J.L. Giraudel

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.

Utilisation of non-supervised neural networks and principal component analysis to study fish assemblages

Kohonen self-organizing maps (SOM) belong to the non-supervised artificial neural network modelling methods. It typically displays a high dimensional data set in a lower dimensional space. In this way, that method can be considered as a non-linear surrogate to the principal component analysis (PCA). In order to test the efficiency of SOM on complex ecological data gathered in the natural environment, we made a comparison between PCA and SOM capabilities to analyse the spatial occupancy of several European freshwater fish species in the littoral zone of a large French lake. The same data matrix consisting of 710 samples and 15 species was analysed using PCA and SOM. Both methods provided insights on the major trends in fish spatial occupancy. However, a more detailed analysis showed that only SOM was able to reliably visualise the entire fish assemblage in a two dimensional space (i.e. both dominant and scarce species). On the contrary PCA provided irrelevant ecological information for some species. These drawbacks were afforded to data heterogeneity, scarce species being poorly represented on the PCA plane. These results led us to conclude that SOM constitute a more reliable data representation method than PCA when complex ecological data sets are used.

Spatial analysis of stream invertebrates distribution in the Adour-Garonne drainage basin (France), using Kohonen self organizing maps

We analysed the regional distribution of 283 lotic macroinvertebrate species from four insect orders (Ephemeroptera, Plecoptera, Trichoptera, Coleoptera =EPTC) in the Adour-Garonne drainage basin (South–Western France, surface =116 000 km 2 ). The aim of this work was to provide a stream classification based on characteristic species assemblages. The faunistic data corresponded to the occurrence (presence or absence) of 283 species at 252 sampling sites. These data were computed with the Kohonen self organised map algorithm (SOM) (Kohonen, Self-Organizing Maps, volume30 of Springer Series in Information Sciences. Springer, Berlin, Heidelberg. (Second Extended Edition 1997)). This neural network algorithm has already been successfully used in ecology (Giraudel et al., Artificial neural networks, applications to ecology and evolution. Springer-Verlag, (in press); Chon et al., Ecol. Model., 90, 1996, 69–78) for communities patternizing. SOM enable visualisation of the complex species assemblage in a two-dimensional space, preserving the topology of the input data. Then, using the U-matrix method, it was possible to classify the data without prior knowledge. Four major EPTC regions were characterised within the

Application of the Self-Organizing Mapping and Fuzzy Clustering to Microsatellite Data: How to Detect Genetic Structure in Brown Trout (Salmo trutta) Populations

Artificial Neuronal Networks (ANNs) are now currently used for various purposes, from physical and chemical studies to biological ones. Even if they are less used in ecology and populations genetics, recent studies have shown that they can be very efficient for such problems (Cornuet et al. 1996; Foody 1997; Mastrorillo et al. 1997; Guegan et al. 1998). ANNs have several advantages: they can be applied to various data, from environmental variables to genotypes, and are usually more efficient than classical statistical techniques (FDA, for example; see Cornuet et al. 1996). In order to classify biological objects (individuals or populations, for example) using ANNs, two main types of methods can be applied: supervised and unsupervised learning. Supervised learning can be applied to the classification of individuals of unknown origin among already well-defined groups: This has been successfully applied to genetic data on bees (Conuet et al. 1996, with some phylogenetically well separated lineages), and on trout(Aurelle et al. 1998, but with some less clearly differentiated groups).

Use of unsupervised neural networks for ecoregional zoning of hydrosystems through diatom communities: case study of Adour-Garonne watershed (France)

Knowing that diatoms are good indicators of stream ecological conditions, the aim of our research program was to test on a pilot data-set the interest and efficiency of using a Self-Organizing Map (SOM) as an ordination technique to determine and to classify types of river ecosystems. Such neural networks have already been successfully used for other aquatic communities patterning. Diatoms, waterchemistry and stream morpho-dynamical parameters were characterised for 49 non impacted sampling stations spread over the Adour-Garonne watershed (South-Western France). Combining the SOM to the Structuring Index we selected in a second step the most relevant species (called structuring species) influencing this typology. In this way, three main homogeneous regions were characterised, as regards to diatom communities and abiotic parameters, allowing us to meet the Water Framework Directive requirements concerning stream ecoregional classification.

Neuronal Networks: Algorithms and Architectures for Ecologists and Evolutionary Ecologists

In ecological research, the processing and interpretation of data play an important role. The ecologist disposes of many methods, ranging from numerical, mathematical, and statistical methods to techniques originating from artificial intelligence (Ackley et al. 1985) like expert systems (Bradshaw et al. 1991; Recknagel et al. 1994), genetic algorithms (d’Angelo et al. 1995; Golikov et al. 1995) and artificial neuronal networks, i.e. ANN (Colasanti 1991; Edwards and Morse 1995).

A non-destructive morphometric technique to predict Ligula intestinalis L. plerocercoid load in roach (Rutilus rutilus L.) abdominal cavity

The aim of the present work was to propose a model for the estimation of the endoparasitic load using morphological descriptors easily accessible without killing the animal i.e. non-destructive method. The study was conducted using plerocercoid forms of Ligula intestinalis in its second intermediate host, the roach (Rutilus rutilus). The Kohonen Self-Organizing Map (non-supervised neural network) made it possible to present the complex data matrix in a two-dimensional space, with individual clusters visualised by the U-matrix method. The six main descriptors were selected and used to build the predictive model, four lateral and two thickness measures. The generalisation ability of the backpropagation algorithm (supervised neural network) is confirmed by a determination coefficient higher than 0.90 between observed and predicted values. The study for the first partial derivatives of the parasitic load with respect to the six morphological variables is used to identify the factors influencing the parasitic load and the mode of action of each factor.