DiatSOM: A R-package for diatom biotypology using self-organizing maps

Marius Bottin, Jean Luc Giraudel, Sovan Lek, Juliette Tison-Rosebery

Research output: Contribution to journalArticlepeer-review

9 Scopus citations

Abstract

Owing to the high complexity of diatom community data, there is a special need for methods accounting for complex non-linear gradients. A Kohonen's self-organizing map (SOM) is a neural network with unsupervised learning. It allows both unbiased classification of the communities and visualization of biological gradients on a two-dimensional plane. However, as with other neural networks, many parameters must be set. A new R-package with a SOM parameterization specifically suited to diatom communities has been developed. Further developments will consist of creating a graphical user interface in order to make this method easier to use for the scientific community.

Original languageEnglish (US)
Pages (from-to)5-9
Number of pages5
JournalDiatom Research
Volume29
Issue number1
DOIs
StatePublished - Jan 2 2014
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Aquatic Science

Fingerprint Dive into the research topics of 'DiatSOM: A R-package for diatom biotypology using self-organizing maps'. Together they form a unique fingerprint.

Cite this