Decision tree classification of behaviors in the nesting process of green turtles (Chelonia mydas) from tri-axial acceleration data

Estimation of the Maternal Investment of Sea Turtles by Automatic Identification of Nesting Behavior and Number of Eggs Laid from a Tri-Axial Accelerometer

Simple Summary

During the reproduction period, female sea turtles come several times onto the beaches to lay their eggs. Monitoring of the nesting populations is therefore important to estimate the state of a population and its future. However, measuring the clutch size and frequency of sea turtles is tedious work that requires rigorous monitoring of the nesting site throughout the breeding season. In order to support the fieldwork, we propose an automatic method to remotely record the behavior on land of the sea turtles from animal-attached sensors; an accelerometer. The proposed method estimates, with an accuracy of 95%, the behaviors on land of sea turtles and the number of eggs laid. This automatic method should therefore help researchers monitor nesting sea turtle populations and contribute to improving global knowledge on the demographic status of these threatened species.

Abstract

Monitoring reproductive outputs of sea turtles is difficult, as it requires a large number of observers patrolling extended beaches every night throughout the breeding season with the risk of missing nesting individuals. We introduce the first automatic method to remotely record the reproductive outputs of green turtles (Chelonia mydas) using accelerometers. First, we trained a fully convolutional neural network, the V-net, to automatically identify the six behaviors shown during nesting. With an accuracy of 0.95, the V-net succeeded in detecting the Egg laying process with a precision of 0.97. Then, we estimated the number of laid eggs from the predicted Egg laying sequence and obtained the outputs with a mean relative error of 7% compared to the observed numbers in the field. Based on deployment of non-invasive and miniature loggers, the proposed method should help researchers monitor nesting sea turtle populations. Furthermore, its use can be coupled with the deployment of accelerometers at sea during the intra-nesting period, from which behaviors can also be estimated. The knowledge of the behavior of sea turtle on land and at sea during the entire reproduction period is essential to improve our knowledge of this threatened species.

Bottlenose dolphin habitat and management factors related to activity and distance traveled in zoos and aquariums

High-resolution non-invasive cetacean tagging systems can be used to investigate the influence of habitat characteristics and management factors on behavior by quantifying activity levels and distance traveled by bottlenose dolphins (Tursiops truncatus and Tursiops aduncus) in accredited zoos and aquariums. Movement Tags (MTags), a bio-logging device, were used to record a suite of kinematic and environmental information outside of formal training sessions as part of a larger study titled "Towards understanding the welfare of cetaceans in zoos and aquariums" (colloquially called the Cetacean Welfare Study). The purpose of the present study was to explore if and how habitat characteristics, environmental enrichment programs, and training programs were related to the distance traveled and energy expenditure of dolphins in accredited zoos and aquariums. Bottlenose dolphins in accredited zoos and aquariums wore MTags one day per week for two five-week data collection periods. Overall dynamic body acceleration (ODBA), a proxy for energy expenditure, and average distance traveled per hour (ADT) of 60 dolphins in 31 habitats were examined in relation to demographic, habitat, and management factors. Participating facilities were accredited by the Alliance for Marine Mammal Parks and/or Aquariums and the Association of Zoos & Aquariums. Two factors were found to be related to ADT while six factors were associated with ODBA. The results showed that enrichment programs were strongly related to both ODBA and ADT. Scheduling predictable training session times was also positively associated with ADT. The findings suggested that habitat characteristics had a relatively weak association with ODBA and were not related to ADT. In combination, the results suggested that management practices were more strongly related to activity levels than habitat characteristics.

Behaviour Classification on Giraffes (Giraffa camelopardalis) Using Machine Learning Algorithms on Triaxial Acceleration Data of Two Commonly Used GPS Devices and Its Possible Application for Their Management and Conservation

Averting today's loss of biodiversity and ecosystem services can be achieved through conservation efforts, especially of keystone species. Giraffes (Giraffa camelopardalis) play an important role in sustaining Africa's ecosystems, but are 'vulnerable' according to the IUCN Red List since 2016. Monitoring an animal's behavior in the wild helps to develop and assess their conservation management. One mechanism for remote tracking of wildlife behavior is to attach accelerometers to animals to record their body movement. We tested two different commercially available high-resolution accelerometers, e-obs and Africa Wildlife Tracking (AWT), attached to the top of the heads of three captive giraffes and analyzed the accuracy of automatic behavior classifications, focused on the Random Forests algorithm. For both accelerometers, behaviors of lower variety in head and neck movements could be better predicted (i.e., feeding above eye level, mean prediction accuracy e-obs/AWT: 97.6%/99.7%; drinking: 96.7%/97.0%) than those with a higher variety of body postures (such as standing: 90.7-91.0%/75.2-76.7%; rumination: 89.6-91.6%/53.5-86.5%). Nonetheless both devices come with limitations and especially the AWT needs technological adaptations before applying it on animals in the wild. Nevertheless, looking at the prediction results, both are promising accelerometers for behavioral classification of giraffes. Therefore, these devices when applied to free-ranging animals, in combination with GPS tracking, can contribute greatly to the conservation of giraffes.

Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers

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.

Quantifying the impacts of future sea level rise on nesting sea turtles in the southeastern United States

Sandy beaches, a necessary habitat for nesting sea turtles, are increasingly under threat as they become squeezed between human infrastructure and shorelines that are changing as a result of rising sea levels. Forecasting where shifting sandy beaches will be obstructed and how that directly impacts coastal nesting species is necessary for successful conservation and management. Predicting changes to coastal nesting areas is difficult because of a lack of consensus on the physical attributes used by females in nesting site choice. In this study, we leveraged long-term data sets of nesting localities for two sea turtle species, loggerhead sea turtle, Caretta caretta, and green sea turtle, Chelonia mydas, within four barrier island National Seashores in the southeastern United States to predict future nesting beach area based on where these species currently nest in relation to mean high water. We predicted the future location of nesting areas based on a sea level rise scenario for 2100 and quantified how impervious surfaces will inhibit future beach movement, which will impact both the total available nesting area and the percentage of nesting area predicted to flood following a hurricane-related storm surge. Contrary to our expectations, those barrier islands with the greatest levels of human infrastructure were not projected to experience the greatest percentage of sea turtle nesting area loss due to sea level rise or storm surge events. Notably, loss of nesting beach areas will not have equal impacts across the four Seashores; the Seashore projected to have the least amount of total nesting area lost and percentage nesting area lost currently has the highest nesting densities of our two study species, suggesting that even low levels of beach loss could have substantial impacts on future nesting densities and disproportionate impacts on the population growth of these species. Our novel method of estimating current and future nesting beach area can be broadly applied to studies requiring a bounded area that encompasses the part of a beach used by nesting coastal species and will be useful in comparing future global nesting densities and population trajectories under projected future sea level rise and storm surge activity.

Buried treasure-marine turtles do not 'disguise' or 'camouflage' their nests but avoid them and create a decoy trail

After laying their eggs and refilling the egg chamber, sea turtles scatter sand extensively around the nest site. This is presumed to camouflage the nest, or optimize local conditions for egg development, but a consensus on its function is lacking. We quantified activity and mapped the movements of hawksbill (Eretmochelys imbricata) and leatherback (Dermochelys coriacea) turtles during sand-scattering. For leatherbacks, we also recorded activity at each sand-scattering position. For hawksbills, we recorded breathing rates during nesting as an indicator of metabolic investment and compared with published values for leatherbacks. Temporal and inferred metabolic investment in sand-scattering was substantial for both species. Neither species remained near the nest while sand-scattering, instead moving to several other positions to scatter sand, changing direction each time, progressively displacing themselves from the nest site. Movement patterns were highly diverse between individuals, but activity at each sand-scattering position changed little between completion of egg chamber refilling and return to the sea. Our findings are inconsistent with sand-scattering being to directly camouflage the nest, or primarily for modifying the nest-proximal environment. Instead, they are consistent with the construction of a series of dispersed decoy nests that may reduce the discovery of nests by predators.

Combined use of two supervised learning algorithms to model sea turtle behaviours from tri-axial acceleration data

Accelerometers are becoming ever more important sensors in animal-attached technology, providing data that allow determination of body posture and movement and thereby helping to elucidate behaviour in animals that are difficult to observe. We sought to validate the identification of sea turtle behaviours from accelerometer signals by deploying tags on the carapace of a juvenile loggerhead (Caretta caretta), an adult hawksbill (Eretmochelys imbricata) and an adult green turtle (Chelonia mydas) at Aquarium La Rochelle, France. We recorded tri-axial acceleration at 50 Hz for each species for a full day while two fixed cameras recorded their behaviours. We identified behaviours from the acceleration data using two different supervised learning algorithms, Random Forest and Classification And Regression Tree (CART), treating the data from the adult animals as separate from the juvenile data. We achieved a global accuracy of 81.30% for the adult hawksbill and green turtle CART model and 71.63% for the juvenile loggerhead, identifying 10 and 12 different behaviours, respectively. Equivalent figures were 86.96% for the adult hawksbill and green turtle Random Forest model and 79.49% for the juvenile loggerhead, for the same behaviours. The use of Random Forest combined with CART algorithms allowed us to understand the decision rules implicated in behaviour discrimination, and thus remove or group together some 'confused' or under--represented behaviours in order to get the most accurate models. This study is the first to validate accelerometer data to identify turtle behaviours and the approach can now be tested on other captive sea turtle species.

