2018_Multilinear Regression Method For Prediction of Water Quality Index
| Format: | General Document |
|---|
| _version_ | 1860797983341150208 |
|---|---|
| building | INTELEK Repository |
| collection | Online Access |
| collectionurl | https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 |
| copyright | Copyright©PWB2025 |
| country | Malaysia |
| date | 2025-01-22 15:18 |
| format | General Document |
| id | 15270 |
| institution | UniSZA |
| originalfilename | MULTILINEAR REGRESSION METHOD FOR PREDICTION OF WATER QUALITY INDEX |
| person | PDFsam Basic v4.2.10 Ismail bin Zainal Abidin |
| recordtype | oai_dc |
| resourceurl | https://intelek.unisza.edu.my/intelek/pages/view.php?ref=15270 |
| sourcemedia | Server storage Scanned document |
| spelling | 15270 https://intelek.unisza.edu.my/intelek/pages/view.php?ref=15270 https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 General Document Malaysia Library Staff (Top Management) Library Staff (Management) Library Staff (Support) Terengganu English UniSZA East Coast Environmental Research Institute application/pdf 1.5 PDFsam Basic v4.2.10 Chemometrics Server storage Scanned document Universiti Sultan Zainal Abidin UniSZA Private Access Universiti Sultan Zainal Abidin SAMBox 2.3.4; modified using iTextSharp™ 5.5.10 ©2000-2016 iText Group NV (AGPL-version) 2025-01-22 15:18 MULTILINEAR REGRESSION METHOD FOR PREDICTION OF WATER QUALITY INDEX 153 2018_Multilinear Regression Method For Prediction of Water Quality Index Copyright©PWB2025 Pollution—Measurement Multivariate analysis Environmental chemistry—Statistical methods Ismail bin Zainal Abidin Multilinear Regression Method Prediction Water Quality Index Water quality—Mathematical models Water quality—Measurement Environmental monitoring—Statistical methods Year by year, the Malaysian government had to allocate a huge sum of budget just to preserve the river water monitoring program. The budget will be used to cover the labor charges, reagent, chemical, and lab instruments. If the WQI can be calculated using less parameter, the monitoring cost obviously can be reduced can cause a less burden to the government. By using current statistical analysis, an intelligent prediction model can be created and used to predict the WQI with lesser parameters. Apart from that, to ensure the water quality model can be easily used by the public, an application or software can be created. So that, the environmentalist can gains the maximum potential of the water quality model in water quality monitoring and able to deliver the knowledge to others. There are three rivers selected (Terengganu river, Kuantan river and Johor river) in this study, which covered Terengganu, Pahang and Johor state. In this study, discriminant analysis was applied to determine the significant variables among all the water quality index parameters. In the forward stepwise mode, variables are included step by step beginning with the most significant variable until no significant changes were obtained. Significant variables that are found in discriminant analysis, then undergo regression analysis to find the standardized coefficient for the construction of water quality model. The discriminant analysis and multi-linear regression (MLR) modeling method was performed by the XLStat software (Version 2014.5.03). Four parameters are found significantly in Terengganu river, Kuantan river and Johor river. For Terengganu river, the significant parameters are, DO, COD, SS, pH with partial R² value 0.230, 0.256, 0.141, 0.112 respectively, with the accuracy of spatial classification of 87.18%. Meanwhile, for Kuantan river, the significant parameters recorded which are COD, DO, AN and SS with partial R² value 0.603, 0.247, 0.150 and 0.089 respectively, with the accuracy of spatial classification of 96.12%. Lastly, for Johor river, the variables are BOD, SS, AN and DO with the accuracy of spatial classification of 98.00%, and the partial R² are 0.410, 0.081, 0.087 and 0.065 respectively. The R value that indicates the correlation coefficient between dependent variable (WQI) and independent variables (significant parameters) for Terengganu river, Johor river and Kuantan river are 0.928, 0.960 and 0.960 respectively. This study clearly indicates that it is possible to reduce the number of parameters in the water quality prediction without losing much of the information. Using discriminant analysis, the parameters are selected from the most significant and the non-significant parameters have been left out. The high values of correlation coefficient among all rivers indicate a strong relationship between actual WQI and the predicted WQI. The difference of the significant parameters of these rivers can be related to the type of pollution load received by each river, type of land use along the river, anthropogenic activities, rainfall and surface runoff. The models can be used if rapid calculation of WQI is required. Hydrology—Statistical methods Water—Pollution—Analysis Geochemical modeling Dissertations, Academic Thesis |
