ABSTRACT
Marine predators are integral to the functioning of marine ecosystems, and their consumption requirements should be integrated into ecosystem-based management policies. However, estimating prey consumption in diving marine predators requires innovative methods as predator-prey interactions are rarely observable. We developed a novel method, validated by animal-borne video, that uses tri-axial acceleration and depth data to quantify prey capture rates in chinstrap penguins (Pygoscelis antarctica). These penguins are important consumers of Antarctic krill (Euphausia superba), a commercially harvested crustacean central to the Southern Ocean food web. We collected a large data set (n = 41 individuals) comprising overlapping video, accelerometer and depth data from foraging penguins. Prey captures were manually identified in videos, and those observations were used in supervised training of two deep learning neural networks (convolutional neural network (CNN) and V-Net). Although the CNN and V-Net architectures and input data pipelines differed, both trained models were able to predict prey captures from new acceleration and depth data (linear regression slope of predictions against video-observed prey captures = 1.13; R 2 ≈ 0.86). Our results illustrate that deep learning algorithms offer a means to process the large quantities of data generated by contemporary bio-logging sensors to robustly estimate prey capture events in diving marine predators.
ABSTRACT
Incidental capture of non-target species poses a pervasive threat to many marine species, with sometimes devastating consequences for both fisheries and conservation efforts. Because of the well-known importance of vocalizations in cetaceans, acoustic deterrents have been extensively used for these species. In contrast, acoustic communication for sea turtles has been considered negligible, and this question has been largely unexplored. Addressing this challenge therefore requires a comprehensive understanding of sea turtles' responses to sensory signals. In this study, we scrutinized the avenue of auditory cues, specifically the natural sounds produced by green turtles (Chelonia mydas) in Martinique, as a potential tool to reduce bycatch. We recorded 10 sounds produced by green turtles and identified those that appear to correspond to alerts, flight or social contact between individuals. Subsequently, these turtle sounds-as well synthetic and natural (earthquake) sounds-were presented to turtles in known foraging areas to assess the behavioral response of green turtles to these sounds. Our data highlighted that the playback of sounds produced by sea turtles was associated with alert or increased the vigilance of individuals. This therefore suggests novel opportunities for using sea turtle sounds to deter them from fishing gear or other potentially harmful areas, and highlights the potential of our research to improve sea turtles populations' conservation.
Subject(s)
Turtles , Vocalization, Animal , Animals , Turtles/physiology , Vocalization, Animal/physiology , Conservation of Natural Resources/methods , SoundABSTRACT
The urgent need for effective wildlife monitoring solutions in the face of global biodiversity loss has resulted in the emergence of conservation technologies such as passive acoustic monitoring (PAM). While PAM has been extensively used for marine mammals, birds, and bats, its application to primates is limited. Black-and-white ruffed lemurs (Varecia variegata) are a promising species to test PAM with due to their distinctive and loud roar-shrieks. Furthermore, these lemurs are challenging to monitor via traditional methods due to their fragmented and often unpredictable distribution in Madagascar's dense eastern rainforests. Our goal in this study was to develop a machine learning pipeline for automated call detection from PAM data, compare the effectiveness of PAM versus in-person observations, and investigate diel patterns in lemur vocal behavior. We did this study at Mangevo, Ranomafana National Park by concurrently conducting focal follows and deploying autonomous recorders in May-July 2019. We used transfer learning to build a convolutional neural network (optimized for recall) that automated the detection of lemur calls (57-h runtime; recall = 0.94, F1 = 0.70). We found that PAM outperformed in-person observations, saving time, money, and labor while also providing re-analyzable data. Using PAM yielded novel insights into V. variegata diel vocal patterns; we present the first published evidence of nocturnal calling. We developed a graphic user interface and open-sourced data and code, to serve as a resource for primatologists interested in implementing PAM and machine learning. By leveraging the potential of this pipeline, we can address the urgent need for effective primate population surveys to inform conservation strategies.
