Hybrid modelling based on support vector regression with genetic algorithms in forecasting the cyanotoxins presence in the Trasona reservoir (Northern Spain)

• Published in: Environmental research Vol. 122; pp. 1 - 10
• Main Authors: García Nieto, P.J., Alonso Fernández, J.R., de Cos Juez, F.J., Sánchez Lasheras, F., Díaz Muñiz, C.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01.04.2013; Elsevier
• Subjects: algorithms; Bacterial Toxins - analysis; Bacteriology; Biological; Biological and medical sciences; Cyanobacteria; cyanobacterial toxins; Cyanotoxins; drinking; Forecasting; Fundamental and applied biological sciences. Psychology; Genetic algorithms; Genetic algorithms (GAs); Marine Toxins - analysis; Mathematical analysis; Mathematical models; Microbiology; Microcystins - analysis; Pathogenicity, virulence, toxins, bacteriocins, pyrogens, host-bacteria relations, miscellaneous strains; Regression; Regression Analysis; Reservoirs; risk; Spain; Statistical machine learning techniques; Support Vector Machine; Support vector regression (SVR); Vectors (mathematics); Water Microbiology; Water Supply - analysis; Europe; Spain; Support vector regression (SVR); Genetic algorithms (GAs); Statistical machine learning techniques; Cyanobacteria; Cyanotoxins; Hybrid; Regression; Reservoir; Modeling; Forecasting; Learning; Outbreak; Genetic algorithm; Bloom; Bacteria; Biological contamination; Vector
• ISSN: 0013-9351; 1096-0953; 1096-0953
• DOI: 10.1016/j.envres.2013.01.001

Cyanotoxins, a kind of poisonous substances produced by cyanobacteria, are responsible for health risks in drinking and recreational waters. As a result, anticipate its presence is a matter of importance to prevent risks. The aim of this study is to use a hybrid approach based on support vector regression (SVR) in combination with genetic algorithms (GAs), known as a genetic algorithm support vector regression (GA–SVR) model, in forecasting the cyanotoxins presence in the Trasona reservoir (Northern Spain). The GA-SVR approach is aimed at highly nonlinear biological problems with sharp peaks and the tests carried out proved its high performance. Some physical–chemical parameters have been considered along with the biological ones. The results obtained are two-fold. In the first place, the significance of each biological and physical–chemical variable on the cyanotoxins presence in the reservoir is determined with success. Finally, a predictive model able to forecast the possible presence of cyanotoxins in a short term was obtained. ► A hybrid GA–SVR model is built as a predictive model of cyanotoxins presence. ► Cyanobacterial HABs are dangerous for environment and people in fresh waters. ► Biological and physical. ► chemical variables in this process are studied in depth. ► The obtained regression accuracy of our method is 98%. ► The results show that GA–SVR model can assist in the diagnosis of cyanotoxins.