SOM clustering of 21-year data of a small pristine boreal lake
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 Fi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2017-01-01
|
| Series: | Knowledge and Management of Aquatic Ecosystems |
| Subjects: | |
| Online Access: | https://doi.org/10.1051/kmae/2017027 |
| _version_ | 1818152914629165056 |
|---|---|
| author | Voutilainen Ari Arvola Lauri |
| author_facet | Voutilainen Ari Arvola Lauri |
| author_sort | Voutilainen Ari |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-11T14:02:17Z |
| format | Article |
| id | doaj.art-7bf56d7821744cb685b3c1483f0c60a7 |
| institution | Directory Open Access Journal |
| issn | 1961-9502 |
| language | English |
| last_indexed | 2024-12-11T14:02:17Z |
| publishDate | 2017-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | Knowledge and Management of Aquatic Ecosystems |
| spelling | doaj.art-7bf56d7821744cb685b3c1483f0c60a72022-12-22T01:03:49ZengEDP SciencesKnowledge and Management of Aquatic Ecosystems1961-95022017-01-0104183610.1051/kmae/2017027kmae170041SOM clustering of 21-year data of a small pristine boreal lakeVoutilainen AriArvola LauriIn 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.https://doi.org/10.1051/kmae/2017027boreal lakedata partitioningecological complexitylong-term dataself-organizing map |
| spellingShingle | Voutilainen Ari Arvola Lauri SOM clustering of 21-year data of a small pristine boreal lake Knowledge and Management of Aquatic Ecosystems boreal lake data partitioning ecological complexity long-term data self-organizing map |
| title | SOM clustering of 21-year data of a small pristine boreal lake |
| title_full | SOM clustering of 21-year data of a small pristine boreal lake |
| title_fullStr | SOM clustering of 21-year data of a small pristine boreal lake |
| title_full_unstemmed | SOM clustering of 21-year data of a small pristine boreal lake |
| title_short | SOM clustering of 21-year data of a small pristine boreal lake |
| title_sort | som clustering of 21 year data of a small pristine boreal lake |
| topic | boreal lake data partitioning ecological complexity long-term data self-organizing map |
| url | https://doi.org/10.1051/kmae/2017027 |
| work_keys_str_mv | AT voutilainenari somclusteringof21yeardataofasmallpristineboreallake AT arvolalauri somclusteringof21yeardataofasmallpristineboreallake |