A Machine Learning-Based Framework for Water Quality Index Estimation in the Southern Bug River
River water quality is of utmost importance because the river is not only one of the key water resources but also a natural habitat serving its surrounding environment. In a bid to address whether it has a qualified quality, various analytics are required to be considered, but it is challenging to m...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/15/20/3543 |
| _version_ | 1797571999414878208 |
|---|---|
| author | Adil Masood Majid Niazkar Mohammad Zakwan Reza Piraei |
| author_facet | Adil Masood Majid Niazkar Mohammad Zakwan Reza Piraei |
| author_sort | Adil Masood |
| collection | DOAJ |
| description | River water quality is of utmost importance because the river is not only one of the key water resources but also a natural habitat serving its surrounding environment. In a bid to address whether it has a qualified quality, various analytics are required to be considered, but it is challenging to measure all of them frequently along a river reach. Therefore, estimating water quality index (WQI) incorporating several weighted analytics is a useful approach to assess water quality in rivers. This study explored applications of ten machine learning (ML) models to estimate WQI for the Southern Bug River, which is the second-longest river in Ukraine. The ML methods considered in this study include artificial neural networks (ANNs), Support Vector Regressor (SVR), Extreme Learning Machine, Decision Tree Regressor, random forest, AdaBoost (AB), Gradient Boosting Regressor, XGBoost Regressor (XGBR), Gaussian process (GP), and K-nearest neighbors (KNN). Each data measurement consists of nine analytics (NH<sub>4</sub>, BOD<sub>5</sub>, suspended solids, DO, NO<sub>3</sub>, NO<sub>2</sub>, SO<sub>4</sub>, PO<sub>4</sub>, Cl), while the quantity of data is more than 2700 data points. The results indicated that all ML models demonstrate satisfactory performance in predicting WQI. However, GP outperformed the other models, followed by XGBR, SVR, and KNN. Furthermore, ANN and AB demonstrated relatively weaker performance. Moreover, a reliability assessment conducted on both training and testing datasets also confirmed the results of the comparative analysis. Overall, the results enhance the assertion that ML models can sufficiently predict WQI, thereby enhancing water quality management. |
| first_indexed | 2024-03-10T20:48:27Z |
| format | Article |
| id | doaj.art-062f98fe6f304a72a583103650ec9369 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-10T20:48:27Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-062f98fe6f304a72a583103650ec93692023-11-19T18:29:09ZengMDPI AGWater2073-44412023-10-011520354310.3390/w15203543A Machine Learning-Based Framework for Water Quality Index Estimation in the Southern Bug RiverAdil Masood0Majid Niazkar1Mohammad Zakwan2Reza Piraei3Department of Civil Engineering, Jamia Millia Islamia University, New Delhi 110025, IndiaFaculty of Engineering, Free University of Bozen-Bolzano, Piazza Università 5, 39100 Bolzano, ItalySchool of Technology, Maulana Azad National Urdu University, Hyderabad 500032, Telangana, IndiaDepartment of Civil Engineering, Shiraz University, Shiraz 71348511554, IranRiver water quality is of utmost importance because the river is not only one of the key water resources but also a natural habitat serving its surrounding environment. In a bid to address whether it has a qualified quality, various analytics are required to be considered, but it is challenging to measure all of them frequently along a river reach. Therefore, estimating water quality index (WQI) incorporating several weighted analytics is a useful approach to assess water quality in rivers. This study explored applications of ten machine learning (ML) models to estimate WQI for the Southern Bug River, which is the second-longest river in Ukraine. The ML methods considered in this study include artificial neural networks (ANNs), Support Vector Regressor (SVR), Extreme Learning Machine, Decision Tree Regressor, random forest, AdaBoost (AB), Gradient Boosting Regressor, XGBoost Regressor (XGBR), Gaussian process (GP), and K-nearest neighbors (KNN). Each data measurement consists of nine analytics (NH<sub>4</sub>, BOD<sub>5</sub>, suspended solids, DO, NO<sub>3</sub>, NO<sub>2</sub>, SO<sub>4</sub>, PO<sub>4</sub>, Cl), while the quantity of data is more than 2700 data points. The results indicated that all ML models demonstrate satisfactory performance in predicting WQI. However, GP outperformed the other models, followed by XGBR, SVR, and KNN. Furthermore, ANN and AB demonstrated relatively weaker performance. Moreover, a reliability assessment conducted on both training and testing datasets also confirmed the results of the comparative analysis. Overall, the results enhance the assertion that ML models can sufficiently predict WQI, thereby enhancing water quality management.https://www.mdpi.com/2073-4441/15/20/3543water quality indexriversmachine learningsupport vector machineextreme learning machineboosting algorithms |
| spellingShingle | Adil Masood Majid Niazkar Mohammad Zakwan Reza Piraei A Machine Learning-Based Framework for Water Quality Index Estimation in the Southern Bug River Water water quality index rivers machine learning support vector machine extreme learning machine boosting algorithms |
| title | A Machine Learning-Based Framework for Water Quality Index Estimation in the Southern Bug River |
| title_full | A Machine Learning-Based Framework for Water Quality Index Estimation in the Southern Bug River |
| title_fullStr | A Machine Learning-Based Framework for Water Quality Index Estimation in the Southern Bug River |
| title_full_unstemmed | A Machine Learning-Based Framework for Water Quality Index Estimation in the Southern Bug River |
| title_short | A Machine Learning-Based Framework for Water Quality Index Estimation in the Southern Bug River |
| title_sort | machine learning based framework for water quality index estimation in the southern bug river |
| topic | water quality index rivers machine learning support vector machine extreme learning machine boosting algorithms |
| url | https://www.mdpi.com/2073-4441/15/20/3543 |
| work_keys_str_mv | AT adilmasood amachinelearningbasedframeworkforwaterqualityindexestimationinthesouthernbugriver AT majidniazkar amachinelearningbasedframeworkforwaterqualityindexestimationinthesouthernbugriver AT mohammadzakwan amachinelearningbasedframeworkforwaterqualityindexestimationinthesouthernbugriver AT rezapiraei amachinelearningbasedframeworkforwaterqualityindexestimationinthesouthernbugriver AT adilmasood machinelearningbasedframeworkforwaterqualityindexestimationinthesouthernbugriver AT majidniazkar machinelearningbasedframeworkforwaterqualityindexestimationinthesouthernbugriver AT mohammadzakwan machinelearningbasedframeworkforwaterqualityindexestimationinthesouthernbugriver AT rezapiraei machinelearningbasedframeworkforwaterqualityindexestimationinthesouthernbugriver |