Fish food in the deep sea: revisiting the role of large food-falls

Abstract

The carcasses of large pelagic vertebrates that sink to the seafloor represent a bounty of food to the deep-sea benthos, but natural food-falls have been rarely observed. Here were report on the first observations of three large 'fish-falls' on the deep-sea floor: a whale shark (Rhincodon typus) and three mobulid rays (genus Mobula). These observations come from industrial remotely operated vehicle video surveys of the seafloor on the Angola continental margin. The carcasses supported moderate communities of scavenging fish (up to 50 individuals per carcass), mostly from the family Zoarcidae, which appeared to be resident on or around the remains. Based on a global dataset of scavenging rates, we estimate that the elasmobranch carcasses provided food for mobile scavengers over extended time periods from weeks to months. No evidence of whale-fall type communities was observed on or around the carcasses, with the exception of putative sulphide-oxidising bacterial mats that outlined one of the mobulid carcasses. Using best estimates of carcass mass, we calculate that the carcasses reported here represent an average supply of carbon to the local seafloor of 0.4 mg m(-2)d(-1), equivalent to ∼ 4% of the normal particulate organic carbon flux. Rapid flux of high-quality labile organic carbon in fish carcasses increases the transfer efficiency of the biological pump of carbon from the surface oceans to the deep sea. We postulate that these food-falls are the result of a local concentration of large marine vertebrates, linked to the high surface primary productivity in the study area.

Figure 1. Map showing the locations of elasmobranch carcasses (inset) observed on the Angola continental margin.

Figure 2. Still images showing each of the observed carcasses.

A Whale shark (Rhincodon typus); B Mobulid carcass 1; C Mobulid carcass 2; D Mobulid Carcass 3. Images have been enhanced. Originals and details of enhancements are available in Figure S1.

Figure 3. Relationship between carcass mass and the rate at which it is scavenged, based on a global dataset comprising different carcass types: •mammal; ▪ teleost; ⧫ elasmobranch; ▴ squid.

A logarithmic regression (solid black line defined by the equation) y  =  4.345ln(x) − 3.222)explained a significant proportion of the variance in the relationship; R² =  0.84, F(1,30) =  154.6, p <0.001. Data and references are presented in Dataset S1. Areas highlighted in turquoise indicate possible range in mass of the mobulid carcasses (left) and whale shark carcass (right). Corresponding dashed gray lines show best estimate for the mass of each carcass type and hence scavenging rate according to the regression equation.