Title: | Water quality assessment with emphasis in parameter optimisation using pattern recognition methods and genetic algorithm |
Other Titles: | |
Authors: | Sotomayor Valarezo, Gonzalo Patricio Hampel , Henrietta Vazquez Zambrano, Raul Fernando |
metadata.dc.ucuenca.correspondencia: | Sotomayor Valarezo, Gonzalo Patricio, gonpa83@yahoo.com |
Keywords: | Water quality Pattern recognition Genetic algorithm Land cover |
metadata.dc.ucuenca.areaconocimientofrascatiamplio: | 1. Ciencias Naturales y Exactas |
metadata.dc.ucuenca.areaconocimientofrascatidetallado: | 1.5.10 Recursos Hídricos |
metadata.dc.ucuenca.areaconocimientofrascatiespecifico: | 1.5 Ciencias de la Tierra y el Ambiente |
metadata.dc.ucuenca.areaconocimientounescoamplio: | 05 - Ciencias Físicas, Ciencias Naturales, Matemáticas y Estadísticas |
metadata.dc.ucuenca.areaconocimientounescodetallado: | 0521 - Ciencias Ambientales |
metadata.dc.ucuenca.areaconocimientounescoespecifico: | 052 - Medio Ambiente |
Issue Date: | 2017 |
metadata.dc.ucuenca.embargoend: | 30-Dec-2050 |
metadata.dc.ucuenca.volumen: | volumen 130 |
metadata.dc.source: | Water Research |
metadata.dc.identifier.doi: | https://doi.org/10.1016/j.watres.2017.12.010 |
metadata.dc.type: | ARTÍCULO |
Abstract: | A non-supervised (k-means) and a supervised (k-Nearest Neighbour in combination with genetic algorithm optimisation, k-NN/GA) pattern recognition algorithms were applied for evaluating and interpreting a large complex matrix of water quality (WQ) data collected during five years (2008, 2010e2013) in the Paute river basin (southern Ecuador). 21 physical, chemical and microbiological parameters collected at 80 different WQ sampling stations were examined. At first, the k-means algorithm was carried out to identify classes of sampling stations regarding their associated WQ status by considering three internal validation indexes, i.e., Silhouette coefficient, Davies-Bouldin and Cali nski-Harabasz. As a result, two WQ classes were identified, representing low (C1) and high (C2) pollution. The k-NN/GA algorithm was applied on the available data to construct a classification model with the two WQ classes, previously defined by the k-means algorithm, as the dependent variables and the 21 physical, chemical and microbiological parameters being the independent ones. This algorithm led to a significant reduction of the multidimensional space of independent variables to only nine, which are likely to explain most of the structure of the two identified WQ classes. These parameters are, namely, electric conductivity, faecal coliforms, dissolved oxygen, chlorides, total hardness, nitrate, total alkalinity, biochemical oxygen demand and turbidity. Further, the land use cover of the study basin revealed a very good agreement with the WQ spatial distribution suggested by the k-means algorithm, confirming the credibility of the main results of the used WQ data mining approach. |
Description: | A non-supervised (k-means) and a supervised (k-Nearest Neighbour in combination with genetic algorithm optimisation, k-NN/GA) pattern recognition algorithms were applied for evaluating and interpreting a large complex matrix of water quality (WQ) data collected during five years (2008, 2010e2013) in the Paute river basin (southern Ecuador). 21 physical, chemical and microbiological parameters collected at 80 different WQ sampling stations were examined. At first, the k-means algorithm was carried out to identify classes of sampling stations regarding their associated WQ status by considering three internal validation indexes, i.e., Silhouette coefficient, Davies-Bouldin and Cali nski-Harabasz. As a result, two WQ classes were identified, representing low (C1) and high (C2) pollution. The k-NN/GA algorithm was applied on the available data to construct a classification model with the two WQ classes, previously defined by the k-means algorithm, as the dependent variables and the 21 physical, chemical and microbiological parameters being the independent ones. This algorithm led to a significant reduction of the multidimensional space of independent variables to only nine, which are likely to explain most of the structure of the two identified WQ classes. These parameters are, namely, electric conductivity, faecal coliforms, dissolved oxygen, chlorides, total hardness, nitrate, total alkalinity, biochemical oxygen demand and turbidity. Further, the land use cover of the study basin revealed a very good agreement with the WQ spatial distribution suggested by the k-means algorithm, confirming the credibility of the main results of the used WQ data mining approach. |
URI: | https://www.sciencedirect.com/science/article/pii/S0043135417310059?via%3Dihub |
metadata.dc.ucuenca.urifuente: | www.sciencedirect.com/journal/water-research |
ISSN: | 00431354 |
Appears in Collections: | Artículos
|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.