Comparison of feeding preferences of herbivorous fishes and the sea urchin Diadema antillarum in Little Cayman

Abstract

On Caribbean coral reefs, losses of two key groups of grazers, herbivorous fishes and Diadema antillarum, coincided with dramatic increases in macroalgae, which have contributed to decreases in the resilience of these coral reefs and continued low coral cover. In some locations, herbivorous reef fishes and D. antillarum populations have begun to recover, and reductions in macroalgal cover and abundance have followed. Harder to determine, and perhaps more important, are the combined grazing effects of herbivorous fishes and D. antillarum on the structure of macroalgal communities. Surprisingly few studies have examined the feeding preferences of D. antillarum for different macroalgal species, and there have been even fewer comparative studies between these different herbivore types. Accordingly, a series of in-situ and ex-situ feeding assays involving herbivorous fishes and D. antillarum were used to examine feeding preferences. Ten macrophytes representing palatable and chemically and/or structurally defended species were used in these assays, including nine macroalgae, and one seagrass. All species were eaten by at least one of the herbivores tested, although consumption varied greatly. All herbivores consumed significant portions of two red algae species while avoiding Halimeda tuna, which has both chemical and structural defenses. Herbivorous fishes mostly avoided chemically defended species while D. antillarum consumed less of the structurally defended algae. These results suggest complementarity and redundancy in feeding by these different types of herbivores indicating the most effective macroalgal control and subsequent restoration of degraded coral reefs may depend on the recovery of both herbivorous fishes and D. antillarum.

Keywords: Caribbean coral reefs; Diadema antillarum; Herbivory; Long spined sea urchin; Macroalgae; Parrotfish; Surgeonfish.

Figure 1. Photographs of macrophytes used in feeding assays.

Photographs show Dictyota sp. (A) Palisada sp. (B) Laurencia sp. 2 (C) Lobophora sp. (D) Turbinaria sp. (E) Galaxaura sp. (F) Halimeda tuna (G) Laurencia sp. 1 (H) Padina sp. (I) and the seagrass Thalassia testudinum (J) Insets are included to show details of some of the macroalgae.

Figure 2. Map of study sites referenced in manuscript.

Map of experimental sites around Little Cayman, Cayman Islands including feeding assays sites, algal collection sites, and Diadema antillarum collection sites. Map data ©2023 Google.

Figure 3. Proportion of pieces of each macrophyte eaten by fish at the shallow (A–G) and deep (H–N) sites.

Each panel represents an individual trial (n = 14) deployed for 24 h. Data analyzed using a G-test followed by Fisher’s exact tests, and letters indicate significant differences.

Figure 4. Comparison of proportion eaten among macrophyte species (x-axis) at the shallow (A) and deep (B) site as well as a direct comparison between sites (C).

Error bars represent 95% confidence intervals. Data were analyzed using a linear mixed effects model followed by post-hoc least-squares means tests to determine differences within and between sites. Letters indicate significant differences (p < 0.05) in proportion consumed within each site and * indicates significant differences for each macrophyte (p < 0.05) between sites.

Figure 5. Abundance of each herbivorous fish species (±SE) per m² found at the shallow and deep site.

Values acquired from visual surveys along belt transects at the shallow (n = 4) and deep (n = 3) sites.

Figure 6. Percent of bites by each herbivorous fish on each macrophyte across both shallow (A) and deep (B) sites.

Bite numbers obtained from video recordings of the assays. For Sparisoma species, (I) indicates initial phase fish and (T) indicates terminal phase. Species that were recorded taking less than 1 bite per hour of macrophytes are not shown in the figure.

Figure 7. Amount in grams of each macrophyte ± standard error eaten by Diadema antillarum in choice feeding assays in December 2017 (A–G) and May 2018 (H).

Different letters indicate significant differences when analyzed by Friedman’s tests followed by Student-Newman-Keuls tests.