Loggerhead turtles (Caretta caretta) are a circumglobal species of sea turtle found throughout temperate and tropical oceans and seas [1]. Loggerhead turtle nesting is restricted to a few locations in major ocean basins such as the Southeastern USA, the Mediterranean, Oman, Western Australia, and Southern Japan, where females lay their eggs on sandy beaches [2], [3]. After hatchlings leave the nesting beaches, they are thought to remain oceanic for 7–12 years before migrating to coastal habitats [4]. Despite good swimming abilities, juvenile loggerhead turtles are thought to drift passively for a significant portion of their existence on the high seas [5]. In contrast, Polovina et al. [6] found that active swimming seemed to be a large component of overall movement for oceanic juveniles. It is likely that a behavioral response cued by current flow orientation (i.e., rheotaxis) is involved. With passive drifting, active swimming, and rheotactic responses, it is important to know the magnitude and direction of ocean currents the oceanic juveniles have to contend with, as it is clear that the response of an organism to a moving flow field can be highly complex [7]. For oceanic juvenile loggerhead turtles, a key issue is their placement in the vertical portion of the water column, which will be closely linked to their diving behavior.

Oceanic juvenile diving behavior is not well studied, with scant data from only a small number of tagged individuals. Studies in the Atlantic have shown that oceanic juveniles spend ∼75% of their time in the upper 5 m of the water column [4]. Studies in the Pacific have indicated oceanic juveniles may spend more time in deeper layers. For example, Polovina et al. [8], and Polovina et al. [9] found that oceanic juveniles spend ∼90% of their time in the upper 40 m of the water column, with 75% of the time spent in the upper 15 m, and 40% of the time in the upper 1 m. Howell et al. [10] found that oceanic juveniles spend ∼90% of their time in the upper 15 m and 80% of their time in the upper 5 m of the water column. While loggerhead turtles can dive to much deeper depths, it is clear oceanic juveniles primarily use the upper layers (5–40 m) of the water column where the wind-driven component may be more important than large scale (e.g., geostrophic) water movements. Although studies have attempted to compare oceanic juvenile movement to ocean currents, these approaches often use geostrophic currents, which may not be appropriate for this situation. Alternative approaches using field measurements or high-resolution ocean circulation models are needed, with careful attention to matching the turtle data to the appropriate vertical layers of current flow. Combining turtle movement data with depth appropriate ocean circulation models will aid in our understanding of rheotaxis in juvenile turtle ecology.

Rheotaxis in the aquatic environment is defined as the response orientation of an organism to a current flow. The rheotaxis can either be positive (turning to face into the current) or negative (turning to face away from the current). The mechanism involved in the rheotaxis can be active (e.g., turning caused by behavior) or passive (e.g., turning caused by body shape hydrodynamics). Rheotaxis is thought to occur throughout the animal kingdom and has been suggested for organisms as different as spermatozoa [11], tadpoles [12], and whale sharks [13]. Many occurrences have been documented from laboratory studies, but the experimental apparatus often confounds such studies since multiple cues may be available to the organism making it difficult to isolate pure rheotaxis. Pure rheotaxis occurs when the organism is responding only to the current flow and not following any chemical signal or similar fluid-borne plume. Often, orientation to a current is facilitated artificially by the laboratory apparatus via visual or tactile feedback to the container or substrate, which may or may not mimic natural conditions for the organism under study. Field studies with oceanic organisms likely offer the best opportunity to document true rheotaxis whereby the primary cue available to the organism is the current flow with few other easily sensed cues available to assist in orientation.

Vestibular senses such as the inner ear of vertebrates and statoliths of invertebrates, as well as the mechanoreceptory lateral line of fishes and amphibians, are likely useful for detecting bodily orientation with respect to a current flow. In addition to the normal suite of senses (hearing, sight, touch, smell, taste), it is worth noting that loggerheads, like all vertebrates, have vestibular sensory organs in the inner ear [14] for detecting motion. While this sense is generally useful for equilibrium and coordinated movement, the vestibular sensory organs are thought to also be used by sea turtles for subsurface orientation to wave direction based on the orbital movements of the water parcel within the wave swell [15]. Additionally, loggerheads have been well demonstrated to have magnetic orientation abilities [16].