Subject(s)
Deep Learning , Lemur , Lemuridae , Strepsirhini , Humans , Animals , Madagascar , Parks, Recreational , Acoustics , MammalsABSTRACT
Fibropapillomatosis (FP) threatens the survival of green turtle (Chelonia mydas) populations at a global scale, and human activities are regularly pointed as causes of high FP prevalence. However, the association of ecological factors with the disease's severity in complex coastal systems has not been well established and requires further studies. Based on a set of 405 individuals caught over ten years, this preliminary study provides the first insight of FP in Martinique Island, which is a critical development area for immature green turtles. Our main results are: (i) 12.8% of the individuals were affected by FP, (ii) FP has different prevalence and temporal evolution between very close sites, (iii) green turtles are more frequently affected on the upper body part such as eyes (41.4%), fore flippers (21.9%), and the neck (9.4%), and (iv) high densities of individuals are observed on restricted areas. We hypothesise that turtle's aggregation enhances horizontal transmission of the disease. FP could represent a risk for immature green turtles' survival in the French West Indies, a critical development area, which replenishes the entire Atlantic population. Continuing scientific monitoring is required to identify which factors are implicated in this panzootic disease and ensure the conservation of the green turtle at an international scale.
Subject(s)
Turtles , Animals , Martinique/epidemiology , PrevalenceABSTRACT
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.
ABSTRACT
The identification of sea turtle behaviours is a prerequisite to predicting the activities and time-budget of these animals in their natural habitat over the long term. However, this is hampered by a lack of reliable methods that enable the detection and monitoring of certain key behaviours such as feeding. This study proposes a combined approach that automatically identifies the different behaviours of free-ranging sea turtles through the use of animal-borne multi-sensor recorders (accelerometer, gyroscope and time-depth recorder), validated by animal-borne video-recorder data. We show here that the combination of supervised learning algorithms and multi-signal analysis tools can provide accurate inferences of the behaviours expressed, including feeding and scratching behaviours that are of crucial ecological interest for sea turtles. Our procedure uses multi-sensor miniaturized loggers that can be deployed on free-ranging animals with minimal disturbance. It provides an easily adaptable and replicable approach for the long-term automatic identification of the different activities and determination of time-budgets in sea turtles. This approach should also be applicable to a broad range of other species and could significantly contribute to the conservation of endangered species by providing detailed knowledge of key animal activities such as feeding, travelling and resting.
ABSTRACT
Here we propose a new machine learning algorithm for classification of human activities by means of accelerometer and gyroscope signals. Based on a novel hierarchical system of logistic regression classifiers and a relatively small set of features extracted from the filtered signals, the proposed algorithm outperformed previous work on the DaLiAc (Daily Life Activity) and mHealth datasets. The algorithm also represents a significant improvement in terms of computational costs and requires no feature selection and hyper-parameter tuning. The algorithm still showed a robust performance with only two (ankle and wrist) out of the four devices (chest, wrist, hip and ankle) placed on the body (96.8% vs. 97.3% mean accuracy for the DaLiAc dataset). The present work shows that low-complexity models can compete with heavy, inefficient models in classification of advanced activities when designed with a careful upstream inspection of the data.
Subject(s)
Accelerometry , Activities of Daily Living , Machine Learning , Wearable Electronic Devices , Algorithms , Humans , WristABSTRACT
The change of animal biometrics (body mass and body size) can reveal important information about their living environment as well as determine the survival potential and reproductive success of individuals and thus the persistence of populations. However, weighing individuals like marine turtles in the field presents important logistical difficulties. In this context, estimating body mass (BM) based on body size is a crucial issue. Furthermore, the determinants of the variability of the parameters for this relationship can provide information about the quality of the environment and the manner in which individuals exploit the available resources. This is of particular importance in young individuals where growth quality might be a determinant of adult fitness. Our study aimed to validate the use of different body measurements to estimate BM, which can be difficult to obtain in the field, and explore the determinants of the relationship between BM and size in juvenile green turtles. Juvenile green turtles were caught, measured, and weighed over 6 years (2011-2012; 2015-2018) at six bays to the west of Martinique Island (Lesser Antilles). Using different datasets from this global database, we were able to show that the BM of individuals can be predicted from body measurements with an error of less than 2%. We built several datasets including different morphological and time-location information to test the accuracy of the mass prediction. We show a yearly and north-south pattern for the relationship between BM and body measurements. The year effect for the relationship of BM and size is strongly correlated with net primary production but not with sea surface temperature or cyclonic events. We also found that if the bay locations and year effects were removed from the analysis, the mass prediction degraded slightly but was still less than 3% on average. Further investigations of the feeding habitats in Martinique turtles are still needed to better understand these effects and to link them with geographic and oceanographic conditions.