Identifying the spatial and temporal characteristics of foraging habitat, search tactics, and diet of predators is fundamental to understanding their role in ecosystems and to developing conservation measures for threatened species, such as the protection of critical habitat. We expect animals to balance the benefits and costs of foraging decisions, since time and energy are spent searching for, capturing, and handling prey [1]. To begin to understand the foraging decisions of marine predators, it is important to study how prey characteristics (e.g., size of prey and patch density) influence their foraging behavior and success (e.g., [2], [3], [4]). However, prey are usually encountered and consumed at depth by marine animals, therefore, foraging behavior and diets are typically inferred indirectly, for instance from analyses of dive behavior and various diet estimate methods. The ability to directly observe and quantify foraging success in conjunction with understanding spatial movements over fine (1–10 km), meso (10s–100s of km), and large oceanographic scales (>1,000 km) is of great importance to better understanding marine animal populations and their variability [5].

The leatherback turtle (Dermochelys coriacea) is the largest living species of marine turtle, and also has the widest global distribution of any reptile. This species is listed as critically endangered globally [6] and endangered in Canada [7]. Leatherbacks undertake long-distance migrations (up to 18,000 km round-trip) between tropical breeding and foraging grounds and northern temperate foraging grounds [8], [9], [10]. Although east-west migrations are typical of some leatherback populations [8], [11] and return trips to specific foraging areas may span as long as 2–3 years, most sub-adult and adult leatherbacks in the northwest Atlantic perform these migrations annually [9], [12] to feed on gelatinous zooplankton, primarily jellyfish [13], [14], which are often associated with oceanographic features such as areas of upwelling [8]. For sexually mature adult leatherbacks, such migrations to high latitudes are presumably driven by the need to accumulate resources for reproduction [12]. However, during these migrations, leatherback turtles are exposed to a number of threats including fisheries bycatch (e.g., pelagic longline and particularly fixed gear in temperate waters [7]). In addition to human impacts, climate and oceanographic variability (which also influence prey distributions) no doubt also impact the life history of turtles in the Northwest Atlantic and are expected to influence juvenile recruitment and breeding remigration and contribute to range expansion (e.g., [5], [15]). Thus, it is of great importance to better understand leatherback foraging strategies to assess their significance to leatherback population energetics and to inform management measures such as the identification of critical habitat.

One of the most intriguing aspects of the foraging strategy of leatherback turtles is the almost complete reliance of such a large-bodied animal (up to 640 kg [12]) on a diet of gelatinous zooplankton, a low-energy food source [16], [17]. It has been estimated that hatchling leatherbacks may consume more than 100% body weight • day^-1 [18] and adults at least 50% body weight • day^-1 [19]. However, both the remote location of foraging and the sub-surface consumption of prey have precluded verification of such estimates. Found throughout the world's oceans, jellyfish are patchily distributed, but occur predictably at high densities in specific areas and at certain times of year [20]. Temperate coastal shelf waters of the North Atlantic are characterized by high concentrations of jellyfish during the summer months [21], [22]. Although dedicated studies of jellyfish distribution and abundance in Atlantic Canadian waters are lacking, spatial distributions of lion's mane jellyfish (Cyanea capillata), the largest extant species of jellyfish and a known prey of the leatherback turtle [14], are known to overlap with the occurrence of leatherback turtles (e.g., [23]).

Despite this overlap, the marine environment is dynamic, with prey often distributed heterogeneously within the landscape over space and time. The location of these prey are likely predictable at a large oceanographic scale, given the long-distance migrations of leatherback turtles and inter-annual fidelity to foraging areas [24], [25]. However, locating prey patches of jellyfish at meso-scales may be more difficult, as they vary spatially and temporally with influences from the movement of surface water and associated nutrients caused by wind [26] and tidal cycles. Because of this heterogeneity in prey presence with space and time, collecting simultaneous information about a predator's prey field and their movements [24], [25], [27] is necessary to try to understand an animal's foraging behavior. However, such sampling is expensive and logistically difficult.

Tracking data from satellite tags deployed over several months and over subsequent years have been used to explore the migratory movements of leatherback turtles, with foraging behavior inferred from diving behavior and dive-shape [9], [10], [28], [29], [30]. Such tracking data have been used to estimate behavioral states of leatherbacks based on changes in movement parameters such as speed and turning angle [31], [32], [33]. Movement data, along with concurrently collected dive data, have been used as a proxy for studying leatherback foraging (e.g., [34]), and sensors that can detect mouth opening [35], [36] and stomach temperature [37] may help determine the timing of prey capture events. Despite the utility of such methods, they are indirect measures of foraging since prey consumption is not observed.

The use of underwater animal-borne video cameras, in conjunction with electronic tagging technologies, provides the opportunity to directly observe foraging behavior. Such camera systems have been deployed on a variety of large marine predators, including pinnipeds, whales, sharks, and cheloniid turtles [38], [39], [40], [41]. Given the challenges associated with conducting in-situ studies of leatherback turtles at sea and recovering data loggers from free-swimming turtles, deployments of animal-borne cameras have been limited to nesting females and have not documented foraging [42]. However, the predictable occurrence of leatherback turtles off the coast of Canada during the summer months [43] provides the opportunity to study foraging leatherbacks when they are presumably acquiring the energy required for southward migration and, for many, reproduction. We attached an animal-borne video camera with an incorporated global positioning system (GPS) to free-ranging leatherback turtles in shelf waters off Nova Scotia, Canada. Our objectives were to describe prey-specific components of foraging behavior (e.g., encounter rate, capture success rate, and handling time), and to estimate daily energy intake, with the aim to better understand the profitability of migratory patterns and implications for characterizing critical foraging habitat of leatherback populations.

Video from the Serrano-V camera was recovered from 19 turtles (Table S1) during 2008 (n = 8), 2009 (n = 4), and 2010 (n = 7). Video duration averaged 1 hour and 53 minutes per turtle (range 0:08–3:38 h). In 2006–2007, when cameras had been deployed on turtles that were first captured, no foraging behavior was recorded (MC James, pers. comm.). However, placement of the camera on free-swimming turtles without capture in 2008–2010 resulted in no observed behavioral effects and foraging behavior was recorded for all camera deployments, suggesting that there was minimal effect of the camera on foraging.

The temperate waters off eastern Canada support one of the largest seasonal foraging populations of sub-adult and adult leatherback turtles in the Atlantic [34]. The 12,000–18,000 km round-trip migrations of leatherbacks from tropical and sub-tropical breeding areas to high latitude foraging areas in the western Atlantic is thought to have evolved to permit turtles to capitalize on seasonally-abundant prey in coastal temperate waters. James et al. [48] estimated an average ∼33% increase in mass of turtles before their initiation of southward migration. Although surface foraging by leatherback turtles has been opportunistically documented in this high latitude foraging area [14], until now, prey encounter rates, prey size, and handling times at depth had not been quantified nor had daily energy intake been estimated.

The range of prey encounter rates reported here presumably reflect patchily distributed jellyfish at fine spatial scales (100s of meters) [26], even though jellyfish were present in about 75% of dives. The high encounter rates of jellyfish per dive lend support to the identification of this area as a foraging “hotspot” for leatherbacks (e.g., [33], [48]). The importance of this foraging area is further supported by our estimate that turtles in this area consume an average of 66,018 kJ and up to 167,797 kJ per day. We were able to measure mass for only two of the turtles equipped with video cameras (mean = 455 kg; Table S1). However, mean curved carapace length of six of the turtles was 154 cm, which also roughly corresponds to a body mass of 455 kg [12], [48]. Thus, if we assume 455 kg was the average mass of individuals in our study, turtles consumed an average of 73% and up to 184% of their body mass per day in wet mass of jellyfish, equating to an average energy intake of 145 kJ•kg⁻¹ or up to 369 kJ•kg⁻¹ per day. The allometric relationship for the field metabolic rate (FMR, kJ•d⁻¹) of an ectothermic reptile [49] suggests the predicted FMR for a 455 kg reptile would be 46.2 kJ•kg⁻¹. Although it has been proposed that leatherback turtles demonstrate some metabolic endothermy (perhaps regionally), using doubly-labeled water, Bradshaw et al. [50] estimated the daily diving metabolic rate (DMR) of leatherbacks nesting in the tropics to be 20.7 kJ•kg⁻¹ or less than half that predicted by for an ectothermic reptile of similar size (and an order of magnitude lower than a similarly-sized endotherm). These estimates were not dissimilar to earlier measurements of leatherback FMR made by Wallace et al. [51], supporting the conclusion that leatherbacks appear to be ectothermic and rely on large body size, insulating fat layers, and thermal inertia to regulate body temperatures above ambient [50]. The turtles in our study consumed an average of 3 (and up to 8) times their daily metabolic requirements as would be estimated by allometry, or 7 (up to 17) times their DMR as measured in nesting leatherbacks.

Although jellyfish are relatively energy-poor [17], our results demonstrate that leatherback predation on high densities of readily-captured lion's mane jellyfish results in high energy intake at least at this time of year, which is consistent with the estimated mass gain of leatherback turtles in Canadian waters. Jellyfish graze on copepods, larvaceans, cladocerans, and meroplankton [52], [53], and leatherbacks in turn graze on patches of these scyphomedusae which tend to ingest the relatively larger size component of available zooplankton prey [52], [54]. Although jellyfish are patchily distributed in time and space, oceanographic features and processes produce predictable foraging opportunities for leatherbacks such that the benefits of reliance on a diet of jellyfish apparently outweigh the energetic costs of migrating to these northern waters. Leatherbacks were not likely prey-limited in our study, as productivity of jellyfish in temperate coastal areas and particularly here in the strongest outflow of the Gulf of St Lawrence can yield excellent foraging opportunities. Also there seems to be little competition for jellyfish apart from niche overlap with ocean sunfish (Mola mola), a species which is also present in the study area during the same times of year.

Our data further suggest that leatherback turtles are efficient predators since no time was wasted on unsuccessful attacks, a foraging strategy similar to that of grazers. Also jellyfish appeared to be completely consumed. Predation rate on high density prey is likely to be limited by handling time or the animal becoming satiated [55]. We found some evidence for this prediction, as turtles while they were already handling other prey in ∼80% of those instances when jellyfish in the field of view of the camera were not targeted. The longer handling times of prey when turtles returned to the surface further suggests that turtles may require further handling for some jellyfish. Given the relatively simple body composition of jellyfish, it is unlikely that digestion time is limiting. Conversely, given the anatomy of lion's mane jellyfish, and particularly those with very large bell diameters and long tentacles, turtles likely face prey handling challenges. Therefore, it is understandable that even with the assistance of the leatherback turtle's specialized esophagus (with papillae pointing towards the stomach), consuming such prey may limit intake. We were unable to distinguish between handling and digesting prey, therefore, it is unclear how digestion may influence the foraging behavior of turtles.

Our estimates of leatherback turtle foraging behavior are based on relatively short-term video records compared to a leatherback's typical 3–5 month high-latitude foraging period in the Northwest Atlantic and, therefore, may not be representative of the entire period. Additional information on daily predation rates, sizes of prey consumed, and variability in energy contents of jellyfish in these northwest Atlantic waters during the summer and fall will be useful to refine these estimates. Nevertheless, our results offer evidence that the feeding tactics of leatherbacks in this high latitude coastal foraging area off Atlantic Canada are energetically profitable and are consistent with estimates of mass gain prior to southward migration and preparation for the breeding season. Longer deployments will be needed to confirm our estimates over time periods that have broader ecological implications, and to place the fine- to meso-scale foraging movements of leatherback turtles within the context of the large-scale migratory movements that have been previously described for this population. Further studies of the foraging decisions that turtles make would also benefit from the collection of concurrent conductivity-time-depth recordings, location and three-dimensional movement data, as well as better information on the prey field.

By simultaneously collecting video and high-resolution dive and ocean temperature data, the purpose-built camera we used to study leatherback foraging behavior during relatively short daytime periods may help confirm inferences of foraging from satellite tracking data that has been collected over much broader spatial and temporal scales. Therefore, this technology offers promise as a tool for determining critical areas of foraging habitat in support of conserving this endangered species.