Artificial ocean iron fertilization (OIF) of high nutrient low chlorophyll (HNLC) oceanic waters and subsequent carbon drawdown [1] could provide a contribution to mitigation of anthropogenic atmospheric CO₂ [2], [3], [4]. Artificial OIF involves the seeding of surface HNLC waters with iron, for example as FeSO₄ [5]. However, the impacts of large-scale manipulation of oceanic waters on pelagic and benthic ecosystems are unknown [1], [6]. While spatial and temporal variations in total biomass and gross taxon composition of deep-sea metazoan macrofauna and megafauna appear to reflect changes in upper ocean conditions [7], [8], [9], the relationship between species distributions and surface ocean productivity is not understood. This information is vital in assessing the consequences of large-scale manipulations of surface ocean productivity and carbon sequestration by artificial OIF [10].

The Southern Ocean is the largest HNLC region on Earth. Within this expanse, there are hotspots of primary productivity during the Austral spring and summer. These occur in areas of natural OIF, through the entrainment of dissolved iron leached from isolated oceanic islands, such as at the Kerguelen and Crozet Plateaus [11], [12]. The chemical form of natural iron differs from FeSO₄; while its precise chemistry is not well understood, a large fraction is likely to be complexed by humic materials or other ligands [13], [14]. Fe enrichment over the light-limited winter period to the north and east of the Crozet Plateau (48°S 56°E) in the Southern Indian Ocean, leads to a seasonal phytoplankton bloom when solar irradiance increases and the critical depth exceeds that of the mixed layer due to the onset of stratification in the spring. The spatial extent of the bloom is controlled by a semi-permanent meander in the Sub-Antarctic Front (Fig. 1a), while the water circulation is such that south of Crozet HNLC conditions prevail [15]. SeaWIFs images confirm that the hotspots of primary production stimulated by natural iron fertilization occur consistently from year to year [12], [16] and it is likely that these seasonal high productivity regions have persisted throughout the Holocene [17].

The Crozet Plateau provides an ideal opportunity to study the impact of nutrient enrichment in surface waters on the ecology of the deep-ocean floor. Studies of upper ocean biogeochemistry in the Austral summer of 2004/2005 [11], [12] confirmed enhanced primary productivity in surface waters to the north and east of the Crozet Plateau stimulated by iron enrichment. Sediment traps deployed over periods of ∼12 months from December 2004 to January 2006 [12], [18] indicated enhanced export of carbon to the deep ocean, north and east of the Crozet Islands [11], [12]; the annual carbon flux at ∼3000 m water depth in iron-enriched waters was ∼2.5× greater than the flux in HNLC waters south of the Plateau [12] during this period.

We undertook an intensive research programme during the Austral summer of 2005/2006 around the Crozet Islands in the Southern Ocean [19], to test for the first time our hypothesis that abyssal benthic ecology is influenced by natural OIF. We chose two sites, +Fe and HNLC (460 km apart), at the same water depth (∼4200 m) and in similar geomorphological, hydrographic and sedimentary settings with no physical barrier between them (Fig. 1b) [20]. The two sites are almost identical in their environmental characteristics apart from the productivity of overlying surface waters. The absence of geomorphological and hydrographic barriers between the two sites ensured that there are no constraints on the dispersal of fauna, other than that which might be related to surface water productivity. We measured fluxes of organic matter in the water column, with a specific aim of assessing the composition and quality of the sinking particulate organic matter. We investigated the megabenthos (>4 cm and large enough to be seen in bottom photographs; [21]) by means of trawls and video transects. These fauna, in particular holothurians, are a good group to use to investigate the influence of productivity from surface waters because they feed almost exclusively on freshly deposited detritus on the seafloor [22]. The holothurians dominate the deep-ocean megabenthos, sometimes accounting for up to 95% of individuals [22]. The ophiuroids are another important group, which feed on a variety of substrates [23]. Macrofauna are not included, because we were unable to collect sufficient samples, while results for the meiofauna and fish are reported elsewhere [19], [20].

