Studying the relationship between species and their environment is at the core of ecology. Modeling this relationship has long been performed, using a wide array of methods (Domisch et al., 2015;Franklin, 1995;Guisan & Zimmermann, 2000). The focus in developing these models may be to study species-environment relationships or to predict the occurrence of the studied species. In fisheries research, the identification of the environmental variables that characterize fish distributions has been one of the main objectives (Nelson et al., 1992;Rieman & McIntyre, 1995). Predictive models may help in fish-based bioassessment (Brosse et al., 2001;Oberdorff et al., 2001Oberdorff et al., , 2002 and in focusing inventory and management activities on areas where species are considered likely to occur (Porter et al., 2000).Several studies have indicated that field-measured site-scale (local) variables such as stream width, water depth, water chemistry, riverbed substrate, flowrate, undercut banks, canopy cover, riparian vegetation, and the slope at the sampling site can predict the