The role of individual variability on the predictive performance of machine learning applied to large bio-logging datasets.

Animal-borne tagging (bio-logging) generates large and complex datasets. In particular, accelerometer tags, which provide information on behaviour and energy expenditure of wild animals, produce high-resolution multi-dimensional data, and can be challenging to analyse. We tested the performance of commonly used artificial intelligence tools on datasets of increasing volume and dimensionality. By collecting bio-logging data across several sampling seasons, datasets are inherently characterized by inter-individual variability. Such information should be considered when predicting behaviour. We integrated both unsupervised and supervised machine learning approaches to predict behaviours in two penguin species. The classified behaviours obtained from the unsupervised approach Expectation Maximisation were used to train the supervised approach Random Forest. We assessed agreement between the approaches, the performance of Random Forest on unknown data and the implications for the calculation of energy expenditure. Consideration of behavioural variability resulted in high agreement (> 80%) in behavioural classifications and minimal differences in energy expenditure estimates. However, some outliers with < 70% of agreement, highlighted how behaviours characterized by signal similarity are confused. We advise the broad bio-logging community, approaching these large datasets, to be cautious when upscaling predictions, as this might lead to less accurate estimates of behaviour and energy expenditure.

Echolocating toothed whales use ultra-fast echo-kinetic responses to track evasive prey.

Visual predators rely on fast-acting optokinetic responses to track and capture agile prey. Most toothed whales, however, rely on echolocation for hunting and have converged on biosonar clicking rates reaching 500/s during prey pursuits. If echoes are processed on a click-by-click basis, as assumed, neural responses 100× faster than those in vision are required to keep pace with this information flow. Using high-resolution biologging of wild predator-prey interactions, we show that toothed whales adjust clicking rates to track prey movement within 50-200 ms of prey escape responses. Hypothesising that these stereotyped biosonar adjustments are elicited by sudden prey accelerations, we measured echo-kinetic responses from trained harbour porpoises to a moving target and found similar latencies. High biosonar sampling rates are, therefore, not supported by extreme speeds of neural processing and muscular responses. Instead, the neurokinetic response times in echolocation are similar to those of tracking responses in vision, suggesting a common neural underpinning.

In the animal world, split-second decisions determine whether a predator eats, or its prey survives. There is a strong evolutionary advantage to fast reacting brains and bodies. For example, the eye muscles of hunting cheetahs must lock on to a gazelle and keep track of it, no matter how quickly or unpredictably it moves. In fact, in monkeys and primates, these muscles can react to sudden movements in as little as 50 milliseconds ­ faster than the blink of an eye. But what about animals that do not rely on vision to hunt? To find food at night or in the deep ocean, whales and porpoises make short ultrasonic sounds, or 'clicks', and then listen for returning echoes. As they close in on a prey, they need to click faster to get quicker updates on its location. What is unclear is how fast they react to the echoes. Just before a kill, a harbour porpoise can click over 500 times a second: if they wait for the echo from one click before making the next one, they would need responses 100 times faster than human eyes. Exploring this topic is difficult, as it requires tracking predator and prey at the same time. Vance et al. took up the challenge by building sound and movement recorders that attach to whales with suction cups. These were used on two different hunters: deep-diving beaked whales and shallow-hunting harbour porpoises. Both species adapted their click rate depending on how far they were from their prey, but their response times were similar to visual responses in monkeys and humans. This means that whales and porpoises do not act on each echo before clicking again: instead, they respond to groups of tens of clicks at a time. This suggests that their brains may be wired in much the same way as the ones of visual animals. In the ocean, increased human activity creates a dangerous noise pollution that disrupts the delicate hunting mechanism of whales and porpoises. Better understanding how these animals find their food may therefore help conservation efforts.

Long-term sound and movement recording tags to study natural behavior and reaction to ship noise of seals.

The impact of anthropogenic noise on marine fauna is of increasing conservation concern with vessel noise being one of the major contributors. Animals that rely on shallow coastal habitats may be especially vulnerable to this form of pollution.Very limited information is available on how much noise from ship traffic individual animals experience, and how they may react to it due to a lack of suitable methods. To address this, we developed long-duration audio and 3D-movement tags (DTAGs) and deployed them on three harbor seals and two gray seals in the North Sea during 2015-2016.These tags recorded sound, accelerometry, magnetometry, and pressure continuously for up to 21 days. GPS positions were also sampled for one seal continuously throughout the recording period. A separate tag, combining a camera and an accelerometer logger, was deployed on two harbor seals to visualize specific behaviors that helped interpret accelerometer signals in the DTAG data.Combining data from depth, accelerometer, and audio sensors, we found that animals spent 6.6%-42.3% of the time hauled out (either on land or partly submerged), and 5.3%-12.4% of their at-sea time resting at the sea bottom, while the remaining time was used for traveling, resting at surface, and foraging. Animals were exposed to audible vessel noise 2.2%-20.5% of their time when in water, and we demonstrate that interruption of functional behaviors (e.g., resting) in some cases coincides with high-level vessel noise. Two-thirds of the ship noise events were traceable by the AIS vessel tracking system, while one-third comprised vessels without AIS.This preliminary study demonstrates how concomitant long-term continuous broadband on-animal sound and movement recordings may be an important tool in future quantification of disturbance effects of anthropogenic activities at sea and assessment of long-term population impacts on pinnipeds.

