Prey patch patterns predict habitat use by top marine predators with diverse foraging strategies

Abstract

Spatial coherence between predators and prey has rarely been observed in pelagic marine ecosystems. We used measures of the environment, prey abundance, prey quality, and prey distribution to explain the observed distributions of three co-occurring predator species breeding on islands in the southeastern Bering Sea: black-legged kittiwakes (Rissa tridactyla), thick-billed murres (Uria lomvia), and northern fur seals (Callorhinus ursinus). Predictions of statistical models were tested using movement patterns obtained from satellite-tracked individual animals. With the most commonly used measures to quantify prey distributions--areal biomass, density, and numerical abundance--we were unable to find a spatial relationship between predators and their prey. We instead found that habitat use by all three predators was predicted most strongly by prey patch characteristics such as depth and local density within spatial aggregations. Additional prey patch characteristics and physical habitat also contributed significantly to characterizing predator patterns. Our results indicate that the small-scale prey patch characteristics are critical to how predators perceive the quality of their food supply and the mechanisms they use to exploit it, regardless of time of day, sampling year, or source colony. The three focal predator species had different constraints and employed different foraging strategies--a shallow diver that makes trips of moderate distance (kittiwakes), a deep diver that makes trip of short distances (murres), and a deep diver that makes extensive trips (fur seals). However, all three were similarly linked by patchiness of prey rather than by the distribution of overall biomass. This supports the hypothesis that patchiness may be critical for understanding predator-prey relationships in pelagic marine systems more generally.

Figure 1. The distribution of juvenile walleye pollock in 2009 based on three different metrics.

A. biomass density, the most commonly used measure, B. the mean volumetric density of pollock within aggregations, a measure of local density within a patch, and C. the maximum volumetric density of pollock per sampling transect. Map surfaces were generated using minimum curvature interpolations (N = 165).

Figure 2. The observed versus expected density of prey aggregations on each transect.

A. Shows dense pollock aggregations and B. euphausiid aggregations. Only transects on which these groups were detected were included. The expected density of aggregations is the total biomass for each transect divided by the median biomass per aggregation observed across all transects. Note that in panel A there are 23 data points to the left of the regression line on the x axis but because of overlapping values, it is not possible to see each point.

Figure 3. Predicted and observed predator densities.

The observed density of each predator versus the density predicted by the full multiple regression model for each species.

Figure 4. Predicted and observed predator habitat use in 2009.

A. The predicted density classes for each predator species using the full multiple-regression model based on transect data and B. the kernel densities for tagged individual predators at each sampled transect. C. The difference between the model category and the kernel category. Positive, cool colored values indicate that fewer predators used an area than predicted by the model while negative, warm colored values indicate the opposite. On each plot, the center of each transect that was visually surveyed for birds and mammals and thus was used to create the regression model is shown with a +. The center of each transect for which environmental and prey data were available but could not be used to create the regression model is shown by o. Map surfaces were generated using minimum curvature interpolation that did not allow values plotted at sampled points to differ from their actual values.