Search

Background: Animal-borne sensors ('bio-loggers') can record a suite of kinematic and environmental data, which are used to elucidate animal ecophysiology and improve conservation efforts. Machine learning techniques are used for interpreting the large amounts of data recorded by bio-loggers, but there exists no common framework for comparing the different machine learning techniques in this domain. This makes it difficult to, for example, identify patterns in what works well for machine learning-based analysis of bio-logger data. It also makes it difficult to evaluate the effectiveness of novel methods developed by the machine learning community., Methods: To address this, we present the Bio-logger Ethogram Benchmark (BEBE), a collection of datasets with behavioral annotations, as well as a modeling task and evaluation metrics. BEBE is to date the largest, most taxonomically diverse, publicly available benchmark of this type, and includes 1654 h of data collected from 149 individuals across nine taxa. Using BEBE, we compare the performance of deep and classical machine learning methods for identifying animal behaviors based on bio-logger data. As an example usage of BEBE, we test an approach based on self-supervised learning. To apply this approach to animal behavior classification, we adapt a deep neural network pre-trained with 700,000 h of data collected from human wrist-worn accelerometers., Results: We find that deep neural networks out-perform the classical machine learning methods we tested across all nine datasets in BEBE. We additionally find that the approach based on self-supervised learning out-performs the alternatives we tested, especially in settings when there is a low amount of training data available., Conclusions: In light of these results, we are able to make concrete suggestions for designing studies that rely on machine learning to infer behavior from bio-logger data. Therefore, we expect that BEBE will be useful for making similar suggestions in the future, as additional hypotheses about machine learning techniques are tested. Datasets, models, and evaluation code are made publicly available at https://github.com/earthspecies/BEBE , to enable community use of BEBE., Competing Interests: Declarations. Ethics approval and consent to participate: All animal behavior datasets except the Crow dataset were reported in previous publications. Crow behavior data were collected in accordance with ASAB/ABS guidelines and Spanish regulations for animal research, and were authorized by Junta de Castilla y León (licence: EP/LE/681-2019). Competing interest: The authors declare no competing interests., (© 2024. The Author(s).)

Movement ecology has traditionally focused on the movements of animals over large time scales, but, with advancements in sensor technology, the focus can become increasingly fine scale. Accelerometers are commonly applied to quantify animal behaviours and can elucidate fine-scale (<2 s) behaviours. Machine learning methods are commonly applied to animal accelerometry data; however, they require the trial of multiple methods to find an ideal solution. We used tri-axial accelerometers (10 Hz) to quantify four behaviours in Port Jackson sharks ( Heterodontus portusjacksoni ): two fine-scale behaviours (<2 s)-(1) vertical swimming and (2) chewing as proxy for foraging, and two broad-scale behaviours (>2 s-mins)-(3) resting and (4) swimming. We used validated data to calculate 66 summary statistics from tri-axial accelerometry and assessed the most important features that allowed for differentiation between the behaviours. One and two second epoch testing sets were created consisting of 10 and 20 samples from each behaviour event, respectively. We developed eight machine learning models to assess their overall accuracy and behaviour-specific accuracy (one classification tree, five ensemble learners and two neural networks). The support vector machine model classified the four behaviours better when using the longer 2 s time epoch ( F -measure 89%; macro-averaged F -measure: 90%). Here, we show that this support vector machine (SVM) model can reliably classify both fine- and broad-scale behaviours in Port Jackson sharks.