High rates of vessel noise disrupt foraging in wild harbour porpoises (Phocoena phocoena).

Shipping is the dominant marine anthropogenic noise source in the world's oceans, yet we know little about vessel encounter rates, exposure levels and behavioural reactions for cetaceans in the wild, many of which rely on sound for foraging, communication and social interactions. Here, we used animal-borne acoustic tags to measure vessel noise exposure and foraging efforts in seven harbour porpoises in highly trafficked coastal waters. Tagged porpoises encountered vessel noise 17-89% of the time and occasional high-noise levels coincided with vigorous fluking, bottom diving, interrupted foraging and even cessation of echolocation, leading to significantly fewer prey capture attempts at received levels greater than 96 dB re 1 µPa (16 kHz third-octave). If such exposures occur frequently, porpoises, which have high metabolic requirements, may be unable to compensate energetically with negative long-term fitness consequences. That shipping noise disrupts foraging in the high-frequency-hearing porpoise raises concerns that other toothed whale species may also be affected.

Ultra-High Foraging Rates of Harbor Porpoises Make Them Vulnerable to Anthropogenic Disturbance.

The question of how individuals acquire and allocate resources to maximize fitness is central in evolutionary ecology. Basic information on prey selection, search effort, and capture rates are critical for understanding a predator's role in its ecosystem and for predicting its response to natural and anthropogenic disturbance. Yet, for most marine species, foraging interactions cannot be observed directly. The high costs of thermoregulation in water require that small marine mammals have elevated energy intakes compared to similar-sized terrestrial mammals [1]. The combination of high food requirements and their position at the apex of most marine food webs may make small marine mammals particularly vulnerable to changes within the ecosystem [2-4], but the lack of detailed information about their foraging behavior often precludes an informed conservation effort. Here, we use high-resolution movement and prey echo recording tags on five wild harbor porpoises to examine foraging interactions in one of the most metabolically challenged cetacean species. We report that porpoises forage nearly continuously day and night, attempting to capture up to 550 small (3-10 cm) fish prey per hour with a remarkable prey capture success rate of >90%. Porpoises therefore target fish that are smaller than those of commercial interest, but must forage almost continually to meet their metabolic demands with such small prey, leaving little margin for compensation. Thus, for these "aquatic shrews," even a moderate level of anthropogenic disturbance in the busy shallow waters they share with humans may have severe fitness consequences at individual and population levels.

Harbour porpoises react to low levels of high frequency vessel noise.

Cetaceans rely critically on sound for navigation, foraging and communication and are therefore potentially affected by increasing noise levels from human activities at sea. Shipping is the main contributor of anthropogenic noise underwater, but studies of shipping noise effects have primarily considered baleen whales due to their good hearing at low frequencies, where ships produce most noise power. Conversely, the possible effects of vessel noise on small toothed whales have been largely ignored due to their poor low-frequency hearing. Prompted by recent findings of energy at medium- to high-frequencies in vessel noise, we conducted an exposure study where the behaviour of four porpoises (Phocoena phocoena) in a net-pen was logged while they were exposed to 133 vessel passages. Using a multivariate generalised linear mixed-effects model, we show that low levels of high frequency components in vessel noise elicit strong, stereotyped behavioural responses in porpoises. Such low levels will routinely be experienced by porpoises in the wild at ranges of more than 1000 meters from vessels, suggesting that vessel noise is a, so far, largely overlooked, but substantial source of disturbance in shallow water areas with high densities of both porpoises and vessels.

Acoustic gaze adjustments during active target selection in echolocating porpoises.

Visually dominant animals use gaze adjustments to organize perceptual inputs for cognitive processing. Thereby they manage the massive sensory load from complex and noisy scenes. Echolocation, as an active sensory system, may provide more opportunities to control such information flow by adjusting the properties of the sound source. However, most studies of toothed whale echolocation have involved stationed animals in static auditory scenes for which dynamic information control is unnecessary. To mimic conditions in the wild, we designed an experiment with captive, free-swimming harbor porpoises tasked with discriminating between two hydrophone-equipped targets and closing in on the selected target; this allowed us to gain insight into how porpoises adjust their acoustic gaze in a multi-target dynamic scene. By means of synchronized cameras, an acoustic tag and on-target hydrophone recordings we demonstrate that porpoises employ both beam direction control and range-dependent changes in output levels and pulse intervals to accommodate their changing spatial relationship with objects of immediate interest. We further show that, when switching attention to another target, porpoises can set their depth of gaze accurately for the new target location. In combination, these observations imply that porpoises exert precise vocal-motor control that is tied to spatial perception akin to visual accommodation. Finally, we demonstrate that at short target ranges porpoises narrow their depth of gaze dramatically by adjusting their output so as to focus on a single target. This suggests that echolocating porpoises switch from a deliberative mode of sensorimotor operation to a reactive mode when they are close to a target.