Modeling eutrophication and risk prevention in a reservoir in the Northwest of Spain by using multivariate adaptive regression splines analysis

• Published in: Ecological engineering Vol. 68; pp. 80 - 89
• Main Authors: ALONSO FERNANDEZ, J. R, GARCIA, P. J, DIAZ MUNIZ, C, ALVAREZ ANTON, J. C
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01-07-2014; Elsevier
• Subjects: Animal, plant and microbial ecology; Biological; Biological and medical sciences; Chlorophyll; Chlorophylls; Eutrophication; Evolution; Fundamental and applied biological sciences. Psychology; General aspects. Techniques; Mathematical models; Methods and techniques (sampling, tagging, trapping, modelling...); Multivariate adaptive regression splines (MARS); Regression; Regression analysis; Reservoirs; Splines; Statistical learning techniques; Southern Europe; Europe; Spain; Spain, Asturias; ANE, Spain; Chlorophyll; Statistical learning techniques; Multivariate adaptive regression splines (MARS); Regression analysis; Eutrophication; Statistical character; Risk; Reservoir; Multivariate analysis; Modeling; Environmental engineering; Learning; Statistical method; Prevention
• ISSN: 0925-8574; 1872-6992
• DOI: 10.1016/j.ecoleng.2014.03.094

•A MARS model is built as a predictive model of chlorophyll presence.•Eutrophication is dangerous for environment in fresh waters.•Biological and physical–chemical variables in this process are studied in depth.•The obtained correlation coefficient is equal to 0.99.•The results show that the MARS model can assist in the diagnosis of eutrophication.
The aim of this study was to obtain a predictive model able to perform an early detection of eutrophication using as predictors the chlorophyll concentration of the previous days. In this research work, the evolution of chlorophyll in the Trasona reservoir (Principality of Asturias, Northern Spain) was studied with success using the data mining methodology based on multivariate adaptive regression splines (MARS) technique. For this purpose, some biological parameters (phytoplankton species expressed in biovolume) in addition to the most important physical–chemical parameters are considered. The results of the present study are two-fold. In the first place, the significance of each biological and physical–chemical variables on the eutrophication in the reservoir is presented through the model. Secondly, a model for forecasting eutrophication is obtained. The agreement between experimental data and the model confirmed the good performance of the latter. Finally, conclusions of this innovative research work are exposed.