Applying Multivariate Analysis and Machine Learning Approaches to Evaluating Groundwater Quality on the Kairouan Plain, Tunisia
In the Zeroud basin, a diverse array of methodologies were employed to assess, simulate, and predict the quality of groundwater intended for irrigation. These methodologies included the irrigation water quality indices (IWQIs); intricate statistical analysis involving multiple variables, supported w...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/15/19/3495 |
| _version_ | 1797447098427244544 |
|---|---|
| author | Sarra Bel Haj Salem Aissam Gaagai Imed Ben Slimene Amor Ben Moussa Kamel Zouari Krishna Kumar Yadav Mohamed Hamdy Eid Mostafa R. Abukhadra Ahmed M. El-Sherbeeny Mohamed Gad Mohamed Farouk Osama Elsherbiny Salah Elsayed Stefano Bellucci Hekmat Ibrahim |
| author_facet | Sarra Bel Haj Salem Aissam Gaagai Imed Ben Slimene Amor Ben Moussa Kamel Zouari Krishna Kumar Yadav Mohamed Hamdy Eid Mostafa R. Abukhadra Ahmed M. El-Sherbeeny Mohamed Gad Mohamed Farouk Osama Elsherbiny Salah Elsayed Stefano Bellucci Hekmat Ibrahim |
| author_sort | Sarra Bel Haj Salem |
| collection | DOAJ |
| description | In the Zeroud basin, a diverse array of methodologies were employed to assess, simulate, and predict the quality of groundwater intended for irrigation. These methodologies included the irrigation water quality indices (IWQIs); intricate statistical analysis involving multiple variables, supported with GIS techniques; an artificial neural network (ANN) model; and an XGBoost regression model. Extensive physicochemical examinations were performed on groundwater samples to elucidate their compositional attributes. The results showed that the abundance order of ions was Na<sup>+</sup> > Ca<sup>2+</sup> > Mg<sup>2+</sup> > K<sup>+</sup> and SO<sub>4</sub><sup>2−</sup> > HCO<sub>3</sub><sup>−</sup> > Cl<sup>−</sup>. The groundwater facies reflected Ca-Mg-SO<sub>4</sub>, Na-Cl, and mixed Ca-Mg-Cl/SO<sub>4</sub> water types. A cluster analysis (CA) and principal component analysis (PCA), along with ionic ratios, detected three different water characteristics. The mechanisms controlling water chemistry revealed water–rock interaction, dolomite dissolution, evaporation, and ion exchange. The assessment of groundwater quality for agriculture with respect IWQIs, such as the irrigation water quality index (IWQI), sodium adsorption ratio (SAR), sodium percentage (Na%), soluble sodium percentage (SSP), potential salinity (PS), and residual sodium carbonate (RSC), revealed that the domination of the water samples was valuable for agriculture. However, the IWQI and PS fell between high-to-severe restrictions and injurious-to-unsatisfactory. The ANN and XGBoost regression models showed robust results for predicting IWQIs. For example, ANN-HyC-9 emerged as the most precise forecasting framework according to its outcomes, as it showcased the most robust link between prime attributes and IWQI. The nine attributes of this model hold immense significance in IWQI prediction. The R<sup>2</sup> values for its training and testing data stood at 0.999 (RMSE = 0.375) and 0.823 (RMSE = 3.168), respectively. These findings indicate that XGB-HyC-3 emerged as the most accurate forecasting model, displaying a stronger connection between IWQI and its exceptional characteristics. When predicting IWQI, approximately three of the model’s attributes played a pivotal role. Notably, the model yielded R<sup>2</sup> values of 0.999 (RMSE = 0.001) and 0.913 (RMSE = 2.217) for the training and testing datasets, respectively. Overall, these results offer significant details for decision-makers in managing water quality and can support the long-term use of water resources. |
| first_indexed | 2024-03-09T13:49:57Z |
| format | Article |
