Development and evaluation of an innovative Enhanced River Pollution Index model for holistic monitoring and management of river water quality
Autor: | Suyog Gupta, Sunil Kumar Gupta |
---|---|
Rok vydání: | 2020 |
Předmět: |
Coefficient of determination
Index (economics) Mean squared error Health Toxicology and Mutagenesis Water Pollution Mean absolute error Conventional treatment General Medicine 010501 environmental sciences 01 natural sciences Pollution River water Rivers Water Quality Linear regression Statistics Multivariate Analysis Linear Models Environmental Chemistry River pollution 0105 earth and related environmental sciences Mathematics Environmental Monitoring |
Zdroj: | Environmental science and pollution research international. 28(21) |
ISSN: | 1614-7499 |
Popis: | The present study was conceptualized to develop the Enhanced River Pollution Index (ERPI) model. The ERPI model was used to evaluate the river water quality (RWQ) for its beneficial usage, i.e., drinking with (DCD) and without (DD) conventional treatment, outdoor-bathing (OB), wildlife and fisheries (WF), and industrial and irrigation (IIW). The adequacy of multiple linear regression (MLR) and support vector regression (SVR) models was also investigated to predict the ERPI for estimating the RWQ. The accuracy of the MLR and SVR models was tested by using the statistical parameters, i.e., root mean squared error (RMSE), coefficient of determination (R2), and mean absolute error (MAE). The results revealed that the MLR models performed well (RMSE = 0.004 ± 0.0043, R2 = 0.998 ± 0.001, and MAE = 0.002 ± 0.003) for the DD, DCD, and OB. However, the SVR models estimated the RWQ more accurately (RMSE = 0.041 ± 0.001, R2 = 0.962 ± 0.010, and MAE = 0.026 ± 0.002) than the MLR models for WF and IIW. Moreover, this study disclosed that the RWQ was not excellent for DD, OB, and DCD. However, the RWQ was categorized from excellent to poor classes for WF, while it was suitable for IIW. |
Databáze: | OpenAIRE |
Externí odkaz: |