A comprehensive account of sampling activities is given in the RRS Discovery cruise 300 Cruise Report [19] together with a narrative and full station list. We summarise relevant sampling activities in Table 1.

Sediment traps were deployed at the +Fe and HNLC sites at 3195 and 3183 m water depth (ca. 1000 m above the seafloor), respectively [12], [18]. The timing and temporal variability in flux was significantly different between the two sites (Fig. 2 a, b) [12]. At the +Fe site, east-southeast flows led to transport of exported flux from the Crozet bloom to the sediment trap. This extended over a period of at least 120 days originating from the spring/summer bloom in late 2004/early 2005. We deduce that the high-flux event towards the end of 2005 was derived from the onset of the late 2005 peak export flux to the deep sea. In contrast, downward flux at the HNLC site was focused in one very short event. It is not known if this represents a typical annual event, or one that occurs occasionally. For the purpose of this study we use the measured cumulative fluxes of organic carbon in the deep traps of 41.1 mmol m⁻² (355 days) at the +Fe site, and of 14.1 mmol m⁻² (352 days) at the HNLC site. At both sites, molar C/N ratios of organic matter reaching the sediment traps were close to the Redfield ratio (∼6.6), varying from 4.2 to 8.0. However, the chemical composition of the sediment trap material revealed substantial differences in organic matter quality between the two sites. Hence, fluxes (and concentrations) of labile lipids, including polyunsaturated fatty acids (PUFAs) and monounsaturated fatty acids (MUFAs), the presence of which suggest a source of high quality organic matter [32], [33], [34], were significantly higher (Friedman's test; n = 6 contiguous pairs, p = 0.014) at the +Fe site than at the HNLC site (Table 2; Fig. 3). PUFAs were below detection limits at the HNLC site. Photographs taken using the WASP system at the +Fe site in December 2005 confirm the presence of fresh phytodetritus at the seafloor (Fig. 4). We interpret this phytodetritus as originating from the late 2005 spring bloom event (Fig. 2a). Suspended POM (sPOM) collected using stand alone pump systems close to the seafloor at the +Fe site at that time had high chlorophyll and PUFA concentrations of 1.62 and 23.9 mg gC⁻¹, respectively (cf. below detection and 5.6 mg gC⁻¹, respectively at HNLC). The chlorophyll/phaeopigment ratio of surface sediments was also consistent with the presence of very fresh phytoplankton-derived material [35] (Table 2). WASP images showed no evidence of fresh phytodetritus at the seafloor at the HNLC site (Fig. 4).

The total standing stock of invertebrate megafauna, in terms of biomass and abundance, mirrored the particulate organic carbon (POC) fluxes at the two sites (Table 3; Table S1; Fig. 2). It should be noted that we were able to collect four trawls at +Fe, but only two at HNLC because of severe technical difficulties [19]. Despite this, we have some confidence in our data because the video transects confirmed the significant difference in populations between the +Fe and HNLC sites. Biomass was ×3 greater at the +Fe site than at the HNLC site (15,251 and 5,083 g wet weight ha⁻¹, respectively), while abundance was ∼×6 higher at +Fe vs the HNLC site (44,600 and 7,200 individuals ha⁻¹, respectively). The close relationship between biomass and organic input has been observed in other abyssal ecosystems [36]. Abundance is a better measure of rate processes and ecosystem function [7], [37], [38]. The much higher abundances (Table 3; Table S1) suggest a higher rate of carbon cycling at the +Fe than the HNLC sites; this is reflected in the lower organic carbon contents of surface sediments at +Fe than HNLC (Table 2).

Holothurians were the dominant megafaunal group at both sites accounting for between 70 and 89% of the total biomass. However, rather than the same species occurring at +Fe and HNLC sites, despite their close proximity, there were striking differences in species composition and dominance (Table 3; Figs. 5 a & b). Some species were common to the two sites, and occurred in similar abundances, such as the ophiuroids Ophiura lienosa, Ophiura irrorata loveni and Amphioplus daleus, but most megafaunal species showed very marked differences (Table 3, Table S1). Of the elpidiid holothurians Kolga nana, Peniagone willemoesi and Peniagone affinis dominated at the HNLC site, while closely related, but different, species, Peniagone crozeti [39] and Peniagone challengeri dominated at the +Fe site in all of the trawls.