| id | doaj.art-3eac489e02534d32a827cad625780b12 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-09T13:49:57Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-3eac489e02534d32a827cad625780b122023-11-30T20:50:49ZengMDPI AGWater2073-44412023-10-011519349510.3390/w15193495Applying Multivariate Analysis and Machine Learning Approaches to Evaluating Groundwater Quality on the Kairouan Plain, TunisiaSarra Bel Haj Salem0Aissam Gaagai1Imed Ben Slimene2Amor Ben Moussa3Kamel Zouari4Krishna Kumar Yadav5Mohamed Hamdy Eid6Mostafa R. Abukhadra7Ahmed M. El-Sherbeeny8Mohamed Gad9Mohamed Farouk10Osama Elsherbiny11Salah Elsayed12Stefano Bellucci13Hekmat Ibrahim14Research Laboratory of Environmental Sciences and Technologies, Higher Institute of Sciences and Technology of Environment of Borj Cedria, University of Carthage, University Campus of the Borj-Cedria Technopole BP 122, Hammam-Chott 1164, TunisiaScientific and Technical Research Center on Arid Regions (CRSTRA), Biskra 07000, AlgeriaResearch Laboratory of Environmental Sciences and Technologies, Higher Institute of Sciences and Technology of Environment of Borj Cedria, University of Carthage, University Campus of the Borj-Cedria Technopole BP 122, Hammam-Chott 1164, TunisiaResearch Laboratory of Environmental Sciences and Technologies, Higher Institute of Sciences and Technology of Environment of Borj Cedria, University of Carthage, University Campus of the Borj-Cedria Technopole BP 122, Hammam-Chott 1164, TunisiaResearch Laboratory of Environmental Sciences and Technologies, Higher Institute of Sciences and Technology of Environment of Borj Cedria, University of Carthage, University Campus of the Borj-Cedria Technopole BP 122, Hammam-Chott 1164, TunisiaFaculty of Science and Technology, Madhyanchal Professional University, Bhopal 462044, IndiaGeology Department, Faculty of Science, Beni-Suef University, Beni-Suef 65211, EgyptGeology Department, Faculty of Science, Beni-Suef University, Beni-Suef 65211, EgyptIndustrial Engineering Department, College of Engineering, King Saud University, P.O. Box 800, Riyadh 11421, Saudi ArabiaHydrogeology, Evaluation of Natural Resources Department, Environmental Studies and Research Institute, University of Sadat City, Shibin El-Kom 32897, EgyptAgricultural Engineering, Surveying of Natural Resources in Environmental Systems Department, Environmental Studies and Research Institute, University of Sadat City, Sadat City 32897, EgyptAgricultural Engineering Department, Faculty of Agriculture, Mansoura University, Mansoura 35516, EgyptAgricultural Engineering, Evaluation of Natural Resources Department, Environmental Studies and Research Institute, University of Sadat City, Shiben El Kom 32897, EgyptINFN, Laboratori Nazionali di Frascati, E. Fermi 54, 00044 Frascati, ItalyGeology Department, Faculty of Science, Menoufia University, Shibin El-Kom 51123, EgyptIn the Zeroud basin, a diverse array of methodologies were employed to assess, simulate, and predict the quality of groundwater intended for irrigation. These methodologies included the irrigation water quality indices (IWQIs); intricate statistical analysis involving multiple variables, supported with GIS techniques; an artificial neural network (ANN) model; and an XGBoost regression model. Extensive physicochemical examinations were performed on groundwater samples to elucidate their compositional attributes. The results showed that the abundance order of ions was Na<sup>+</sup> > Ca<sup>2+</sup> > Mg<sup>2+</sup> > K<sup>+</sup> and SO<sub>4</sub><sup>2−</sup> > HCO<sub>3</sub><sup>−</sup> > Cl<sup>−</sup>. The groundwater facies reflected Ca-Mg-SO<sub>4</sub>, Na-Cl, and mixed Ca-Mg-Cl/SO<sub>4</sub> water types. A cluster analysis (CA) and principal component analysis (PCA), along with ionic ratios, detected three different water characteristics. The mechanisms controlling water chemistry revealed water–rock interaction, dolomite dissolution, evaporation, and ion exchange. The assessment of groundwater quality for agriculture with respect IWQIs, such as the irrigation water quality index (IWQI), sodium adsorption ratio (SAR), sodium percentage (Na%), soluble sodium percentage (SSP), potential salinity (PS), and residual sodium carbonate (RSC), revealed that the domination