| spellingShingle | 2018_Multilinear Regression Method For Prediction of Water Quality Index |
| state | Terengganu |
| subject | Chemometrics Pollution—Measurement Multivariate analysis Environmental chemistry—Statistical methods Water quality—Mathematical models Water quality—Measurement Environmental monitoring—Statistical methods Hydrology—Statistical methods Water—Pollution—Analysis Geochemical modeling Dissertations, Academic |
| summary | Year by year, the Malaysian government had to allocate a huge sum of budget just to preserve the river water monitoring program. The budget will be used to cover the labor charges, reagent, chemical, and lab instruments. If the WQI can be calculated using less parameter, the monitoring cost obviously can be reduced can cause a less burden to the government. By using current statistical analysis, an intelligent prediction model can be created and used to predict the WQI with lesser parameters. Apart from that, to ensure the water quality model can be easily used by the public, an application or software can be created. So that, the environmentalist can gains the maximum potential of the water quality model in water quality monitoring and able to deliver the knowledge to others. There are three rivers selected (Terengganu river, Kuantan river and Johor river) in this study, which covered Terengganu, Pahang and Johor state. In this study, discriminant analysis was applied to determine the significant variables among all the water quality index parameters. In the forward stepwise mode, variables are included step by step beginning with the most significant variable until no significant changes were obtained. Significant variables that are found in discriminant analysis, then undergo regression analysis to find the standardized coefficient for the construction of water quality model. The discriminant analysis and multi-linear regression (MLR) modeling method was performed by the XLStat software (Version 2014.5.03). Four parameters are found significantly in Terengganu river, Kuantan river and Johor river. For Terengganu river, the significant parameters are, DO, COD, SS, pH with partial R² value 0.230, 0.256, 0.141, 0.112 respectively, with the accuracy of spatial classification of 87.18%. Meanwhile, for Kuantan river, the significant parameters recorded which are COD, DO, AN and SS with partial R² value 0.603, 0.247, 0.150 and 0.089 respectively, with the accuracy of spatial classification of 96.12%. Lastly, for Johor river, the variables are BOD, SS, AN and DO with the accuracy of spatial classification of 98.00%, and the partial R² are 0.410, 0.081, 0.087 and 0.065 respectively. The R value that indicates the correlation coefficient between dependent variable (WQI) and independent variables (significant parameters) for Terengganu river, Johor river and Kuantan river are 0.928, 0.960 and 0.960 respectively. This study clearly indicates that it is possible to reduce the number of parameters in the water quality prediction without losing much of the information. Using discriminant analysis, the parameters are selected from the most significant and the non-significant parameters have been left out. The high values of correlation coefficient among all rivers indicate a strong relationship between actual WQI and the predicted WQI. The difference of the significant parameters of these rivers can be related to the type of pollution load received by each river, type of land use along the river, anthropogenic activities, rainfall and surface runoff. The models can be used if rapid calculation of WQI is required. |
| title | 2018_Multilinear Regression Method For Prediction of Water Quality Index |
| title_full | 2018_Multilinear Regression Method For Prediction of Water Quality Index |
| title_fullStr | 2018_Multilinear Regression Method For Prediction of Water Quality Index |
| title_full_unstemmed | 2018_Multilinear Regression Method For Prediction of Water Quality Index |
| title_short | 2018_Multilinear Regression Method For Prediction of Water Quality Index |
| title_sort | 2018_multilinear regression method for prediction of water quality index |