Key factors explaining critical swimming speed in freshwater fish: a review and statistical analysis for Iberian species

Abstract

Swimming performance is a key feature that mediates fitness and survival in aquatic animals. Dispersal, habitat selection, predator-prey interactions and reproduction are processes that depend on swimming capabilities. Testing the critical swimming speed (U_crit) of fish is the most straightforward method to assess their prolonged swimming performance. We analysed the contribution of several predictor variables (total body length, experimental water temperature, time step interval between velocity increments, species identity, taxonomic affiliation, native status, body shape and form factor) in explaining the variation of U_crit, using linear models and random forests. We compiled in total 204 studies testing U_crit of 35 inland fishes of the Iberian Peninsula, including 17 alien species that are non-native to that region. We found that body length is largely the most important predictor of U_crit out of the eight tested variables, followed by family, time step interval and species identity. By contrast, form factor, temperature, body shape and native status were less important. Results showed a generally positive relationship between U_crit and total body length, but regression slopes varied markedly among families and species. By contrast, linear models did not show significant differences between native and alien species. In conclusion, the present study provides a first comprehensive database of U_crit in Iberian freshwater fish, which can be thus of considerable interest for habitat management and restoration plans. The resulting data represents a sound foundation to assess fish responses to hydrological alteration (e.g. water flow tolerance and dispersal capacities), or to categorize their habitat preferences.

Figure 1

Variable importance of predictors of U_crit according to the random forest model. Variable importance is the difference in prediction accuracy (i.e. the number of observations classified correctly) before and after permuting a variable, averaged over all trees; and represents the effect of a variable in both main effects and interactions. Total percentage of explained variation was 72.8%. Figure created using R.

Figure 2

Partial dependence of U_crit across fish species based on the random forest model. Figure created using R.

Figure 3

Relationship of U_crit with fish total length (TL) across species belonging to: (a) Cyprinidae and Leuciscidae; (b) Salmonidae; (c) Percidae, Moronidae, Centrarchidae and Esocidae; and (d) other families. Only lines for significant regressions are shown (see Table S1 for statistics). Figure created using R.

Figure 4

Surface plots relating U_crit with fish total length (TL) and temperature for two well-studied species: (a) Rutilus rutilus, and (b) Salmo trutta. Note log₁₀-transformations for U_crit and TL variables. Figure created using R.