohdazfarshaida optimizedintelligentlearningforgroundwaterqualitypredictionindiverseaquifersofaridandsemiaridregionsofindia
AT smashekuzzaman optimizedintelligentlearningforgroundwaterqualitypredictionindiverseaquifersofaridandsemiaridregionsofindia
AT stephennash optimizedintelligentlearningforgroundwaterqualitypredictionindiverseaquifersofaridandsemiaridregionsofindia
AT agnieszkaiolbert optimizedintelligentlearningforgroundwaterqualitypredictionindiverseaquifersofaridandsemiaridregionsofindia
AT mdgalaluddin optimizedintelligentlearningforgroundwaterqualitypredictionindiverseaquifersofaridandsemiaridregionsofindia