of the water samples was valuable for agriculture. However, the IWQI and PS fell between high-to-severe restrictions and injurious-to-unsatisfactory. The ANN and XGBoost regression models showed robust results for predicting IWQIs. For example, ANN-HyC-9 emerged as the most precise forecasting framework according to its outcomes, as it showcased the most robust link between prime attributes and IWQI. The nine attributes of this model hold immense significance in IWQI prediction. The R<sup>2</sup> values for its training and testing data stood at 0.999 (RMSE = 0.375) and 0.823 (RMSE = 3.168), respectively. These findings indicate that XGB-HyC-3 emerged as the most accurate forecasting model, displaying a stronger connection between IWQI and its exceptional characteristics. When predicting IWQI, approximately three of the model’s attributes played a pivotal role. Notably, the model yielded R<sup>2</sup> values of 0.999 (RMSE = 0.001) and 0.913 (RMSE = 2.217) for the training and testing datasets, respectively. Overall, these results offer significant details for decision-makers in managing water quality and can support the long-term use of water resources.https://www.mdpi.com/2073-4441/15/19/3495physicochemical parametersgroundwateragriculturecluster analysismachine learning modelsGIS |
| spellingShingle | Sarra Bel Haj Salem Aissam Gaagai Imed Ben Slimene Amor Ben Moussa Kamel Zouari Krishna Kumar Yadav Mohamed Hamdy Eid Mostafa R. Abukhadra Ahmed M. El-Sherbeeny Mohamed Gad Mohamed Farouk Osama Elsherbiny Salah Elsayed Stefano Bellucci Hekmat Ibrahim Applying Multivariate Analysis and Machine Learning Approaches to Evaluating Groundwater Quality on the Kairouan Plain, Tunisia Water physicochemical parameters groundwater agriculture cluster analysis machine learning models GIS |
| title | Applying Multivariate Analysis and Machine Learning Approaches to Evaluating Groundwater Quality on the Kairouan Plain, Tunisia |
| title_full | Applying Multivariate Analysis and Machine Learning Approaches to Evaluating Groundwater Quality on the Kairouan Plain, Tunisia |
| title_fullStr | Applying Multivariate Analysis and Machine Learning Approaches to Evaluating Groundwater Quality on the Kairouan Plain, Tunisia |
| title_full_unstemmed | Applying Multivariate Analysis and Machine Learning Approaches to Evaluating Groundwater Quality on the Kairouan Plain, Tunisia |
| title_short | Applying Multivariate Analysis and Machine Learning Approaches to Evaluating Groundwater Quality on the Kairouan Plain, Tunisia |
| title_sort | applying multivariate analysis and machine learning approaches to evaluating groundwater quality on the kairouan plain tunisia |
| topic | physicochemical parameters groundwater agriculture cluster analysis machine learning models GIS |
| url | https://www.mdpi.com/2073-4441/15/19/3495 |
| work_keys_str_mv | AT sarrabelhajsalem applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT aissamgaagai applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT imedbenslimene applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT amorbenmoussa applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT kamelzouari applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT krishnakumaryadav applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT mohamedhamdyeid applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT mostafarabukhadra applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT ahmedmelsherbeeny applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT mohamedgad applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT mohamedfarouk applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT osamaelsherbiny applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT salahelsayed applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT stefanobellucci applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia AT hekmatibrahim applyingmultivariateanalysisandmachinelearningapproachestoevaluatinggroundwaterqualityonthekairouanplaintunisia |