A comparison of self-organizing map algorithm and some conventional statistical methods for ecological community ordination

In order to summarise the structure of ecological communities some ordination techniques are well known and widely-used, (e.g. Principal Component Analysis (PCA), Correspondence Analysis (CoA). Inspired by the structure and the mechanism of the human brain, the Artificial Neural Networks should be a convenient alternative tool to traditional statistical methods. The Kohonen Self-Organizing Map (SOM) is one of the most well-known neural network with unsupervised learning rules; it performs a topology-preserving projection of the data space onto a regular two-dimensional space. Its achievement has already been demonstrated in various areas, but this approach is not yet widely known and used by ecologists. The present work describes how SOM can be used for the study of ecological communities. After the presentation of SOM adapted to ecological data, SOM was trained on popular example data; upland forest in Wisconsin (USA). The SOM results were compared with classical statistical techniques. Similarity between the results may be observed and constitutes a validation of the SOM method. SOM algorithm seems fully usable in ecology, it can perfectly complete classical techniques for exploring data and for achieving community ordination.