Selecting Variables for Habitat Suitability of Asellus (Crustacea, Isopoda) by Applying Input Variable Contribution Methods to Artificial Neural Network Models

Abstract

This study aimed to compare different methods to analyse the contribution of individual river characteristics to predict the abundance of Asellus (Crustacea, Isopoda). Six methods which provide the relative contribution and/or the contribution profile of the input variables of artificial neural network models were therefore compared: (1) the 'partial derivatives' method; (2) the 'weights' method; (3) the 'perturb' method; (4) the 'profile' method; (5) the 'classical stepwise' method; (6) the 'improved stepwise' method. Consequently, the key variables which affect the habitat preferences of Asellus could be identified. To evaluate the performance of the artificial neural network model, the model predictions were compared with the results of a multiple linear regression analysis. The dataset consisted of 179 samples, collected over a 3-year period in the Zwalm catchment in Flanders, Belgium. Twenty-four environmental variables as well as the log-transformed abundance of Asellus were used in this study. The different contribution methods seemed to give similar results concerning the order of importance of the input variables. Nevertheless, their diverse computation led to differences in sensitivity and stability of the methods and the derived outcomes on the habitat preferences. From an ecological point of view, the environmental variables describing the stream type (width, depth, stream order and distance to mouth) were the most significant variables for Asellus in the Zwalm catchment during the period 2000-2002 for all applied methods. Indirectly, one can conclude that the water quality is not the limiting factor for the survival of Asellus in the Zwalm catchment.

Generalized Linear Models to Identify Key Hydromorphological and Chemical Variables Determining the Occurrence of Macroinvertebrates in the Guayas River Basin (Ecuador)

“…Our results proved the ability of GLMs to determine the relative importance of each environmental variable towards the biotic integrity and macroinvertebrate communities in particular, which is an advantage over other techniques, such as ANN [47,52]. However, we also experienced one limitation of using GLMs as compared to other techniques.…”

“…The sensitivity analysis assessed the effect of an explanatory variable towards the response variable under a given situation [50][51][52]. The variables contained in the final models were selected to illustrate the effects of changing their values on the biotic integrity expressed as the BMWP-Col. To do so, other variables included in the models were assumed not to cause restrictions and set constant to their median values.…”

The identification of relationships between selected honey parameters by extracting the contribution of independent variables in a neural network model

“…According to the reports published by other authors, the results' similarity is not the rule. Even if the results obtained using the selected methods are comparable, the percentage influence of input variables on output variables is different for each method [25,26,52]. The phenomenon described above can be observed also in the results presented in this work.…”

A simple fish-based approach to assess the ecological quality of freshwater reservoirs in Central Europe

“…Such advanced modelling may reveal causal relationships for sufficiently large datasets (ter Braak and Verdonschot, 1995) but is usually not applicable to relatively small datasets such as those underlying the CZ-FBI. Instead, simple methods can identify clear patterns in the dataset (Mouton et al, 2010). Expert judgement was also involved in the development of CZ-FBI; this subjective approach is appropriate when undisturbed reference conditions do not exist and a limited dataset is available (Moss, 2008).…”