A novel integrated approach to predict the sodium absorption ratio (SAR) of groundwater sustainability using deep learning models and SHAP approach

Abstract Agriculture is a crucial factor in improving the country economic growth. With the massive impact of environment variation, supplying and measuring the quality of water for irrigation usage is a crucial task for water resource management authority. The demand for good quality water for both...

Full description

Saved in:
Bibliographic Details
Main Authors: Kanak N. Moharir, Chaitanya Baliram Pande, Rabin Chakrabortty, Malay Pramanik, Balamurugan Paneerselvam, Okan Mert Katipoğlu, Subodh Chandra Pal, Miklas Scholz, Krishna Kumar Yadav, Lamjed Mansour, Mohamed Elsahabi
Format: Article
Language:English
Published: SpringerOpen 2025-06-01
Series:Applied Water Science
Subjects:
Online Access:https://doi.org/10.1007/s13201-025-02521-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849764505004802048
author Kanak N. Moharir
Chaitanya Baliram Pande
Rabin Chakrabortty
Malay Pramanik
Balamurugan Paneerselvam
Okan Mert Katipoğlu
Subodh Chandra Pal
Miklas Scholz
Krishna Kumar Yadav
Lamjed Mansour
Mohamed Elsahabi
author_facet Kanak N. Moharir
Chaitanya Baliram Pande
Rabin Chakrabortty
Malay Pramanik
Balamurugan Paneerselvam
Okan Mert Katipoğlu
Subodh Chandra Pal
Miklas Scholz
Krishna Kumar Yadav
Lamjed Mansour
Mohamed Elsahabi
author_sort Kanak N. Moharir
collection DOAJ
description Abstract Agriculture is a crucial factor in improving the country economic growth. With the massive impact of environment variation, supplying and measuring the quality of water for irrigation usage is a crucial task for water resource management authority. The demand for good quality water for both drinking and irrigation uses is increasing day by day in recent years. The main aim of the present study is to identify the suitability of surface water for irrigation uses in the Man River basin of Maharashtra, India using advanced techniques. These region first time is used such kind of models i.e. boosted tree, AdaBoost, decision tree, extremely randomized tree model, and feed-forward neural network (deep learning) models, and these models are better to analyze and understand the groundwater quality datasets in the saline area. The prediction results are evaluated with the use of different performance metrics, mean absolute error (MAE), mean absolute relative error (MARE), Nash Sutcliffe efficiency (NSE), root mean squared error (RMSE), and coefficient of determination (R 2). The study identified that the boosted tree model is more appropriate for the SAR prediction value, this model with high accuracy compared with other models. The result of this study shows that boosted tree model is very suitable for prediction of SAR and also provided the accurate information for agriculture purposes. In the first scenario, the boosted tree model shows lower value of mean squared error (MSE) of 0.26 and higher R 2 of 0.88, the second scenario shows lower value of MSE of 0.11 and higher value of R 2 of 0.91. Overall, in both the scenarios, the result of boosted tree model is more favorable for SAR% prediction. This work shows that machine and deep learning models can improve and better prediction of the groundwater quality in the study area. It is essential to understand the water quality and improve the sustainable agriculture system and development. These advanced modeling methods help to stakeholders make better water management and irrigation decisions, boosting agricultural sustainability and productivity.
format Article
id doaj-art-66695ba8484b4808a72253efa295c0e7
institution DOAJ
issn 2190-5487
2190-5495
language English
publishDate 2025-06-01
publisher SpringerOpen
record_format Article
series Applied Water Science
spelling doaj-art-66695ba8484b4808a72253efa295c0e72025-08-20T03:05:07ZengSpringerOpenApplied Water Science2190-54872190-54952025-06-0115712710.1007/s13201-025-02521-2A novel integrated approach to predict the sodium absorption ratio (SAR) of groundwater sustainability using deep learning models and SHAP approachKanak N. Moharir0Chaitanya Baliram Pande1Rabin Chakrabortty2Malay Pramanik3Balamurugan Paneerselvam4Okan Mert Katipoğlu5Subodh Chandra Pal6Miklas Scholz7Krishna Kumar Yadav8Lamjed Mansour9Mohamed Elsahabi10School of earth Sciences, Banasthali VidyapithDepartment of Civil Engineering, School of Core Engineering, Faculty of Science, Technology and Architecture (FoSTA), Manipal University JaipurDepartment of Civil Engineering, American University of SharjahSchool of Environment Resources and Development, Asian Institute of Technology (AIT)Center of Excellence in Interdisciplinary Research for Sustainable Development, Chulalongkorn UniversityFaculty of Engineering and Architecture, Department of Civil Engineering, Erzincan Binali Yıldırım UniversityDepartment of Geography, The University of BurdwanDepartment of Water Management, Sector of Regional Development, Environment and ConstructionDepartment of Environmental Science, Parul Institute of Applied Sciences, Parul UniversityDepartment of Zoology, College of Science, King Saud UniversityCivil Engineering Departments, Faculty of Engineering, Aswan UniversityAbstract Agriculture is a crucial factor in improving the country economic growth. With the massive impact of environment variation, supplying and measuring the quality of water for irrigation