Background: Accurate time-energy budgets summarise an animal's energy expenditure in a given environment, and are potentially a sensitive indicator of how an animal responds to changing resources. Deriving accurate time-energy budgets requires an estimate of time spent in different activities and of the energetic cost of that activity. Bio-loggers (e.g., accelerometers) may provide a solution for monitoring animals such as fur seals that make long-duration foraging trips. Using low resolution to record behaviour may aid in the transmission of data, negating the need to recover the device., Methods: This study used controlled captive experiments and previous energetic research to derive time-energy budgets of juvenile Australian fur seals ( Arctocephalus pusillus) equipped with tri-axial accelerometers. First, captive fur seals and sea lions were equipped with accelerometers recording at high (20 Hz) and low (1 Hz) resolutions, and their behaviour recorded. Using this data, machine learning models were trained to recognise four states-foraging, grooming, travelling and resting. Next, the energetic cost of each behaviour, as a function of location (land or water), season and digestive state (pre- or post-prandial) was estimated. Then, diving and movement data were collected from nine wild juvenile fur seals wearing accelerometers recording at high- and low- resolutions. Models developed from captive seals were applied to accelerometry data from wild juvenile Australian fur seals and, finally, their time-energy budgets were reconstructed., Results: Behaviour classification models built with low resolution (1 Hz) data correctly classified captive seal behaviours with very high accuracy (up to 90%) and recorded without interruption. Therefore, time-energy budgets of wild fur seals were constructed with these data. The reconstructed time-energy budgets revealed that juvenile fur seals expended the same amount of energy as adults of similar species. No significant differences in daily energy expenditure (DEE) were found across sex or season (winter or summer), but fur seals rested more when their energy expenditure was expected to be higher. Juvenile fur seals used behavioural compensatory techniques to conserve energy during activities that were expected to have high energetic outputs (such as diving)., Discussion: As low resolution accelerometry (1 Hz) was able to classify behaviour with very high accuracy, future studies may be able to transmit more data at a lower rate, reducing the need for tag recovery. Reconstructed time-energy budgets demonstrated that juvenile fur seals appear to expend the same amount of energy as their adult counterparts. Through pairing estimates of energy expenditure with behaviour this study demonstrates the potential to understand how fur seals expend energy, and where and how behavioural compensations are made to retain constant energy expenditure over a short (dive) and long (season) period., Competing Interests: The authors declare there are no competing interests.

Background: Functional groups serve two important functions in ecology: they allow for simplification of ecosystem models and can aid in understanding diversity. Despite their important applications, there has not been a universally accepted method of how to define them. A common approach is to cluster species on a set of traits, validated through visual confirmation of resulting groups based primarily on expert opinion. The goal of this research is to determine a suitable procedure for creating and evaluating functional groups that arise from clustering nominal traits., Methods: To do so, we produced a species by trait matrix of 22 traits from 116 fish species from Tasman Bay and Golden Bay, New Zealand. Data collected from photographs and published literature were predominantly nominal, and a small number of continuous traits were discretized. Some data were missing, so the benefit of imputing data was assessed using four approaches on data with known missing values. Hierarchical clustering is utilised to search for underlying data structure in the data that may represent functional groups. Within this clustering paradigm there are a number of distance matrices and linkage methods available, several combinations of which we test. The resulting clusters are evaluated using internal metrics developed specifically for nominal clustering. This revealed the choice of number of clusters, distance matrix and linkage method greatly affected the overall within- and between- cluster variability. We visualise the clustering in two dimensions and the stability of clusters is assessed through bootstrapping., Results: Missing data imputation showed up to 90% accuracy using polytomous imputation, so was used to impute the real missing data. A division of the species information into three functional groups was the most separated, compact and stable result. Increasing the number of clusters increased the inconsistency of group membership, and selection of the appropriate distance matrix and linkage method improved the fit., Discussion: We show that the commonly used methodologies used for the creation of functional groups are fraught with subjectivity, ultimately causing significant variation in the composition of resulting groups. Depending on the research goal dictates the appropriate strategy for selecting number of groups, distance matrix and clustering algorithm combination., Competing Interests: The authors declare there are no competing interests.

Direct measures of energy expenditure are difficult to obtain in marine mammals, and accelerometry may be a useful proxy. Recently its utility has been questioned as some analyses derived their measure of activity level by calculating the sum of accelerometry-based values and then comparing this summation to summed (total) energy expenditure (the so-called "time trap"). To test this hypothesis, we measured oxygen consumption of captive fur seals and sea lions wearing accelerometers during submerged swimming and calculated total and rate of energy expenditure. We compared these values with two potential proxies of energy expenditure derived from accelerometry data: flipper strokes and dynamic body acceleration (DBA). Total number of strokes, total DBA, and submergence time all predicted total oxygen consumption [Formula: see text] ml kg -1 ). However, both total DBA and total number of strokes were correlated with submergence time. Neither stroke rate nor mean DBA could predict the rate of oxygen consumption ([Formula: see text] ml min -1 kg -1 ). The relationship of total DBA and total strokes with total oxygen consumption is apparently a result of introducing a constant (time) into both sides of the relationship. This experimental evidence supports the conclusion that proxies derived from accelerometers cannot estimate the energy expenditure of marine mammals.

