Ecological effects of full and partial protection in the crowded Mediterranean Sea: a regional meta-analysis

Abstract

Marine protected areas (MPAs) are a cornerstone of marine conservation. Globally, the number and coverage of MPAs are increasing, but MPA implementation lags in many human-dominated regions. In areas with intense competition for space and resources, evaluation of the effects of MPAs is crucial to inform decisions. In the human-dominated Mediterranean Sea, fully protected areas occupy only 0.04% of its surface. We evaluated the impacts of full and partial protection on biomass and density of fish assemblages, some commercially important fishes, and sea urchins in 24 Mediterranean MPAs. We explored the relationships between the level of protection and MPA size, age, and enforcement. Results revealed significant positive effects of protection for fisheries target species and negative effects for urchins as their predators benefited from protection. Full protection provided stronger effects than partial protection. Benefits of full protection for fish biomass were only correlated with the level of MPA enforcement; fish density was higher in older, better enforced, and -interestingly- smaller MPAs. Our finding that even small, well-enforced, fully protected areas can have significant ecological effects is encouraging for "crowded" marine environments. However, more data are needed to evaluate sufficient MPA sizes for protecting populations of species with varying mobility levels.

Figure 1

Marine Protected Areas (MPAs) including one or more no-take area(s) across the Mediterranean Sea (76 in total; data source: MAPAMED database). Orange dots (in highlighted countries) show the 24 MPAs (numbered as in Table 1) for which available data were found through an extensive literature review and that have been included in our analyses. Created by S.G. using ESRI ArcGIS 10.2 Software (http://www.esri.com/software/arcgis).

Figure 2

Mean weighted effect sizes in (a) fully and (b) partially protected areas in Mediterranean MPAs. The graph displays the weighted ratio (E) and 95% Confidence Interval (CI) in and out (fully or partially) protected areas of: fish assemblage biomass, density, and species richness; dusky grouper (Epinephelus marginatus), white seabream (Diplodus sargus sargus), and two-banded seabream (D. vulgaris) biomass and density; and sea urchin (Paracentrotus lividus and Arbacia lixula) density. Open dots correspond to mean effect sizes with confidence intervals that overlapped with zero. Sample sizes for each variable are indicated in parentheses next to effect sizes.

Figure 3

Spearman’s rank correlations among pairs of MPA features. Lower triangular correlation matrix: numbers are Spearman’s rank correlations (rho). Superscripts symbols indicates p-values of Spearman’s rank correlations tests: ^nsp > 0.1; *p < 0.1; **p < 0.01; ***p < 0.001. Upper triangular correlation matrix: Shape and orientation of ellipses are proportional to rho absolute value and direction, respectively.

Figure 4

The relationship between mean effect size (95% Confidence Interval) of fish assemblage biomass across the Mediterranean MPAs. Blue dots correspond to MPAs where the enforcement level is low-medium and yellow dots correspond to MPAs where the enforcement level is high (levels of enforcement sensu Guidetti et al.).

Figure 5

First two axes of the PCA on the four MPA features (green arrows), onto which the effect size of fish assemblage density of each MPA is plotted by using bubbles (bubble size is proportional to effect size value) and a purple arrow (correlation of the response, effect size of fish assemblage density, with PCA axes).