Context-dependent interactions and the regulation of species richness in freshwater fish

Abstract

Species richness is regulated by a complex network of scale-dependent processes. This complexity can obscure the influence of limiting species interactions, making it difficult to determine if abiotic or biotic drivers are more predominant regulators of richness. Using integrative modeling of freshwater fish richness from 721 lakes along an 11^o latitudinal gradient, we find negative interactions to be a relatively minor independent predictor of species richness in lakes despite the widespread presence of predators. Instead, interaction effects, when detectable among major functional groups and 231 species pairs, were strong, often positive, but contextually dependent on environment. These results are consistent with the idea that negative interactions internally structure lake communities but do not consistently 'scale-up' to regulate richness independently of the environment. The importance of environment for interaction outcomes and its role in the regulation of species richness highlights the potential sensitivity of fish communities to the environmental changes affecting lakes globally.

Fig. 1

Direct and indirect drivers of species richness in fish. SEM-derived multivariate relationships among integrated abiotic and biotic regulatory factors (blocks = degree days, circles = lake morphometry, triangles = water quality, and biotic factors [red lines]) for the richness and composition of four major fish functional groups in 721 lakes along an 11° latitudinal gradient in Ontario, Canada SEM integrative model:, n = 648, ML_EST = 4.91, Degree of freedom = 13, P = 0.977, see Methods and Supplementary Note 1). Solid lines indicate negative relationships; dashed lines indicate positive relationships. Arrows indicate the direction of the relationship. Bold lines indicate stronger relationships, arbitrarily assigned as standardized path coefficient values > 0.40. Black lines indicate abiotic influences on biotic factors and red lines indicate influences between biotic factors. Functional groups are predator, littoral, pelagic, and small-prey species, with full species list given in Supplementary Table 1

Fig. 2

Categories of habitat overlap among fish species. Representative ordinations of lakes in multivariate environmental space for fish species pairs, divided into four broad categories described in Supplementary Table 4: a–c species rarely co-occur—there can be a large overlap between A alone and B alone (i.e., they can tolerate similar lake conditions), yet they are rarely found together—this is consistent with negative interactions; d at least one species inhabits a compressed range of lake conditions when the other is present—this could be due to abiotic limitations of one or both species, such that the range of conditions inhabitable is narrower than when they are alone, or it could result from ‘contingent coexistence,’ where a subordinate can only escape the effects of a dominant in certain environmental conditions; e species co-occur quite often with no evidence of a narrowing of environmental conditions in the presence of the other; and f one species is found in a greater range of environmental conditions when the other is present. DD = degree days; P = phosphorus; cond = conductivity

Fig. 3

Frequency of negative, positive, and non-associated pair-wise interactions between among-lake richness versus within-lake abundance. a Frequency of significantly positive, nonsignificant, and negative associations among 231 species pairs of freshwater fish in 721 lakes, for two classes of data: lake presence/absence (differences in among-lake richness) and lake abundance based on catch per unit effort for each species in each lake (differences in within-lake abundance). We hypothesized an increase in the frequency of negative interactions within-lakes but this was generally not the case, for both species pairs in the ‘same’ temperature class (e.g., two species of ‘warm-water’ fish, Supplementary Table 1) versus ‘different’ classes (warm vs cold-water species). b Relative change in the importance of four major explanatory factors (climate, morphometry, water quality, and negative species interactions) between BRT analyses of among-lake richness to BRT analyses of within-lake abundance (see Supplementary Table 3). Significant thresholds were based on an α < 0.05