Diversity of polychaete fauna in the Gulf of Lions (NW Mediterranean)

Ninety two sites (10, 20, 30, 40 and 50 m depth), located on 21 transects along the portion of coast between the Spanish-French border and the mouth of the Rhone River were sampled for sediment and polychaete fauna during September-October 1998. Four assemblages were identified using cluster analysis, namely littoral fine sands (LFS), southern littoral sandy mud (LSMS), northern littoral sandy mud (LSMN) and terrigeneous coastal mud (TCM). Several components of polychaete diversity were assessed: a-diversity (i.e., within sites), P-diversity (i.e., turnover of species over the whole sampled area), estimates of the total number of polychaete species within each assemblage and gamma-diversity (i.e., total number of polychaete species over the whole sampled area). Dominance and synthetic indices of alpha-diversity were strongly influenced by the few dominant species (i.e., mostly Ditrupa arietina and Owenia fusiformis). Whittaker's beta(w) was estimated at 9.3 when considering the whole data set, which is high compared to the few other data available for polychaete fauna. This was partly linked to the high diversity of sampled habitats as shown by the drastic decrease in beta(w), when considering each assemblage separately. In all assemblages but LSMS, beta-diversity was more affected by the habitat than by the distance between sites, which seems to reflect more small scale spatial pattern in diversity than true species substitution along a gradient. The number of polychaete species within each assemblage correlated positively with sampling effort. It was nevertheless highest for LFS (67 species) and lower for LSMN (49 species) for a standardized (9 sites) sampling effort. Several non parametric estimators were used to assess the true number of species within each assemblage. All of them resulted in quite similar total number of species per assemblage. Gamma diversity for the whole data set was computed using both the extrapolation of the accumulation curve and the TS method. Total number of observed polychaete species was 173. The extrapolation of the species accumulation curve resulted in an estimation of an overall number of 873 species versus 980 (when splitting the whole data set in 4 geographical areas) and of 1,051 (when splitting the whole data set in 4 assemblages) for the TS method. The variable estimates of total polychaete species richness based on the TS method is discussed in relation with (1) the effect of the interaction between the pattern of spatial heterogeneity and sampling design, and (2) the arbitrary assignment of a sampled surface to a single sample.