Modeling of the algal atypical increase in La Barca reservoir using the DE optimized least square support vector machine approach with feature selection

P.J. García-Nieto, E. García-Gonzalo, J.R. Alonso Fernández and C. Díaz Muñiz

Mathematics and Computers in Simulation (MATCOM), 2019, vol. 166, issue C, 461-480

Abstract: Algal atypical increase is a consequence of water fertilization (also called eutrophication) and a worldwide environmental concern since water quality and its uses are seriously compromised. The effects of this abnormal proliferation are varied. Among them, and the most direct one is the increase of Chlorophyll a (Chl-a) concentration. Prevention is the most effective measure given that once the algal proliferation starts it is too difficult and costly to stop the process and thus, prediction is essential. A new hybrid algorithm that combines least square support vector machines (LS-SVM) with a radial basis function (RBF) kernel and differential evolution (DE) optimization technique to estimate the algal abnormal proliferation from physical–chemical and biological variables has been constructed here. This technique involves the optimization of the LS-SVM hyperparameters during the training process. Additionally, we have carried out a variable (feature) selection of the model using backward and forward selection processes with success and from this optimized model, the relative importance of the variables was estimated. For comparison purposes, binary PSO and SA were also used in feature selection. Thus, apart from successfully forecasting algal atypical growth (coefficients of determination 0.90 and 0.95 for the Chlorophyll and Total Phosphorus, respectively), the model showed here can establish the significance of each biological and physical–chemical parameter of the algal enhanced growth.

Keywords: Least square support vector machines (LS-SVM); Differential evolution (DE); Algal abnormal productivity in reservoirs; Feature selection; Regression analysis (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0378475419302265
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:matcom:v:166:y:2019:i:c:p:461-480

DOI: 10.1016/j.matcom.2019.07.011

Access Statistics for this article

Mathematics and Computers in Simulation (MATCOM) is currently edited by Robert Beauwens

More articles in Mathematics and Computers in Simulation (MATCOM) from Elsevier
Bibliographic data for series maintained by Catherine Liu ().