usage is a crucial task for water resource management authority. The demand for good quality water for both drinking and irrigation uses is increasing day by day in recent years. The main aim of the present study is to identify the suitability of surface water for irrigation uses in the Man River basin of Maharashtra, India using advanced techniques. These region first time is used such kind of models i.e. boosted tree, AdaBoost, decision tree, extremely randomized tree model, and feed-forward neural network (deep learning) models, and these models are better to analyze and understand the groundwater quality datasets in the saline area. The prediction results are evaluated with the use of different performance metrics, mean absolute error (MAE), mean absolute relative error (MARE), Nash Sutcliffe efficiency (NSE), root mean squared error (RMSE), and coefficient of determination (R 2). The study identified that the boosted tree model is more appropriate for the SAR prediction value, this model with high accuracy compared with other models. The result of this study shows that boosted tree model is very suitable for prediction of SAR and also provided the accurate information for agriculture purposes. In the first scenario, the boosted tree model shows lower value of mean squared error (MSE) of 0.26 and higher R 2 of 0.88, the second scenario shows lower value of MSE of 0.11 and higher value of R 2 of 0.91. Overall, in both the scenarios, the result of boosted tree model is more favorable for SAR% prediction. This work shows that machine and deep learning models can improve and better prediction of the groundwater quality in the study area. It is essential to understand the water quality and improve the sustainable agriculture system and development. These advanced modeling methods help to stakeholders make better water management and irrigation decisions, boosting agricultural sustainability and productivity.https://doi.org/10.1007/s13201-025-02521-2Irrigation water quality assessmentSARMachine and deep learningSustainable Water
spellingShingle Kanak N. Moharir
Chaitanya Baliram Pande
Rabin Chakrabortty
Malay Pramanik
Balamurugan Paneerselvam
Okan Mert Katipoğlu
Subodh Chandra Pal
Miklas Scholz
Krishna Kumar Yadav
Lamjed Mansour
Mohamed Elsahabi
A novel integrated approach to predict the sodium absorption ratio (SAR) of groundwater sustainability using deep learning models and SHAP approach
Applied Water Science
Irrigation water quality assessment
SAR
Machine and deep learning
Sustainable Water
title A novel integrated approach to predict the sodium absorption ratio (SAR) of groundwater sustainability using deep learning models and SHAP approach
title_full A novel integrated approach to predict the sodium absorption ratio (SAR) of groundwater sustainability using deep learning models and SHAP approach
title_fullStr A novel integrated approach to predict the sodium absorption ratio (SAR) of groundwater sustainability using deep learning models and SHAP approach
title_full_unstemmed A novel integrated approach to predict the sodium absorption ratio (SAR) of groundwater sustainability using deep learning models and SHAP approach
title_short A novel integrated approach to predict the sodium absorption ratio (SAR) of groundwater sustainability using deep learning models and SHAP approach
title_sort novel integrated approach to predict the sodium absorption ratio sar of groundwater sustainability using deep learning models and shap approach
topic Irrigation water quality assessment
SAR
Machine and deep learning
Sustainable Water
url https://doi.org/10.1007/s13201-025-02521-2
work_keys_str_mv AT kanaknmoharir anovelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT chaitanyabalirampande anovelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT rabinchakrabortty anovelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT malaypramanik anovelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT balamuruganpaneerselvam anovelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT okanmertkatipoglu anovelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT subodhchandrapal anovelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT miklasscholz anovelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT krishnakumaryadav anovelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT lamjedmansour anovelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT mohamedelsahabi anovelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT kanaknmoharir novelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT chaitanyabalirampande novelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT rabinchakrabortty novelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT malaypramanik novelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT balamuruganpaneerselvam novelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT okanmertkatipoglu novelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT subodhchandrapal novelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT miklasscholz novelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT krishnakumaryadav novelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT lamjedmansour novelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach
AT mohamedelsahabi novelintegratedapproachtopredictthesodiumabsorptionratiosarofgroundwatersustainabilityusingdeeplearningmodelsandshapapproach