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.
Acknowledgements
We thank Julie Gueguen and Isabelle Lavoie for testing the package on their data and giving helpful remarks. We would like to acknowledge all the French regional agencies for the environment, DRIEE and DREAL, and the French water agencies for sending data. We are grateful to two anonymous reviewers for their suggestions which substantially improved the manuscript.