Please login first
Prediction of phytoplankton biomass in small rivers of Central Spain by data mining method of Partial Least-Squares Regression
* 1 , 1 , 1 , 2
1  Centro de Investigación y Desarrollo Tecnológico del Agua (CIDTA) Universidad de Salamanca; Campus Miguel de Unamuno Facultad de Farmacia s/n Salamanca (Spain)
2  Instituto Politécnico Nacional, CIIDIR–Unidad Durango. Sigma 119, Fracc. 20 de Nov. II. 34220. Durango, Dgo., México



The Water Framework Directive (WFD, EC, 2000) states that the "good" ecological status of natural water bodies must be based on the chemical and biological features, compared to the reference conditions. To fulfill the protection of surface waters established in the Water Framework Directive is necessary to monitor the ecological and chemical status of waters quality, especially under drastic conditions of floods or droughts, due to the greater epidemiological risks that occur during these periods.

Phytoplankton is one of the five groups suggested for the assessment of the ecological condition of surface waters under the Water Framework Directive. Phytoplankton is considered a good environmental bioindicator and the spatio-temporal variability in the of phytoplankton communities structures plays an important role in the composition and function of aquatic ecosystems. Although Climate Change has a strong impact on phytoplankton communities and water quality, the development of robust techniques to predict and control phytoplankton growth is still in progress.

The aim of this study is to analyze the impact of the different stressors associated with the change in phytoplanktonic communities in small rivers in the center of the Iberian Peninsula. An statistical study on the identification of the limiting variables in the phytoplankton growth and its seasonal variation by Climate Change was carried out. In this study, a method based on the partial least-squares regression technique (PLS) have been used to predict the concentration of phytoplankton and cyanophytes from 22 variables usually monitored in rivers. The predictive models have shown a good agreement using training data sets. The models were useful to reveal differences between rivers and seasons (dry and wet). The phytoplankton biomass of rivers in dry periods showed greatest similarities, being these dry periods the most important factor in the phytoplankton proliferation.

Keywords: phytoplankton, Climate Change, Prediction, Partial Least Squares Regression