To investigate the role of rheotaxis, an analysis of movement dynamics was undertaken using satellite tag data of oceanic juvenile loggerhead turtles in the South Pacific and currents flows from a variety of sources. This tagging experiment was not initially targeted towards a rheotaxis experiment but was instead an exploratory tagging experiment to characterize range of juvenile loggerhead turtle movement in the South Pacific and to ascertain presence of any potential “hot spots” [17], [18]. However, the data are amenable for an ex post facto investigation of rheotaxis, when compared to a suite of prevailing flow fields for the region. These current flow sources include actual field measurements (NOAA, National Oceanic and Atmospheric Administration, drifter buoys), satellite remotely sensed estimates (NOAA OSCAR), and modeled estimates (HYCOM). Where possible, vertical layering of current flow was examined in conjunction with the tagged animal movements.

The daily SSM satellite tag tracks are shown in Figure 1, with both the initial location and the location of final tag transmission sites indicated. The 42 turtles swam in a variety of directions with some tendency for either a southwest or southeast direction. However, several turtles ventured north, with one of the longest tracks to the northwest before transmission ceased in the vicinity of French Polynesia. One remarkable trajectory went to the southwest and passed through Bass Strait between Australia and Tasmania before transmission ceased. The final location of this tag was in offshore waters southwest of Port Lincoln, South Australia. A detailed summary of all tag movements is shown in Table 1. The number of transmission days ranged from 13–350 days with a median value of 178 days.

Seasonal patterns of HYCOM shallow current flow over the time and space domain of this study are shown in Figure 2. The primary oceanographic features of the region appear to be adequately captured by the HYCOM data including, for example, the summer intensification of the East Australia Current (EAC) running southward along the eastern coast of Australia, the field of numerous mesoscale eddies in the Tasman Front region located off Eastern Australia extending to north of New Zealand, and the primarily winter Zeehan Current flowing to the southeast near Bass Strait and Tasmania. Current fields from the NOAA drifter buoys and OSCAR data were qualitatively similar to the surface HYCOM fields shown in Figure 2, and similarly for other HYCOM layers (intermediate and deep). It is difficult to detect vector differences visually over such a large scale map; therefore, other current fields are not shown as figures. It should be noted that the primary analysis of this study involved finer level comparisons in both space and time through examination of the resultant daily swimming vectors. Statistical evaluation of the different representations of current fields was not within the scope of this paper, but should be examined in greater detail in the future. Since small changes in currents (e.g., shear, Ekman dynamics) may be critically important for a swimming or drifting organism, this analysis used a broad array of current fields, which also served as a means of addressing sensitivity to changes in vertical stratification and diving behavior.

Over the duration of this study, the currents encountered by the oceanic juveniles were characterized similarly by all 5 measures for both speed and direction (Table 2). The average current speed encountered by the tagged turtles was estimated to be 21.37 cm/sec, averaged over the 5 current measurements examined (ranging from 14.55–28.62 cm/sec). Tag movement speed averaged 28.70 cm/sec. Swimming speed averaged 30.01 cm/sec (ranging from 25.46–32.94 cm/sec). The average current direction was to the North-Northeast, the average tag movement direction was to the South-Southeast, and the average swimming direction was to the South-Southwest (Figure 3).

The tag movement direction, current direction, swimming direction, and the difference between the swimming and current directions are illustrated in Figure 4 as polar histogram distributions for the assumption of HYCOM shallow currents. The Rayleigh’s z test indicated that for all currents there were no significant departures from uniformity for the tag movement directions, the current directions, or the swimming directions. However, for drifters and all HYCOM layers there were highly significant departures from uniformity for the difference between the swimming direction and the HYCOM current direction (Table 3). When standardized to a polar orientation where north is the direction of the prevailing HYCOM current, all analyses indicated that the differences tabulated primarily in the relative southward direction, indicating that the swimming direction was against the HYCOM current (Figure 4).

The second-order statistical analyses were entirely consistent with the ad-hoc adjusted degrees of freedom approach. Analyses of all currents except OSCAR displayed evidence of non-uniformity for the difference between the swimming vector and the current vector (Table 4). All group means were clustered about the direction opposing the prevailing current direction. Across the 42 tags the mean of the second-order means was nearly exactly opposed to the prevailing shallow HYCOM current direction at 180.80 degrees with all tags displaying a similar value (95% C.I. = 177.32–184.39). Individual tags behaved similarly, with respect to the difference between swimming vector and current vector, across all currents with the exception of OSCAR (Figure 5). The second-order statistical analysis for spatial and temporal autocorrelation also showed a similar pattern against the prevailing shallow HYCOM current direction with a mean of the second-order means across all 16 spatial and temporal strata of 184.80 degrees with all strata displaying a similar value (95% C.I. = 175.20–196.39).

The absolute swimming direction was decomposed into an East/West u-component and a North/South v-component. These u-component and v-component from the HYCOM shallow analysis were fit to GAMs with a spatial term, a seasonal term, and a corresponding current term (u-component or v-component, depending on the swimming component being fit). All terms were highly significant and further tuning of the GAM models were unnecessary, aside from adjustments to degrees of freedom to avoid overfitting (determined visually when the GAM smoother functions had excessive inflection points). The spatial term for the swimming u-component suggested that the swimming direction was both a function of longitude and latitude with continued westward swimming predicted in the west, and continued eastward swimming in the east, with a zone of high eastward swimming centered at 30S and 165W (Figure 6). The spatial term for the swimming v-component suggested that swimming direction was both a function of longitude and latitude with continued northward swimming to the north, and generally southward swimming continuing to the south and to the east (Figure 7). There was a peak in eastward swimming in July–August and a slight peak in northward swimming in April–May. The relationship between swimming u-component and swimming v-component was negative and nearly linear despite the GAM smoothing spline functions being capable of curvilinear additive functions with variable degrees of freedom. The spatial and temporal terms for the intermediate and deep HYCOM GAM analyses were qualitatively similar to the shallow HYCOM GAM analysis, differing primarily in magnitude of the estimated swimming values since the surface layer tends to move more quickly than deeper layers and, therefore, has an associated faster estimated swimming speed to reconcile with the same net tag displacement.

The polar histograms of the difference between the swimming directions and the prevailing current directions, coupled with the negatively linear GAM terms for swimming u-component and v-component as a function of the corresponding u-component and v-component, are strong evidence of positive rheotaxis occurring in an oceanic organism. There are fewer confounding cues available to an oceanic organism than to the same organism in an experimental laboratory apparatus where presumed rheotactic responses could be simpler orientation to an odor gradient, temperature gradient, or aided by the fixed orientation of the apparatus. For example, if the organism is positioned on the substrate or has a visual fix on the substrate, and wishes to respond to a current, it is a simple matter to re-orient towards the current given the tactile or visual cues of the surrounding environment. However, for an organism in a homogenous and moving liquid environment, both the detection and re-orientation towards the current can be much more complicated. The data and analyses presented here propose that oceanic juvenile loggerhead turtles have such a capability.

It is noteworthy that the comparisons using OSCAR currents were not significant for showing a rheotactic response. While this might be compelling evidence to counter the proposed finding, we feel the most likely explanation for the weaker patterns in the OSCAR analysis is that it is the only ocean current product not providing a daily estimate, as OSCAR is a 5-day composite dataset due to the geometry of satellite orbital cycles and altimeter/scatterometer swath widths. It is difficult to measure animal behavior cued to the environment if the environmental measure is an average over 5 days, while the behavior is measured over the course of a single day. Given the daily NOAA drifter buoy analysis showed evidence of rheotaxis, and that the OSCAR data is essentially tuned to NOAA drifter buoy movement, we feel the lack of significant finding in the OSCAR analysis does not in any way preclude existence of positive rheotaxis in oceanic juvenile loggerhead turtles. The consistent finding in all 3 strata of HYCOM currents (with the HYCOM shallow arguably the most suitable estimate) remains strong evidence of positive rheotaxis.

A similar study on green and leatherback turtles did not find any evidence of non-random directional swimming with respect to the prevailing current [33], [34]. It should be noted however that these studies on green and leatherback turtles used a current product very similar to the OSCAR data (composite of geostrophic and wind-driven components) and is of a relatively coarse resolution in both space and time due to the satellite track geometry in comparison to HYCOM data. Again, it may be difficult to infer animal behavior from a product that is spanning over multiple days in its estimation and expression. Geostrophic flow fields are based on satellite altimeter sensors with orbit repeat cycles of typically 10 days. While wind data from scatterometer sensors can be daily, the final merged product still requires much smoothing and extrapolation for a daily estimate of flow at any given location. Additional flow fields should be examined, particularly modeled flow fields which can better match the tagged animal data resolution, or flow fields generated from simple drifter buoys appear capable of capturing the rheotaxic effect. Perhaps unfortunately, several other turtle studies examining pelagic movement and oceanography have also relied on coarse resolution merged geostrophic and wind-stress products [35], [36].

The vector geometry approach used in this analysis could also be interpreted with respect to mechanisms other than active upstream-oriented swimming. In fact, the findings do not indicate that oceanic juvenile loggerhead turtles are swimming upstream as a migrating salmon would, for example, countering and overcoming an encountered flow field. The data indicate the transport is resisted yet not necessarily overcome in all instances, based on the vector directions and magnitudes. The turtles may be able to resist advection by some means such as a person swimming in a river might backpedal or gently scull with one’s hands when entrained in the main flow field if attempting to maintain position as cued by visual fixes on the shoreline or river bottom. If the turtle was simply attempting to stay in the same location while knowingly being advected, the resultant behavior to maintain that position would manifest as a swimming vector against the background current flow such as documented here. Knowledge of body orientation would be helpful towards resolving this question. Body orientation with respect to prevailing current direction, swimming direction, and net displacement direction would be very insightful towards understanding what the individual is attempting to do.

The resultant swimming vector against the current flow could also be interpreted to be caused by frictional drag slowdown of an object in a flow field, or what is often referred to as slippage. Slippage can account for the difference between a predicted trajectory and an actual trajectory if the object is moving slower than the ambient flow field due to frictional drag on the object. Slippage estimates of surface-tethered drifter buoys have indicated that slippage can be on the order of 13% of the existing current [37], which for this particular situation would predict slippage of 2.8 cm/sec (given an average current of 21.37 cm/sec). Other researchers have indicated that drifter buoy slippage can be 2 cm/sec [38] or 4.5–9 cm/sec [39]. None of these estimates of slippage come close to the estimated 30 cm/sec swimming vector of this study. Hence, attributing the rheotactic response to simple frictional slippage is quite unlikely. The swimming magnitude is approximately 10 times any known slippage factor. Furthermore, the buoy estimated slippage is also accounting for the tether line and a surface buoy, which the sea turtles do not have. Slippage of a simple object would be substantially less than the 2–9 cm/sec estimates from tethered drifter buoys.

Frictional drag of the satellite tag could be similar to the slippage process, whereby this and potential windage on the emergent tag and/or carapace could serve as a mechanism for disrupting active swimming and/or imposing differential drift from surface currents [40]. Drag estimates for the species, carapace length, and tags in this study would be on the order of a 20–22% increase in drag, not including windage effects for sustained surface intervals. However, since the sea turtles appear to be swimming against the current, the estimated rheotaxis is likely conservative, i.e., in the absence of tag drag the magnitude of the swimming response may be higher than what is presented here. Nevertheless tag drag should be addressed in all tagging studies involving attachment of tags to mobile animals, particularly if the size of the tag is large relative to the body size of the organism. Size, weight, buoyancy should be carefully considered [41].

