Evaluating groundwater potential with the synergistic use of geospatial methods and advanced machine learning approaches

Abstract The rapid increase in population, urbanization, and industrial activity in developing countries is intensifying pressure on groundwater resources, leading to severe water shortages. This study aims to evaluate and compare the predictive capabilities of six ensemble machine learning (ML) mod...

Full description

Saved in:
Bibliographic Details
Main Authors: Vicky Anand, Vishnu D. Rajput, Tatiana Minkina, Saglara Mandzhieva, Aastha Sharma, Deepak Kumar, Sunil Kumar
Format: Article
Language:English
Published: Springer 2025-06-01
Series:Discover Cities
Subjects:
Online Access:https://doi.org/10.1007/s44327-025-00095-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850223943130021888
author Vicky Anand
Vishnu D. Rajput
Tatiana Minkina
Saglara Mandzhieva
Aastha Sharma
Deepak Kumar
Sunil Kumar
author_facet Vicky Anand
Vishnu D. Rajput
Tatiana Minkina
Saglara Mandzhieva
Aastha Sharma
Deepak Kumar
Sunil Kumar
author_sort Vicky Anand
collection DOAJ
description Abstract The rapid increase in population, urbanization, and industrial activity in developing countries is intensifying pressure on groundwater resources, leading to severe water shortages. This study aims to evaluate and compare the predictive capabilities of six ensemble machine learning (ML) models; i.e., Random Forest (RF), AdaBoost, Neural Network, Decision Tree, k-Nearest Neighbors and Extreme Gradient Boosting. For the delineating groundwater potential zones by integrating ML algorithms with Geographic Information System (GIS) tools, offering a novel approach for groundwater resource mapping. Eleven conditioning factors, including elevation, slope, soil types, geomorphology, degree of aspect, rainfall, land use/land cover, stream power index, topographic wetness index, and land surface temperature, were used as input parameters. Model performance was evaluated using multiple metrics, including Area Under the Curve (AUC), Classification Accuracy, F1 Score, Precision, Recall, and Matthews Correlation Coefficient (MCC). The results revealed that RF was the most accurate model AUC (0.91), mapping the largest areas for very high 346 sq. km and low 486 sq. km zones. AdaBoost, effective with imbalanced data, achieved the highest MCC (0.672). Sensitivity analysis revealed that geomorphology, elevation, and rainfall were the most influential parameters for groundwater potential zoning. This study highlights the potential of ensemble ML models in advancing groundwater resource assessment and offers a foundation for further exploration in urban regions facing water scarcity challenges, and identifies priority areas for sustainable water use and planning.
format Article
id doaj-art-cf0342ee3dd14ec494871819e2a8bb49
institution OA Journals
issn 3004-8311
language English
publishDate 2025-06-01
publisher Springer
record_format Article
series Discover Cities
spelling doaj-art-cf0342ee3dd14ec494871819e2a8bb492025-08-20T02:05:46ZengSpringerDiscover Cities3004-83112025-06-012112410.1007/s44327-025-00095-xEvaluating groundwater potential with the synergistic use of geospatial methods and advanced machine learning approachesVicky Anand0Vishnu D. Rajput1Tatiana Minkina2Saglara Mandzhieva3Aastha Sharma4Deepak Kumar5Sunil Kumar6Academy of Biology and Biotechnology, Southern Federal UniversityAcademy of Biology and Biotechnology, Southern Federal UniversityAcademy of Biology and Biotechnology, Southern Federal UniversityAcademy of Biology and Biotechnology, Southern Federal UniversityDepartment of Geography, Faculty of Sciences, Jamia Millia IslamiaAtmospheric Sciences Group, Department of Geosciences, College of Arts and Sciences, Texas Tech UniversityDirectorate of Census OperationsAbstract The rapid increase in population, urbanization, and industrial activity in developing countries is intensifying pressure on groundwater resources, leading to severe water shortages. This study aims to evaluate and compare the predictive capabilities of six ensemble machine learning (ML) models; i.e., Random Forest (RF), AdaBoost, Neural Network, Decision Tree, k-Nearest Neighbors and Extreme Gradient Boosting. For the delineating groundwater potential zones by integrating ML algorithms with Geographic Information System (GIS) tools, offering a novel approach for groundwater resource mapping. Eleven conditioning factors, including elevation, slope, soil types, geomorphology, degree of aspect, rainfall, land use/land cover, stream power index, topographic wetness index, and land surface temperature, were used as input parameters. Model performance was evaluated using multiple metrics, including Area Under the Curve (AUC), Classification Accuracy, F1 Score, Precision, Recall, and Matthews Correlation Coefficient (MCC). The results revealed that RF was the most accurate model AUC (0.91), mapping the largest areas for very high 346 sq. km and low 486 sq. km zones. AdaBoost, effective with imbalanced data, achieved the highest MCC (0.672). Sensitivity analysis revealed that geomorphology, elevation, and rainfall were the most influential parameters for groundwater potential zoning. This study highlights the potential of ensemble ML models in advancing groundwater resource assessment and offers a foundation for further exploration in urban regions facing water scarcity challenges, and identifies priority areas for sustainable water use and planning.https://doi.org/10.1007/s44327-025-00095-xGroundwater predictionGroundwater resource mappingMachine learningRandom ForestWater managementWater shortages
spellingShingle Vicky Anand
Vishnu D. Rajput
Tatiana Minkina
Saglara Mandzhieva
Aastha Sharma
Deepak Kumar
Sunil Kumar
Evaluating groundwater potential with the synergistic use of geospatial methods and advanced machine learning approaches
Discover Cities
Groundwater prediction
Groundwater resource mapping
Machine learning
Random Forest
Water management
Water shortages
title Evaluating groundwater potential with the synergistic use of geospatial methods and advanced machine learning approaches
title_full Evaluating groundwater potential with the synergistic use of geospatial methods and advanced machine learning approaches
title_fullStr Evaluating groundwater potential with the synergistic use of geospatial methods and advanced machine learning approaches
title_full_unstemmed Evaluating groundwater potential with the synergistic use of geospatial methods and advanced machine learning approaches
title_short Evaluating groundwater potential with the synergistic use of geospatial methods and advanced machine learning approaches
title_sort evaluating groundwater potential with the synergistic use of geospatial methods and advanced machine learning approaches
topic Groundwater prediction
Groundwater resource mapping
Machine learning
Random Forest
Water management
Water shortages
url https://doi.org/10.1007/s44327-025-00095-x
work_keys_str_mv AT vickyanand evaluatinggroundwaterpotentialwiththesynergisticuseofgeospatialmethodsandadvancedmachinelearningapproaches
AT vishnudrajput evaluatinggroundwaterpotentialwiththesynergisticuseofgeospatialmethodsandadvancedmachinelearningapproaches
AT tatianaminkina evaluatinggroundwaterpotentialwiththesynergisticuseofgeospatialmethodsandadvancedmachinelearningapproaches
AT saglaramandzhieva evaluatinggroundwaterpotentialwiththesynergisticuseofgeospatialmethodsandadvancedmachinelearningapproaches
AT aasthasharma evaluatinggroundwaterpotentialwiththesynergisticuseofgeospatialmethodsandadvancedmachinelearningapproaches
AT deepakkumar evaluatinggroundwaterpotentialwiththesynergisticuseofgeospatialmethodsandadvancedmachinelearningapproaches
AT sunilkumar evaluatinggroundwaterpotentialwiththesynergisticuseofgeospatialmethodsandadvancedmachinelearningapproaches