Use of Genetic Algorithms to select Input Variables in Artificial Neural Network Models for the Prediction of Benthic Macroinvertebrates

The first consideration in predictive ecological modelling is the selection of appropriate input variables. Numerous variables can however be involved and most of them cannot be omitted without a significant loss of information. The collection of field data on the other hand is both time-consuming and expensive. Therefore, rigorous methods are needed to detect which variables are essential and those which are not. Appropriate selection of input variables is not only important for modelling objectives as such, but also to ensure reliable decision-support in river management and policy-making. In this paper, the use of genetic algorithms is explored to automatically select the relevant input variables for artificial neural networks (ANNs), predicting the presence or absence of benthic macroinvertebrate taxa. The applied database consisted of measurements from 360 sites in unnavigable watercourses in Flanders (Belgium). The measured variables are a combination of physical-chemical, eco-toxicological and structural ones. The predictive power of the ANNs was assessed on the basis of the number of Correctly Classified Instances (CCI). The selected genetic algorithm introduced different sets of input variable to the ANN models and compared their predictive power to select the optimal combination of input variables. With this technique, the number of input variables could be reduced from 17 to 5-11. In addition, the prediction success increased with maximum 5 percent. By means of this technique, the key variables that determine the presence or absence of benthic macroinvertebrate taxa in Flanders could also be identified.