If only one or two species had shown radical differences between the +Fe and HNLC sites then one might conclude that spatial patchiness was a key element in the observed differences. However, the marked contrast in many species suggests that environmental factors relating to organic matter supply are important in influencing species composition and ecosystem structure. In this context, the similarity in the composition of the dominant taxa at the +Fe site and at abyssal depths in the productive NE Atlantic, 16,000 km distant [40], [41], is remarkable. The relative contributions to the total biomass by different higher taxonomic groupings is almost identical in the two regions (Fig. 6). In addition, the same, or very similar, abundant holothurian species occur at widely separated eutrophic sites around the world [42].

This poses questions about what factors associated with organic supply are responsible for these broad-scale geographic patterns; is it the quantity, timing or quality of the POM flux or a combination of these factors? Our data suggest that the quality of POM arriving at the sea floor at +Fe was much higher than at HNLC. Phytoplankton communities were distinctly different at the +Fe and HNLC sites during the spring/summer 2004/2005, the former being dominated by Phaeocystis sp., the latter by large diatoms including Fragilariopsis kerguelensis [43]. The preserved planktonic assemblages in the deep-water sediment traps at the +Fe and HNLC sites were dominated by diatoms, but were also distinctly different, in that the neritic species Eucampia antarctica was abundant at +Fe, but completely absent at HNLC site [18]. These significant differences were reflected in the organic composition of the sinking POM collected in 1) the deep-water sediment traps (Fig. 3), 2) sPOM collected close to the seafloor and 3) surface sediments at the two sites (Table 2).

The greatly enhanced flux of labile compounds at +Fe vs. HNLC sites may be crucial in controlling species composition; this is supported indirectly by the differences in the biochemistry and fecundity of Peniagone species between sites. All the Peniagone species had a similar gametogenic biology and similar maximum egg size (ca. 500 µm diameter). The only difference was that Peniagone crozeti had a significantly higher gonad index (weight gonad/weight organism) at the +Fe site compared to all the other species, implying higher fecundity. Furthermore, the concentrations of carotenoids, which are important for echinoderm reproduction and enhance larval maturation and survival [44], [45], namely canthaxanthin, echinenone and β-carotene, were high in the ovaries of Peniagone crozeti at the +Fe site (Table S2). The supply of these pigments, which are believed to be derived from phytoplankton in overlying waters, and the ability of P. crozeti, in particular, to assimilate them, may be critical factors leading to the dominance of this species at +Fe. Peniagone crozeti was the single most abundant species around the Crozet Islands, occurring in great abundance in all of the trawls only at the +Fe site. It has never been recorded at any other locality. The distribution of P. crozeti appears to be restricted by the characteristics of the productivity regime in the overlying surface waters, pointing to the importance of organic input in regulating faunal distributions on the deep seafloor.

The timing and predictability of organic matter flux, including year-to-year consistency in flux, may also be important in structuring deep-sea benthic communities. Unfortunately, inter-annual sediment trap data are not available, but the HNLC site was notable for the prevalence of the holothurian species Kolga nana. Kolga has high fecundity and a small egg size indicative of ‘opportunistic’ species [22], [46]. It can occur episodically for short periods in high numbers [22], [47]. Its presence, together with the complete absence of species generally found in eutrophic settings, suggests that the character of the organic matter supply from year to year in HNLC regions may influence the composition of species in this region.

The quantity and composition of POM arriving at the seafloor in the Crozet region is influenced by the supply of iron to surface waters and this in turn controls the biomass and species composition of large invertebrate fauna at the seafloor. It is likely that enhanced carbon flux to the seafloor, via artificial OIF of the HNLC ocean, would change the deep-sea benthic biomass, species composition and dominance over an extended period of time. Furthermore, our study provides evidence that a combination of timing, quantity and quality of POM export strongly influence community structure of deep-sea benthic ecosystems.