Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Self-organizing maps: a tool to study element distribution in headwater streams
Luleå University of Technology, Department of Civil, Environmental and Natural Resources Engineering, Geosciences and Environmental Engineering.
2018 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Headwater streams are ubiquitous in watercourse systems and their importance for water quality in streams of higher orders is well-known. Yet, element compositions of headwaters are seldom systematically investigated. This study reports data from 104 headwaters in forested catchments in southeastern Sweden sampled at three occasions. Multielement analyses are common practice nowadays, however, vast amounts of data points cannot easily be grasped by the human eye. Therefore, Kohonen’s self-organizing map (SOM) technique, i.e. an unsupervised neural network technique, served as visualization tool to simplify and interpret the large data set here (> 10,000 data points). Similarity index plots were used to reveal that the partially high seasonal variations in total element concentrations were caused by a shift in redox conditions in the overall system. The plots further showed that the included parameters (elements, background parameters, catchment parameters) had different associations to each other under oxic and anoxic conditions. This study clearly demonstrates that SOMs allow to quickly gain a general impression of system properties, which bears a great potential to facilitate decisions about further detailed studies when dealing with multivariate data sets in stream water research.

Place, publisher, year, edition, pages
2018. , p. 67
Keywords [en]
headwater streams, boreonemoral catchments, redox conditions, self-organizing maps, data visualization
National Category
Geochemistry
Identifiers
URN: urn:nbn:se:ltu:diva-69154OAI: oai:DiVA.org:ltu-69154DiVA, id: diva2:1214353
Educational program
Geosciences, master's level (120 credits)
Supervisors
Examiners
Available from: 2018-06-29 Created: 2018-06-06 Last updated: 2018-06-29Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
Geosciences and Environmental Engineering
Geochemistry

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 21 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf