Competition among small individuals hinders adaptive radiation despite ecological opportunity

Abstract

Ontogenetic diet shifts, where individuals change their resource use during development, are the rule rather than the exception in the animal world. Here, we aim to understand how such changes in diet during development affect the conditions for an adaptive radiation in the presence of ecological opportunity. We use a size-structured consumer-resource model and the adaptive dynamics approach to study the ecological conditions for speciation. We assume that small individuals all feed on a shared resource. Large individuals, on the other hand, have access to multiple food sources on which they can specialize. We find that competition among small individuals can hinder an adaptive radiation to unfold, despite plenty of ecological opportunity for large individuals. When small individuals experience strong competition for food, they grow slowly and only a few individuals are recruited to the larger size classes. Hence, competition for food among large individuals is weak and there is therefore no disruptive selection. In addition, initial conditions determine if an adaptive radiation occurs or not. A consumer population initially dominated by small individuals will not radiate. On the other hand, a population initially dominated by large individuals may undergo adaptive radiation and diversify into multiple species.

Keywords: adaptive radiation; life history; ontogenetic diet shifts; size structure; speciation.

Figure 1.

Evolutionary time series of the niche trait x_i in case of (a,b) low and (c,d) high productivities of the shared resource; (a,c) are calculated using the adaptive dynamics approach and (b,d) are results from the IBM. Optimal trait values for feeding on the different species-specific resources are indicated by the ticks on the vertical axes. The colour of the dots in the (b,d) indicates the value of the assortative mating trait. Only mature individuals are plotted in (b,d). At the end of the simulation, reproductive isolation equals 0.97 in (d). At two points (indicated with vertical, dashed lines), we show in figure 3 the growth rate of the two morphs and their hybrid offspring. The ancestral population consists of a single species with a niche trait value of x₁ = 0. The supply rate of the shared resource equals $\delta R_{\mathrm{s},\max }=0.025\hspace{0.17em}\mathrm{g}\hspace{0.17em}{\mathrm{m}}^{-3}{\mathrm{day}}^{-1}$ in (a,b) and $\delta R_{\mathrm{s},\max }=0.2\hspace{0.17em}\mathrm{g}\hspace{0.17em}{\mathrm{m}}^{-3}{\mathrm{day}}^{-1}$ in (c,d). The body mass at birth m_b equals 0.05 g, individuals shift to the species-specific resources at a body mass of m_shift = 5 g. The feeding specialization late in life does not affect feeding ability on the shared resource early in life (τ_s = ∞). All other parameter values are as shown in the electronic supplementary material, tables A1 and A4. (Online version in colour.)

Figure 2.

The productivity of the shared resource strongly affects the size-structure of the population and therefore the likelihood of speciation; (a) shows the density of the shared resource R_s (grey) and resource R₁ (black) as a function of the supply rate of the shared resource; (b) shows the density of small consumers (m < m_shift) in grey, and the density of large consumers (m ≥ m_shift) in black as a function of the supply rate of the shared resource. The solid lines represent stable ecological equilibria, the dashed lines represent unstable ecological equilibria. The consumers are, after the ontogenetic diet shift, specialized in feeding upon resource R₁ (x₁ = 1); (c,d) show individual growth of individuals specialized on R₁ (x = 1) in an environment with a (c) low or (d) high density of the shared resource. The horizontal dashed lines indicate the body mass at which individuals switch to the species-specific resources. The supply rate of the shared food source (δR_s,max) equals (c) 0.025 and (d) 0.2 $\mathrm{g}\hspace{0.17em}{\mathrm{m}}^{-3}{\mathrm{day}}^{-1}$. The body mass at birth m_b equals 0.05 g, individuals shift to the species-specific resources at a body mass of m_shift = 5 g. The feeding specialization late in life does not affect feeding ability on the shared resource earlier in life (τ_s = ∞). All other parameter values are as shown in the electronic supplementary material, table A1. (Online version in colour.)

Figure 3.

Growth curves of the two morphs (solid lines) and their hybrid offspring (dotted lines) just after the first diversification event (a) and just before the collapse of two morphs into a hybrid swarm (b); (c) shows the amount of reproductive isolation over evolutionary time (with a value of 0 indicating random mating and a value of 1 complete isolation), while (d) shows the average value of the assortative mating trait in the population. The vertical lines in these panels correspond to the growth curves in (a,b). In (a), hybrid offspring grow slowly and almost never mature (probability to reach maturity <2 × 10⁻⁸). The supply rate of the shared food source equals $\delta R_{s,\max }=0.2\hspace{0.17em}\mathrm{g}\hspace{0.17em}{\mathrm{m}}^{-3}{\mathrm{day}}^{-1}$. The body mass at birth m_b equals 0.05 g, individuals shift to the species-specific resources at a body mass of m_shift = 5 g. In (a), the R₁ specialist (black line) has a trait value of x = 1.57, the hybrid R₂ specialist (dotted line) has a trait value of x = 3.29, and the R₃ specialist (grey line) has a trait value of x = 4.87. In (b), the R₁ specialist has a trait value of x = 1.3, the hybrid R₂ specialist has a trait value of x = 3.83 and the R₃ specialist has a trait value of x = 6.61. All other parameter values are as shown in the electronic supplementary material, table A1 and A4. (Online version in colour.)

Figure 4.

Two parameter plot showing the number of species that will evolve as a function of the relative productivity of the shared resource (R_s,max/R_c,max) and m_shift, the body mass at which individuals switch from the shared resource to the other resources (a,c), or m_b, the body mass at which individuals are born (b,d). The hatched areas indicate the parameter areas where there is eco-evolutionary bistability. In (a,b), there is no trade-off between feeding upon the shared resource and feeding upon the specific-specific resources (τ_s = ∞). In (c,d), we assume a weak trade-off (τ_s = 20). The body mass at birth m_b equals 0.5 mg in (a,c). Individuals shift to the species-specific resources at a body mass of m_shift = 5 g in (b,d). All other parameter values are as shown in the electronic supplementary material, table A1. The results of these plots are calculated using the adaptive dynamics approach and therefore assume clonal reproduction. (Online version in colour.)

Figure 5.

Evolutionary time series of the niche trait x_i in case of a population initially dominated by small individuals (a) and a population initially dominated by large individuals (b). Optimal trait values for feeding on the different resources are indicated by the ticks on the vertical axes. The colour of the dots indicates the value of the assortative mating trait. Only mature individuals are plotted for clarity. At the end of the simulation, reproductive isolation equals 0.9 in (b). The ancestral population consists of a single species with a niche trait value of x₁ = 3. The supply rate of the shared resource equals $\delta {\mathrm{R}}_{\mathrm{s},\max }=0.6\hspace{0.17em}\mathrm{g}\hspace{0.17em}{\mathrm{m}}^{-3}{\mathrm{day}}^{-1}$. The body mass at birth m_b equals 0.5 mg, individuals shift to the species-specific resources at a body mass of m_shift = 5 g. There is a trade-off between feeding upon the shared resource and the species-specific resources (τ_s = 20). The volume of the system equals 1 × 10³ m³ in (a) and 10⁴ m³ in (b). All other parameter values are as shown in the electronic supplementary material, table A1 and A4. (Online version in colour.)