SOM clustering of 21-year data of a small pristine boreal lake

Show simple item record

dc.contributor University of Helsinki, Lammi Biological Station en
dc.contributor.author Voutilainen, Ari
dc.contributor.author Arvola, Lauri Matti Juhani
dc.date.accessioned 2017-09-08T08:51:02Z
dc.date.available 2017-09-08T08:51:02Z
dc.date.issued 2017-08
dc.identifier.citation Voutilainen , A & Arvola , L M J 2017 , ' SOM clustering of 21-year data of a small pristine boreal lake ' , Knowledge and Management of Aquatic Ecosystems , vol. 2017 , no. 418 . https://doi.org/10.1051/kmae/2017027 en
dc.identifier.issn 1961-9502
dc.identifier.other PURE: 88633885
dc.identifier.other PURE UUID: 2103d697-106c-4a35-b6ba-b3b653031cac
dc.identifier.other WOS: 000410533900006
dc.identifier.other Scopus: 85028084476
dc.identifier.uri http://hdl.handle.net/10138/221346
dc.description.abstract In order to improve our understanding of the connections between the biological processes and abiotic factors, we clustered complex long-term ecological data with the self-organizing map (SOM) technique. The available 21-year long (1990–2010) data set from a small pristine humic lake, in southern Finland, consisted of 27 meteorological, physical, chemical, and biological variables. The SOM grouped the data into three categories of which the first one was the largest with 12 variables, including metabolic processes, dissolved oxygen, total nitrogen and phosphorus, chlorophyll a, and taxonomical groups of plankton known to exist in spring. The second cluster comprised of water temperature and precipitation together with cyanobacteria, algae, rotifers, and crustacean zooplankton, an association emphasized with summer. The third cluster was consisted of six physical and chemical variables linked to autumn, and to the effects of inflow and/or water column mixing. SOM is a useful method for grouping the variables of such a large multi-dimensional data set, especially, when the purpose is to draw comprehensive conclusions rather than to search for associations across sporadic variables. Sampling should minimize the number of missing values. Even flexible statistical techniques, such as SOM, are vulnerable to biased results due to incomplete data. en
dc.format.extent 16
dc.language.iso eng
dc.relation.ispartof Knowledge and Management of Aquatic Ecosystems
dc.rights en
dc.subject 1181 Ecology, evolutionary biology en
dc.subject boreal lake en
dc.subject data partitioning en
dc.subject ecological complexity en
dc.subject long-term data en
dc.subject self-organizing map en
dc.title SOM clustering of 21-year data of a small pristine boreal lake en
dc.type Article
dc.description.version Peer reviewed
dc.identifier.doi https://doi.org/10.1051/kmae/2017027
dc.type.uri info:eu-repo/semantics/other
dc.type.uri info:eu-repo/semantics/publishedVersion
dc.contributor.pbl

Files in this item

Total number of downloads: Loading...

Files Size Format View
Voutilainen_Arv ... quat._Ecosyst._418_36..pdf 6.496Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record