Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6301889 | Ecological Engineering | 2014 | 9 Pages |
Abstract
Water quality controls involve mainly a large number of measurements of chemical and physical-chemical variables. In this sense, turbidity is shown as a key variable in water quality control because it is an integrative parameter. Consequently, the aim of this work is focused on this main parameter and how it is been influenced by other water quality parameters in order to simplify water quality controls since they are expensive and time consuming. Taking into account that support vector machines (SVMs) have been used in a wide range of biological problems with promising results, this paper proposes a practical new hybrid model for long-term turbidity values forecasting based on SVMs in combination with the particle swarm optimization (PSO) technique. This optimization technique involves kernel parameter setting in the SVM training procedure, which significantly influences the regression accuracy. Bearing this in mind, turbidity values have been predicted here by using the hybrid PSO-SVM-based model from the remaining measured water quality parameters (input variables) in the Nalón river basin (Northern Spain) with success. The agreement of the PSO-SVM-based model with experimental data confirmed the good performance of this model. Finally, the main conclusions of this study are exposed.
Keywords
Related Topics
Life Sciences
Agricultural and Biological Sciences
Ecology, Evolution, Behavior and Systematics
Authors
P.J. GarcÃa Nieto, E. GarcÃa-Gonzalo, J.R. Alonso Fernández, C. DÃaz Muñiz,