Superior predatory ability and abundance predicts potential ecological impact towards early-stage anurans by invasive 'Killer Shrimp' (Dikerogammarus villosus)

Abstract

Invasive alien species negatively impact upon biodiversity and generate significant economic costs worldwide. Globally, amphibians have suffered considerable losses, with a key driver being predation by large invasive invertebrate and vertebrate predators. However, there is no research regarding the potential ecological impact of small invertebrate invaders. The invasive freshwater amphipod Dikerogammarus villosus can act as a top predator capable of displacing native amphipods and preying heavily upon a range of native species. Listed as one of Europe's top 100 worst invaders, D. villosus has significantly restructured freshwater communities across western Europe and is expected to invade North America in the near future. Here we explore the ecological impact of invasive D. villosus upon UK native and invasive amphibians (Rana temporaria and Xenopus laevis respectively) using the "Relative Impact Potential" (RIP) metric. By combining estimations of per capita effects (i.e. functional response; FR) and relative field abundances, we apply the RIP metric to quantify the potential ecological impact of invasive D. villosus upon embryonic and larval amphibian prey, compared to the native amphipod Gammarus pulex. Both native and invasive amphipods consumed early-stage amphibians and exhibited potentially destabilising Type II FRs. However, larger body size in invasive D. villosus translated into a superior FR through significantly lower handling times and subsequently higher maximum feeding rates-up to seven times greater than native G. pulex. Higher invader abundance also drove elevated RIP scores for invasive D. villosus, with potential impact scores predicted up to 15.4 times greater than native G. pulex. Overall, D. villosus is predicted to have a greater predatory impact upon amphibian populations than G. pulex, due primarily to its larger body size and superior field abundance, potentially reducing amphibian recruitment within invaded regions.

Figure 1

Type II functional response curves for intermediate D. villosus (filled squares and solid black line) and large D. villosus (filled triangle and dotted black line) towards non-native X. laevis embryos (n = 5 replicates per prey density). Shaded Regions are bootstrapped 95% confidence intervals (yellow: intermediate D. villosus, blue: large D. villosus).

Figure 2

Rogers random-predator (Type II) functional response curves for large G. pulex (filled circles with dot-dash black line), intermediate D. villosus (filled squares and solid black line) and large D. villosus (filled triangle and dotted black line) towards native R. temporaria larvae (n = up to 11 replicates per prey density). Shaded Regions display bootstrapped 95% confidence intervals (red: large G. pulex, yellow: intermediate D. villosus, blue: large D. villosus).

Figure 3

RIP biplots comparing intermediate D. villosus (filled square), large D. villosus (filled triangle) and large G. pulex (open circle) when feeding upon native R. temporaria larvae as prey. Biplots generated using mean ± standard errors (SE) estimates for FRs (i.e. maximum feeding rates) and field abundances (ind/m²) recorded in each amphipod size treatment. Mean (± SE) FR parameters are generated from bootstrapped estimates (n = 30 bootstraps).