Consistent multi-level trophic effects of marine reserve protection across northern New Zealand

Abstract

Through systematic Reef Life Survey censuses of rocky reef fishes, invertebrates and macroalgae at eight marine reserves across northern New Zealand and the Kermadec Islands, we investigated whether a system of no-take marine reserves generates consistent biodiversity outcomes. Ecological responses of reef assemblages to protection from fishing, including potential trophic cascades, were assessed using a control-impact design for the six marine reserves studied with associated reference sites, and also by comparing observations at reserve sites with predictions from random forest models that assume reserve locations are fished. Reserve sites were characterised by higher abundance and biomass of large fishes than fished sites, most notably for snapper Chrysophrys auratus, with forty-fold higher observed biomass inside relative to out. In agreement with conceptual models, significant reserve effects not only reflected direct interactions between fishing and targeted species (higher large fish biomass; higher snapper and lobster abundance), but also second order interactions (lower urchin abundance), third order interactions (higher kelp cover), and fourth order interactions (lower understory algal cover). Unexpectedly, we also found: (i) a consistent trend for higher (~20%) Ecklonia cover across reserves relative to nearby fished sites regardless of lobster and urchin density, (ii) an inconsistent response of crustose coralline algae to urchin density, (iii) low cover of other understory algae in marine reserves with few urchins, and (iv) more variable fish and benthic invertebrate communities at reserve relative to fished locations. Overall, reef food webs showed complex but consistent responses to protection from fishing in well-enforced temperate New Zealand marine reserves. The small proportion of the northeastern New Zealand coastal zone located within marine reserves (~0.2%) encompassed a disproportionately large representation of the full range of fish and benthic invertebrate biodiversity within this region.

Fig 1. Map of New Zealand sites surveyed by Reef Life Survey (RLS) divers.

Note that overlapping sites are hidden (N = 123). The map of sites can be expanded and explored on the RLS website (http://reeflifesurvey.com).

Fig 2. MDS plot of faunal relationships based on mean biomass of fish species at different sites in marine reserves (MR), fished reference sites adjacent to marine reserves (F), and fished sites at the Three Kings Islands (TKI_F) and around Northland (O_F).

Marine reserves investigated are Cape Rodney-Okakari Point (CROP), Tawharanui (Ta), Whanganui a Hei (Wh), Te Matuku (TM), Poor Knights Islands (PKI), Kermadec Islands (KI) and Te Paepae o Aotea (TP). Vector plots are shown for fish species with high (>0.5) correlations with axes.

Fig 3. MDS plot of faunal relationships based on mean density of benthic invertebrate species at marine reserves (MR), fished reference sites adjacent to marine reserves (F), and fished sites at the Three Kings Islands (TKI_F) and around Northland (O_F).

Marine reserves investigated are Cape Rodney-Okakari Point (CROP), Tawharanui (Ta), Whanganui o Hei (Wh), Te Matuku (TM), Poor Knights Islands (PKI), Kermadec Islands (KI) and Te Paepae o Aotea (TP). Vector plots are shown for invertebrate species with high (>0.5) correlations with axes.

Fig 4. MDS plot of biotic relationships based on percent cover of different substrate cover categories at marine reserves (MR), fished reference sites adjacent to marine reserves (F), and fished sites at the Three Kings Islands (TKI_F) and around Northland (O_F).

Marine reserves investigated are Cape Rodney—Okakari Point (CROP), Tawharanui (Ta), Whanganui o Hei (Wh), Te Matuku (TM), Poor Knights Islands (PKI), Kermadec Islands (KI) and Te Paepae o Aotea (TP). Vector plots are shown for taxa with high (>0.5) correlations with axes. Taxa abbreviations are explained in S1 Table.

Fig 5. Means (± SE) of four fish community metrics and two invertebrate metrics in marine reserves, fished reference sites adjacent to marine reserves, and fished sites without associated marine reserves at the Three Kings Islands and around Northland.

No fished reference sites were sampled near Kermadec Islands or Te Matuku. Note: scale of y-axis varies between panels.

Fig 6. Mean biomass (± SE) of four major trophic groups for fishes observerd in marine reserves, fished reference sites adjacent to marine reserves, and fished sites at the Three Kings Islands and around Northland.

Note: scale of y-axis varies between panels.

Fig 7. Mean biomass (± SE) of snapper Chrysophrys auratus in marine reserves surveyed, fished reference sites adjacent to marine reserves, and fished sites at the Three Kings Islands and around Northland.

Fig 8. Relative importance of the 10 covariates used in prediction models developed with random forests.

Note: scale of y-axis varies between panels.

Fig 9. Effect size (± SE) for four fish community metrics at six marine reserves.

Effect size was calculated using the log ratio (ln (observed)–ln (predicted)) where predictions were based on random forest relationships with 10 environmental covariates. Note: scale of y-axis varies between panels.

Fig 10. Mean cover (± SE) of different substratum categories in marine reserves, fished reference sites adjacent to marine reserves, and fished sites at the Three Kings Islands and around Northland.

Note: scale of y-axis varies between panels.

Fig 11. Effect size (± SE), as calculated using difference between observed and predicted values, for three algal cover metrics at six marine reserves.

Predictions were based on random forest relationships with 10 environmental covariates. Note: scale of y-axis varies between panels.