Application of artificial neural network models to analyse the relationships between Gammarus pulex L. (Crustacea, Amphipoda) and river characteristics.

This study aimed at analysing the relationship between river characteristics and abundance of Gammarus pulex. To this end, four methods which can identify the relative contribution and/or the contribution profile of the input variables in neural networks describing the habitat preferences of this species were compared: (i) the "PaD" ("Partial Derivatives") method consists of a calculation of the partial derivatives of the output in relation to the input variables; (ii) the "Weights" method is a computation using the connection weights of the backpropagation Artificial Neural Networks; (iii) the "Perturb" method analyses the effect of a perturbation of the input variables on the output variable; (iv) the "Profile" method is a successive variation of one input variable while the others are kept constant at a fixed set of values. The dataset consisted of 179 samples, collected over a three-year period in the Zwalm river basin in Flanders, Belgium. Twenty-four environmental variables as well as the log-transformed abundance of Gammarus pulex were used in this study. The different contribution methods gave similar results concerning the order of importance of the input variables. Moreover, the stability of the methods was confirmed by gradually removing variables. Only in a limited number of cases a shift in the relative importance of the remaining input variables could be observed. Nevertheless, differences in sensitivity and stability of the methods were detected, probably as a result of the different calculation procedures. In this respect, the "PaD" method made a more severe discrimination between minor and major contributing environmental variables in comparison to the "Weights", "Profile" and "Perturb" methods. From an ecological point of view, the input variables "Ammonium" and to a smaller extent "COD", were selected by these methods as dominant river characteristics for the prediction of the abundance of Gammarus pulex in this study area.

Overview and quantification of the factors affecting the upstream and downstream movements of Gammarus pulex (Amphipoda).

Human activities have severely deteriorated the Flemish river systems, and many functions such as drinking water supply, fishing, ... are threatened. Because their restoration entails drastic social (e.g. change in habits with regard to water use and discharge, urban planning) and economical (e.g. investment in nature restoration, wastewater treatment system installation) consequences, the decisions should be taken with enough forethought. Ecosystem models can act as interesting tools to support decision-making in river restoration management. In particular models that can predict the habitat requirements of organisms are of considerable importance to ensure that the planned actions have the desired effects on the aquatic ecosystems. In preliminary studies, Artificial Neural Network (ANN) models were tested and optimized to obtain the best model configuration for the prediction of the habitat suitability for Gammarus pulex based on the abiotic characteristics of their aquatic environment in the Zwalm river basin (Flanders, Belgium). Although, these ANN models are in general quite robust with a rather high predictive reliability, the model performance has to be increased with regard to simulations for river restoration management. In particular, spatial-temporal expert-rules have to be included. Migration kinetics (downstream drift and upstream migration) of the organism and migration barriers along the river (weirs, impounded river sections, ...) can deliver important additional information on the effectiveness of the restoration plans, and also on the timing of the expected effects. This paper presents an overview and quantification of the factors affecting the upstream and downstream movements of Gammarus pulex. During further research, ANN models will be used to predict the habitat suitability for Gammarus pulex after several restoration options. The migration models, implemented in a Geographical Information System (GIS), are applied to calculate the migration time to the restored parts of the river. In this way, decision makers have an idea whether and when a selected restoration option has the desired effect.

Comparison of Artificial Neural Network (ANN) Model Development Methods for Prediction of Macroinvertebrate Communities in the Zwalm River Basin in Flanders, Belgium.

Modelling has become an interesting tool to support decision making in water management. River ecosystem modelling methods have improved substantially during recent years. New concepts, such as artificial neural networks, fuzzy logic, evolutionary algorithms, chaos and fractals, cellular automata, etc., are being more commonly used to analyse ecosystem databases and to make predictions for river management purposes. In this context, artificial neural networks were applied to predict macroinvertebrate communities in the Zwalm River basin (Flanders, Belgium). Structural characteristics (meandering, substrate type, flow velocity) and physical and chemical variables (dissolved oxygen, pH) were used as predictive variables to predict the presence or absence of macroinvertebrate taxa in the headwaters and brooks of the Zwalm River basin. Special interest was paid to the frequency of occurrence of the taxa as well as the selection of the predictors and variables to be predicted on the prediction reliability of the developed models. Sensitivity analyses allowed us to study the impact of the predictive variables on the prediction of presence or absence of macroinvertebrate taxa and to define which variables are the most influential in determining the neural network outputs.