Susceptibility Prediction of Groundwater Hardness Using Ensemble Machine Learning Models
Groundwater resources, unlike surface water, are more vulnerable to disturbances and contaminations, as they take a very long time and significant cost to recover. So, predictive modeling and prevention strategies can empower policymakers for efficient groundwater governance through informed decisio...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/12/10/2770 |
| id |
doaj-97d92c6cd86f499aac86047bf6f371ac |
|---|---|
| record_format |
Article |
| spelling |
doaj-97d92c6cd86f499aac86047bf6f371ac2020-11-25T03:28:56ZengMDPI AGWater2073-44412020-10-01122770277010.3390/w12102770Susceptibility Prediction of Groundwater Hardness Using Ensemble Machine Learning ModelsAmirhosein Mosavi0Farzaneh Sajedi Hosseini1Bahram Choubin2Mahsa Abdolshahnejad3Hamidreza Gharechaee4Ahmadreza Lahijanzadeh5Adrienn A. Dineva6Environmental Quality, Atmospheric Science and Climate Change Research Group, Ton Duc Thang University, Ho Chi Minh, VietnamReclamation of Arid and Mountainous Regions Department, Faculty of Natural Resources, University of Tehran, Karaj 31585-77871, IranSoil Conservation and Watershed Management Research Department, West Azarbaijan Agricultural and Natural Resources Research and Education Center, AREEO, Urmia 57169-63963, IranReclamation of Arid and Mountainous Regions Department, Faculty of Natural Resources, University of Tehran, Karaj 31585-77871, IranReclamation of Arid and Mountainous Regions Department, Faculty of Natural Resources, University of Tehran, Karaj 31585-77871, IranDeputy for Marine Environment and Wetlands, Iran Department of Environment, Tehran 73831-4155, IranInstitute of Research and Development, Duy Tan University, Da Nang 550000, VietnamGroundwater resources, unlike surface water, are more vulnerable to disturbances and contaminations, as they take a very long time and significant cost to recover. So, predictive modeling and prevention strategies can empower policymakers for efficient groundwater governance through informed decisions and recommendations. Due to the importance of groundwater quality modeling, the hardness susceptibility mapping using machine learning (ML) models has not been explored. For the first time, the current research aimed to predict groundwater hardness susceptibility using the ML models. The performance of two ensemble models of boosted regression trees (BRT) and random forest (RF) is investigated through the arrangement of a comparative study with multivariate discriminant analysis (MDA). According to the hardness values in 135 groundwater quality monitoring wells, the hard and soft water are determined; then, 11 predictor variables including distance from the sea (DFS), land use, elevation, distance from the river (DFR), depth to groundwater (DTGW), pH, precipitation (PCP), evaporation (E), groundwater level (GWL), curvature, and lithology are used for predicting the groundwater hardness susceptibility map. Results indicated that the variables of DFR, DTGW, elevation, and DFS had a higher contribution to the modeling process. So, the high harness areas are mostly related to low elevations, low DTGW, and proximity to river and sea, which facilitate the percolation conditions for minerals containing calcium or magnesium into groundwater.https://www.mdpi.com/2073-4441/12/10/2770water quality assessmentgroundwaterhardnesssusceptibilitymachine learningboosted regression trees |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Amirhosein Mosavi Farzaneh Sajedi Hosseini Bahram Choubin Mahsa Abdolshahnejad Hamidreza Gharechaee Ahmadreza Lahijanzadeh Adrienn A. Dineva |
| spellingShingle |
Amirhosein Mosavi Farzaneh Sajedi Hosseini Bahram Choubin Mahsa Abdolshahnejad Hamidreza Gharechaee Ahmadreza Lahijanzadeh Adrienn A. Dineva Susceptibility Prediction of Groundwater Hardness Using Ensemble Machine Learning Models Water water quality assessment groundwater hardness susceptibility machine learning boosted regression trees |
| author_facet |
Amirhosein Mosavi Farzaneh Sajedi Hosseini Bahram Choubin Mahsa Abdolshahnejad Hamidreza Gharechaee Ahmadreza Lahijanzadeh Adrienn A. Dineva |
| author_sort |
Amirhosein Mosavi |
| title |
Susceptibility Prediction of Groundwater Hardness Using Ensemble Machine Learning Models |
| title_short |
Susceptibility Prediction of Groundwater Hardness Using Ensemble Machine Learning Models |
| title_full |
Susceptibility Prediction of Groundwater Hardness Using Ensemble Machine Learning Models |
| title_fullStr |
Susceptibility Prediction of Groundwater Hardness Using Ensemble Machine Learning Models |
| title_full_unstemmed |
Susceptibility Prediction of Groundwater Hardness Using Ensemble Machine Learning Models |
| title_sort |
susceptibility prediction of groundwater hardness using ensemble machine learning models |
| publisher |
MDPI AG |
| series |
Water |
| issn |
2073-4441 |
| publishDate |
2020-10-01 |
| description |
Groundwater resources, unlike surface water, are more vulnerable to disturbances and contaminations, as they take a very long time and significant cost to recover. So, predictive modeling and prevention strategies can empower policymakers for efficient groundwater governance through informed decisions and recommendations. Due to the importance of groundwater quality modeling, the hardness susceptibility mapping using machine learning (ML) models has not been explored. For the first time, the current research aimed to predict groundwater hardness susceptibility using the ML models. The performance of two ensemble models of boosted regression trees (BRT) and random forest (RF) is investigated through the arrangement of a comparative study with multivariate discriminant analysis (MDA). According to the hardness values in 135 groundwater quality monitoring wells, the hard and soft water are determined; then, 11 predictor variables including distance from the sea (DFS), land use, elevation, distance from the river (DFR), depth to groundwater (DTGW), pH, precipitation (PCP), evaporation (E), groundwater level (GWL), curvature, and lithology are used for predicting the groundwater hardness susceptibility map. Results indicated that the variables of DFR, DTGW, elevation, and DFS had a higher contribution to the modeling process. So, the high harness areas are mostly related to low elevations, low DTGW, and proximity to river and sea, which facilitate the percolation conditions for minerals containing calcium or magnesium into groundwater. |
| topic |
water quality assessment groundwater hardness susceptibility machine learning boosted regression trees |
| url |
https://www.mdpi.com/2073-4441/12/10/2770 |
| work_keys_str_mv |
AT amirhoseinmosavi susceptibilitypredictionofgroundwaterhardnessusingensemblemachinelearningmodels AT farzanehsajedihosseini susceptibilitypredictionofgroundwaterhardnessusingensemblemachinelearningmodels AT bahramchoubin susceptibilitypredictionofgroundwaterhardnessusingensemblemachinelearningmodels AT mahsaabdolshahnejad susceptibilitypredictionofgroundwaterhardnessusingensemblemachinelearningmodels AT hamidrezagharechaee susceptibilitypredictionofgroundwaterhardnessusingensemblemachinelearningmodels AT ahmadrezalahijanzadeh susceptibilitypredictionofgroundwaterhardnessusingensemblemachinelearningmodels AT adriennadineva susceptibilitypredictionofgroundwaterhardnessusingensemblemachinelearningmodels |
| _version_ |
1724581918454841344 |