It remains speculative to identify the mechanism for detecting a current while being moved in that same current. However, directional cues might be inferred by traversing through a region of current shear or by using a similar processing of differential movement at the air-sea interface. This would require knowledge about the state of motion in the adjacent layer, which may be difficult. Wave action might be useful as an indicator of current direction. While the interplay of wind, waves, and currents is a complex process, it remains plausible that an organism could glean some measure of directional movement by the nature of the prevailing wave action [15]. Wind driven currents would likely be the simplest to estimate, since there should be a strong differential in the speed of the wind and the speed of the water, with a nearly constant offset due to the Coriolis effect. Oscillatory movement in the water column might also be useful to infer direction of travel, if wave action and current flow are tightly coupled, as in the case of wind-driven surface currents. Particulate matter in the water could be used as a visual fix to facilitate this orientation. The utility of visual cues could be experimentally examined with existing data to examine the rheotactic patterns separated by day and night with attention to moon phase. If visual cues to interfaces, waves, particulate matter, etc. are critical, then this pattern should break down on dark nights. It is also conceivable that there may be a multiple cues utilized, particularly if a wide range of oceanographic conditions are encountered and if there has been evolution of a long-distance migration route [42].

Another potential mechanism is that an object being pushed by water currents will experience differential pressure on one side of its body versus the opposing side. An application of this is seen in the rheotactic responses experimentally examined using artificial intelligence. In this example, a positively rheotactic fish robot was successfully designed and tested using 2 pressure sensors to determine orientation with respect to a current flow [43]. Such a design is very analogous to the mechanosensory receptors on a lateral line for example, which is found on fish and some amphibians. Nerves embedded in the sea turtle carapace may be able to function in this fashion, though this has yet to be documented. Electronic sensors and circuitry are a poor substitute for living organisms and their neurological capabilities. Hence, it would seem quite likely that simple rheotactic responses would have evolved if this type of response were adaptive for the species. While this artificial intelligence response has been shown to occur in a narrow flow tunnel, it is mechanistically identical to an oceanic condition where a flow field is pushing (or pulling) at an object of different (higher) density and not simply being carried along with it in uniform fluidic unity. Furthermore, flow fields in the ocean do change over time and space, and the differential response of different masses and densities of objects therein might allow for a simple directional fix on the advective movement using changes in pressure.

The adaptive value of rheotaxis can exist if there is benefit to swimming upstream. At its most rudimentary form, this could be a means to minimize dispersive losses to an organism that relies on land. This would allow an organism and progeny to remain in the vicinity of the optimal habitat chosen to reproduce in. Swimming against an advective flow in this situation would be adaptive if mortality was high due to insufficient habitat in other portions of the aquatic system. Generally, there are two responses by an organism when it is pushed: it can either retreat or push back. In this instance the taxis appears to be positive, in that once detected, the reaction is to swim towards the stimulus. It would be extremely useful to have knowledge of body orientation to determine if the turtle is swimming headlong into the flow or being carried with the flow, yet arresting its advection by some means. Directional sensors and/or video cameras should be incorporated into future telemetry studies.

If the flows were predominantly meridional in a particular area then it would be advantageous to resist advection since transport to either lower latitudes or higher latitudes would likely be deleterious for organisms preferring a certain temperature range or with other environmental constraints. While flow fields are difficult to generalize over time and space, the location of this study area is in the western portion of the South Pacific Gyre, a large water mass generally spinning in a counter-clockwise direction below the equator between Australia and South America. Ectothermic organisms such as sea turtles would likely be more concerned with avoiding cold water than warm water and, hence, a swimming response against the southward current might manifest itself as adaptive behavior. The importance of temperature for loggerhead habitat has been well studied in the North Pacific Ocean [22], [44], [45]. Additional study in the South Pacific Ocean is clearly needed.

Several other studies are in progress using data from this particular tagging experiment. The swimming u and v estimated from this study will be utilized in a computer simulation intended to mimic the movement of oceanic juvenile loggerhead turtles from a similar point-source release (Kobayashi et al., in review). Additionally, a wider suite of environmental variables have been examined and will be used to characterize oceanic juvenile habitat in the South Pacific, similar to what was accomplished in the North Pacific [22].

In conclusion, the significant findings of this study include the identification of a positive rheotaxis response in a pelagic organism. This finding will aid in our understanding of oceanic movements of juvenile marine turtles. This paper is another example of active orientation including likely multiple sensory cues that allow juvenile turtles to orient and offset passive displacement due simply to wind and ocean currents.