The energy expenditure of free-living fur seals and sea lions is difficult to measure directly, but may be indirectly derived from flipper stroke rate. We filmed 10 captive otariids swimming with accelerometers either attached to a harness (Daily Diary: sampling frequency 32 Hz, N =4) or taped to the fur (G6a+: 25 Hz, N =6). We used down sampling to derive four recording rates from each accelerometer (Daily Diary: 32, 16, 8, 4 Hz; G6a+: 25, 20, 10, 5 Hz). For each of these sampling frequencies, we derived 20 combinations of two parameters (RMW, the window size used to calculate the running mean; and m , the minimum number of points smaller than a local maxima used to detect a peak) from the dynamic acceleration of x, z and x+z, to estimate stroke rate from the accelerometers. These estimates differed by up to ∼20% in comparison to the actual number of foreflipper strokes counted from videos. RMW and the choice of axis used to make the calculations (x, z or x+z) had little effect on the overall differences, though the variability was reduced when using x+z. The best m varied depending on the axis used and the sampling frequency; a larger m was needed for higher sampling frequencies. This study demonstrates that when parameters are appropriately tuned, accelerometers are a simple yet valid tool for estimating the stroke rates of swimming otariids., Competing Interests: Competing interestsThe authors declare no competing or financial interests., (© 2017. Published by The Company of Biologists Ltd.)

The study of marine mammal energetics can shed light on how these animals might adapt to changing environments. Their physiological potential to adapt will be influenced by extrinsic factors, such as temperature, and by intrinsic factors, such as sex and reproduction. We measured the standard metabolic rate (SMR) of males and females of three Australian otariid species (two Australian fur seals, three New Zealand fur seals and seven Australian sea lions). Mean SMR ranged from 0.47 to 1.05 l O 2 min -1 , which when adjusted for mass was from 5.33 to 7.44 ml O 2 min -1 kg -1 . We found that Australian sea lion mass-specific SMR (sSMR; in millilitres of oxygen per minute per kilogram) varied little in response to time of year or moult, but was significantly influenced by sex and water temperature. Likewise, sSMR of Australian and New Zealand fur seals was also influenced by sex and water temperature, but also by time of year (pre-moult, moult or post-moult). During the moult, fur seals had significantly higher sSMR than at other times of the year, whereas there was no discernible effect of moult for sea lions. For both groups, females had higher sSMR than males, but sea lions and fur seals showed different responses to changes in water temperature. The sSMR of fur seals increased with increasing water temperature, whereas sSMR of sea lions decreased with increasing water temperature. There were no species differences when comparing animals of the same sex. Our study suggests that fur seals have more flexibility in their physiology than sea lions, perhaps implying that they will be more resilient in a changing environment.

Constructing activity budgets for marine animals when they are at sea and cannot be directly observed is challenging, but recent advances in bio-logging technology offer solutions to this problem. Accelerometers can potentially identify a wide range of behaviours for animals based on unique patterns of acceleration. However, when analysing data derived from accelerometers, there are many statistical techniques available which when applied to different data sets produce different classification accuracies. We investigated a selection of supervised machine learning methods for interpreting behavioural data from captive otariids (fur seals and sea lions). We conducted controlled experiments with 12 seals, where their behaviours were filmed while they were wearing 3-axis accelerometers. From video we identified 26 behaviours that could be grouped into one of four categories (foraging, resting, travelling and grooming) representing key behaviour states for wild seals. We used data from 10 seals to train four predictive classification models: stochastic gradient boosting (GBM), random forests, support vector machine using four different kernels and a baseline model: penalised logistic regression. We then took the best parameters from each model and cross-validated the results on the two seals unseen so far. We also investigated the influence of feature statistics (describing some characteristic of the seal), testing the models both with and without these. Cross-validation accuracies were lower than training accuracy, but the SVM with a polynomial kernel was still able to classify seal behaviour with high accuracy (>70%). Adding feature statistics improved accuracies across all models tested. Most categories of behaviour -resting, grooming and feeding-were all predicted with reasonable accuracy (52-81%) by the SVM while travelling was poorly categorised (31-41%). These results show that model selection is important when classifying behaviour and that by using animal characteristics we can strengthen the overall accuracy., Competing Interests: The authors have declared that no competing interests exist.