Relating nutrient ratios to mucilage events in Northern Adriatic
Keywords:
Northern Adriatic mucilage, nutrient ratios, machine learning, regression treesAbstract
The north western part of the northern Adriaticexhibits eutrophic to mesotrophic characteristicswith recurrent algal blooms and quiteunpredictable mucilage events. To contribute to theunderstanding of the mucilage events in thenorthern Adriatic, a machine learning algorithmfor induction of regression trees was applied to adata set comprising physical and chemicalparameters, measured at six stations on the profilefrom the Po River delta (Italy) to Rovinj on thewestern Istrian coast (Croatia). A modeldescribing the connection between the TIN/PO 4ratio, considered as a necessary factor andsometimes even a trigger for mucilage events, andthe environmental conditions in northern Adriaticwas elaborated. The model for TIN/PO 4 ratioconfirmed the assumption that the mucilage eventsare connected with the changes of this ratio in thesystem. This indicates that at certain levels of Plimitation (TIN/PO 4 signal indicate) mucilageevent frequency increases. The model also revealswhich triggers are responsible (salinity andtemperature) for the changes of the TIN/PO 4 ratioas well as their threshold values. As contrasted toto the TIN/PO 4 ratio, the mucilage events could notbe attributed to the TIN/SiO 4 ratio.Downloads
Published
2013-09-13
Issue
Section
Articles
License
Copyright 2022 by Faculty of Engineering University of Rijeka, Faculty of Civil Engineering University of Rijeka. All rights reserved. This material may not be reproduced or copied, in whole or in part, in any printed, mechanical, electronic, film, or other distribution and storage media without the written consent of the publisher.
The journal Engineering Review’s publishing procedure is performed in accordance with the publishing ethics statements, defined within the Publishing Ethics Resource Kit. The Ethics statement is available in the document Ethics Policies.