River water quality modeling using combined principle component analysis (PCA) and multiple linear regressions (MLR): a case study at Klang River, Malaysia
A collective set of data over five years (2003 to 2007) in Klang River, Selangor were studied in attempt to assess and determine the contributions of sources affecting the water quality. A precise technique of multiple linear regressions (MLR) were prepare as an advance tool for surface water modeli...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IDOSI Publications
2011
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/23397/ http://psasir.upm.edu.my/id/eprint/23397/1/23397.pdf |
| _version_ | 1848844746953326592 |
|---|---|
| author | Mohd Nasir, Mohd Fahmi Samsudin, Mohd Saiful Mohamad, Isahak Awaluddin, Mohammad Roshide Amir Mansor, Muhd Ariffin Juahir, Hafizan Ramli, Norlafifah |
| author_facet | Mohd Nasir, Mohd Fahmi Samsudin, Mohd Saiful Mohamad, Isahak Awaluddin, Mohammad Roshide Amir Mansor, Muhd Ariffin Juahir, Hafizan Ramli, Norlafifah |
| author_sort | Mohd Nasir, Mohd Fahmi |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | A collective set of data over five years (2003 to 2007) in Klang River, Selangor were studied in attempt to assess and determine the contributions of sources affecting the water quality. A precise technique of multiple linear regressions (MLR) were prepare as an advance tool for surface water modeling and forecasting. Likewise, principle component analysis (PCA) was used to simplify and understand the complex relationship among water quality parameters. Nine principle components were found responsible for the data structure provisionally named as soil erosion, anthropogenic input, surface runoff, fecal waste, detergent, urban domestic waste, industrial effluent, fertilizer waste and residential waste explains 72% of the total variance for all the data sets. Meanwhile, urban domestic pollution accounted as the highest pollution contributor to the Klang River. Thus, the advancement of receptor model was applied in order to identify the major sources of pollutant at Klang River. Result showed that the use of PCA as inputs improved the MLR model prediction by reducing their complexity and eliminating data collinearity where R2 value in this study is 0.75 and the model indicates that 75% variability of WQI explained by the five independent variables used in the model. This assessment presents the importance and advantages poses by multivariate statistical analysis of large and complex databases in order to get improved information about the water quality and then helps to reduce the sampling time and cost for reagent used prior to analyses. |
| first_indexed | 2025-11-15T08:35:50Z |
| format | Article |
| id | upm-23397 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T08:35:50Z |
| publishDate | 2011 |
| publisher | IDOSI Publications |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-233972020-06-02T03:59:52Z http://psasir.upm.edu.my/id/eprint/23397/ River water quality modeling using combined principle component analysis (PCA) and multiple linear regressions (MLR): a case study at Klang River, Malaysia Mohd Nasir, Mohd Fahmi Samsudin, Mohd Saiful Mohamad, Isahak Awaluddin, Mohammad Roshide Amir Mansor, Muhd Ariffin Juahir, Hafizan Ramli, Norlafifah A collective set of data over five years (2003 to 2007) in Klang River, Selangor were studied in attempt to assess and determine the contributions of sources affecting the water quality. A precise technique of multiple linear regressions (MLR) were prepare as an advance tool for surface water modeling and forecasting. Likewise, principle component analysis (PCA) was used to simplify and understand the complex relationship among water quality parameters. Nine principle components were found responsible for the data structure provisionally named as soil erosion, anthropogenic input, surface runoff, fecal waste, detergent, urban domestic waste, industrial effluent, fertilizer waste and residential waste explains 72% of the total variance for all the data sets. Meanwhile, urban domestic pollution accounted as the highest pollution contributor to the Klang River. Thus, the advancement of receptor model was applied in order to identify the major sources of pollutant at Klang River. Result showed that the use of PCA as inputs improved the MLR model prediction by reducing their complexity and eliminating data collinearity where R2 value in this study is 0.75 and the model indicates that 75% variability of WQI explained by the five independent variables used in the model. This assessment presents the importance and advantages poses by multivariate statistical analysis of large and complex databases in order to get improved information about the water quality and then helps to reduce the sampling time and cost for reagent used prior to analyses. IDOSI Publications 2011 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/23397/1/23397.pdf Mohd Nasir, Mohd Fahmi and Samsudin, Mohd Saiful and Mohamad, Isahak and Awaluddin, Mohammad Roshide Amir and Mansor, Muhd Ariffin and Juahir, Hafizan and Ramli, Norlafifah (2011) River water quality modeling using combined principle component analysis (PCA) and multiple linear regressions (MLR): a case study at Klang River, Malaysia. World Applied Sciences Journal, 14. pp. 73-82. ISSN 1818-4952; ESSN: 1991-6426 https://www.idosi.org/wasj/wasj14(UPM)2011.htm |
| spellingShingle | Mohd Nasir, Mohd Fahmi Samsudin, Mohd Saiful Mohamad, Isahak Awaluddin, Mohammad Roshide Amir Mansor, Muhd Ariffin Juahir, Hafizan Ramli, Norlafifah River water quality modeling using combined principle component analysis (PCA) and multiple linear regressions (MLR): a case study at Klang River, Malaysia |
| title | River water quality modeling using combined principle component analysis (PCA) and multiple linear regressions (MLR): a case study at Klang River, Malaysia |
| title_full | River water quality modeling using combined principle component analysis (PCA) and multiple linear regressions (MLR): a case study at Klang River, Malaysia |
| title_fullStr | River water quality modeling using combined principle component analysis (PCA) and multiple linear regressions (MLR): a case study at Klang River, Malaysia |
| title_full_unstemmed | River water quality modeling using combined principle component analysis (PCA) and multiple linear regressions (MLR): a case study at Klang River, Malaysia |
| title_short | River water quality modeling using combined principle component analysis (PCA) and multiple linear regressions (MLR): a case study at Klang River, Malaysia |
| title_sort | river water quality modeling using combined principle component analysis (pca) and multiple linear regressions (mlr): a case study at klang river, malaysia |
| url | http://psasir.upm.edu.my/id/eprint/23397/ http://psasir.upm.edu.my/id/eprint/23397/ http://psasir.upm.edu.my/id/eprint/23397/1/23397.pdf |