Improved supervised classification of accelerometry data to distinguish behaviors of soaring birds

Soaring birds can balance the energetic costs of movement by switching between flapping, soaring and gliding flight. Accelerometers can allow quantification of flight behavior and thus a context to interpret these energetic costs. However, models to interpret accelerometry data are still being developed, rarely trained with supervised datasets, and difficult to apply. We collected accelerometry data at 140Hz from a trained golden eagle (Aquila chrysaetos) whose flight we recorded with video that we used to characterize behavior. We applied two forms of supervised classifications, random forest (RF) models and K-nearest neighbor (KNN) models. The KNN model was substantially easier to implement than the RF approach but both were highly accurate in classifying basic behaviors such as flapping (85.5% and 83.6% accurate, respectively), soaring (92.8% and 87.6%) and sitting (84.1% and 88.9%) with overall accuracies of 86.6% and 92.3% respectively. More detailed classification schemes, with specific behaviors such as banking and straight flights were well classified only by the KNN model (91.24% accurate; RF = 61.64% accurate). The RF model maintained its accuracy of classifying basic behavior classification accuracy of basic behaviors at sampling frequencies as low as 10Hz, the KNN at sampling frequencies as low as 20Hz. Classification of accelerometer data collected from free ranging birds demonstrated a strong dependence of predicted behavior on the type of classification model used. Our analyses demonstrate the consequence of different approaches to classification of accelerometry data, the potential to optimize classification algorithms with validated flight behaviors to improve classification accuracy, ideal sampling frequencies for different classification algorithms, and a number of ways to improve commonly used analytical techniques and best practices for classification of accelerometry data.

Seeing It All: Evaluating Supervised Machine Learning Methods for the Classification of Diverse Otariid Behaviours

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.

The Use of Acceleration to Code for Animal Behaviours; A Case Study in Free-Ranging Eurasian Beavers Castor fiber

Recent technological innovations have led to the development of miniature, accelerometer-containing electronic loggers which can be attached to free-living animals. Accelerometers provide information on both body posture and dynamism which can be used as descriptors to define behaviour. We deployed tri-axial accelerometer loggers on 12 free-ranging Eurasian beavers Castor fiber in the county of Telemark, Norway, and on four captive beavers (two Eurasian beavers and two North American beavers C. canadensis) to corroborate acceleration signals with observed behaviours. By using random forests for classifying behavioural patterns of beavers from accelerometry data, we were able to distinguish seven behaviours; standing, walking, swimming, feeding, grooming, diving and sleeping. We show how to apply the use of acceleration to determine behaviour, and emphasise the ease with which this non-invasive method can be implemented. Furthermore, we discuss the strengths and weaknesses of this, and the implementation of accelerometry on animals, illustrating limitations, suggestions and solutions. Ultimately, this approach may also serve as a template facilitating studies on other animals with similar locomotor modes and deliver new insights into hitherto unknown aspects of behavioural ecology.

Optimizing acceleration-based ethograms: the use of variable-time versus fixed-time segmentation

BACKGROUND

Animal-borne accelerometers measure body orientation and movement and can thus be used to classify animal behaviour. To univocally and automatically analyse the large volume of data generated, we need classification models. An important step in the process of classification is the segmentation of acceleration data, i.e. the assignment of the boundaries between different behavioural classes in a time series. So far, analysts have worked with fixed-time segments, but this may weaken the strength of the derived classification models because transitions of behaviour do not necessarily coincide with boundaries of the segments. Here we develop random forest automated supervised classification models either built on variable-time segments generated with a so-called 'change-point model', or on fixed-time segments, and compare for eight behavioural classes the classification performance. The approach makes use of acceleration data measured in eight free-ranging crab plovers Dromas ardeola.

RESULTS

Useful classification was achieved by both the variable-time and fixed-time approach for flying (89% vs. 91%, respectively), walking (88% vs. 87%) and body care (68% vs. 72%). By using the variable-time segment approach, significant gains in classification performance were obtained for inactive behaviours (95% vs. 92%) and for two major foraging activities, i.e. handling (84% vs. 77%) and searching (78% vs. 67%). Attacking a prey and pecking were never accurately classified by either method.

CONCLUSION

Acceleration-based behavioural classification can be optimized using a variable-time segmentation approach. After implementing variable-time segments to our sample data, we achieved useful levels of classification performance for almost all behavioural classes. This enables behaviour, including motion, to be set in known spatial contexts, and the measurement of behavioural time-budgets of free-living birds with unprecedented coverage and precision. The methods developed here can be easily adopted in other studies, but we emphasize that for each species and set of questions, the presented string of work steps should be run through.