The influence of environmental variables on the abundance of aquatic insects: a comparison of ordination and artificial neural networks

Two methods to predict the abundance of the mayflies Baetis rhodani and Bae tis vernus (Insecta, Ephemeroptera) in the Breitenbach (Central Germany), b ased on a long-term data set of species and environmental variables were co mpared. Statistic methods and canonical correspondence analysis (CCA) attri buted abundance of emerged insects to a specific discharge pattern during t heir larval development. However, prediction (specimens per year) is limite d to magnitudes of thousands of specimens (which is outside 25% of the mean ). The application of artificial neural networks (ANN) with various methods of variable pre-selection increased the precision of the prediction. Altho ugh more than one appropriate pre-processing method or artificial neural ne tworks was found, R-2 for the best abundance prediction was 0.62 for B. rho dani and 0.71 for B. vernus.