Deriving Animal Behaviour from High-Frequency GPS: Tracking Cows in Open and Forested Habitat

Examination of head versus body heading may help clarify the extent to which animal movement pathways are structured by environmental cues?

Understanding the processes that determine how animals allocate time to space is a major challenge, although it is acknowledged that summed animal movement pathways over time must define space-time use. The critical question is then, what processes structure these pathways? Following the idea that turns within pathways might be based on environmentally determined decisions, we equipped Arabian oryx with head- and body-mounted tags to determine how they orientated their heads - which we posit is indicative of them assessing the environment - in relation to their movement paths, to investigate the role of environment scanning in path tortuosity. After simulating predators to verify that oryx look directly at objects of interest, we recorded that, during routine movement, > 60% of all turns in the animals' paths, before being executed, were preceded by a change in head heading that was not immediately mirrored by the body heading: The path turn angle (as indicated by the body heading) correlated with a prior change in head heading (with head heading being mirrored by subsequent turns in the path) twenty-one times more than when path turns occurred due to the animals adopting a body heading that went in the opposite direction to the change in head heading. Although we could not determine what the objects of interest were, and therefore the proposed reasons for turning, we suggest that this reflects the use of cephalic senses to detect advantageous environmental features (e.g. food) or to detect detrimental features (e.g. predators). The results of our pilot study suggest how turns might emerge in animal pathways and we propose that examination of points of inflection in highly resolved animal paths could represent decisions in landscapes and their examination could enhance our understanding of how animal pathways are structured.

Animal behaviour on the move: the use of auxiliary information and semi-supervision to improve behavioural inferences from Hidden Markov Models applied to GPS tracking datasets

BACKGROUND

State-space models, such as Hidden Markov Models (HMMs), are increasingly used to classify animal tracks into behavioural states. Typically, step length and turning angles of successive locations are used to infer where and when an animal is resting, foraging, or travelling. However, the accuracy of behavioural classifications is seldom validated, which may badly contaminate posterior analyses. In general, models appear to efficiently infer behaviour in species with discrete foraging and travelling areas, but classification is challenging for species foraging opportunistically across homogenous environments, such as tropical seas. Here, we use a subset of GPS loggers deployed simultaneously with wet-dry data from geolocators, activity measurements from accelerometers, and dive events from Time Depth Recorders (TDR), to improve the classification of HMMs of a large GPS tracking dataset (478 deployments) of red-billed tropicbirds (Phaethon aethereus), a poorly studied pantropical seabird.

METHODS

We classified a subset of fixes as either resting, foraging or travelling based on the three auxiliary sensors and evaluated the increase in overall accuracy, sensitivity (true positive rate), specificity (true negative rate) and precision (positive predictive value) of the models in relation to the increasing inclusion of fixes with known behaviours.

RESULTS

We demonstrate that even with a small informed sub-dataset (representing only 9% of the full dataset), we can significantly improve the overall behavioural classification of these models, increasing model accuracy from 0.77 ± 0.01 to 0.85 ± 0.01 (mean ± sd). Despite overall improvements, the sensitivity and precision of foraging behaviour remained low (reaching 0.37 ± 0.06, and 0.06 ± 0.01, respectively).

CONCLUSIONS

This study demonstrates that the use of a small subset of auxiliary data with known behaviours can both validate and notably improve behavioural classifications of state space models of opportunistic foragers. However, the improvement is state-dependant and caution should be taken when interpreting inferences of foraging behaviour from GPS data in species foraging on the go across homogenous environments.

Mapping Welfare: Location Determining Techniques and Their Potential for Managing Cattle Welfare—A Review

Several studies have suggested that precision livestock farming (PLF) is a useful tool for animal welfare management and assessment. Location, posture and movement of an individual are key elements in identifying the animal and recording its behaviour. Currently, multiple technologies are available for automated monitoring of the location of individual animals, ranging from Global Navigation Satellite Systems (GNSS) to ultra-wideband (UWB), RFID, wireless sensor networks (WSN) and even computer vision. These techniques and developments all yield potential to manage and assess animal welfare, but also have their constraints, such as range and accuracy. Combining sensors such as accelerometers with any location determining technique into a sensor fusion system can give more detailed information on the individual cow, achieving an even more reliable and accurate indication of animal welfare. We conclude that location systems are a promising approach to determining animal welfare, especially when applied in conjunction with additional sensors, but additional research focused on the use of technology in animal welfare monitoring is needed.

Habitat amount or landscape configuration: Emerging HotSpot analysis reveals the importance of habitat amount for a grassland bird in South Dakota

Habitat loss and fragmentation are two important drivers of biodiversity decline. Understanding how species respond to landscape composition and configuration in dynamic landscapes is of great importance for informing the conservation and management of grassland species. With limited conservation resources, prescribed management targeted at the appropriate landscape process is necessary for the effective management of species. We used pheasants (Phasianus colchicus) across South Dakota, USA as a model species to identify environmental factors driving spatiotemporal variation in population productivity. Using an emerging Hotspot analysis, we analyzed annual count data from 105 fixed pheasant brood routes over a 24-year period to identify high (HotSpot) and low (ColdSpot) pheasant population productivity areas. We then applied classification and regression tree modeling to evaluate landscape attributes associated with pheasant productivity among spatial scales (500 m and 1000 m). We found that the amount of grassland at a local spatial scale was the primary factor influencing an area being a HotSpot. Our results also demonstrated non-significant or weak effects of fragmentation per se on pheasant populations. These findings are in accordance with the habitat amount hypothesis highlighting the importance of habitat amount in the landscape for maintaining and increasing the pheasant population. We, therefore, recommend that managers should focus on increasing the total habitat area in the landscape and restoring degraded habitats. Our method of identifying areas of high productivity across the landscape can be applied to other species with count data.

Intelligent Systems Using Sensors and/or Machine Learning to Mitigate Wildlife-Vehicle Collisions: A Review, Challenges, and New Perspectives

Worldwide, the persistent trend of human and animal life losses, as well as damage to properties due to wildlife-vehicle collisions (WVCs) remains a significant source of concerns for a broad range of stakeholders. To mitigate their occurrences and impact, many approaches are being adopted, with varying successes. Because of their increased versatility and increasing efficiency, Artificial Intelligence-based methods have been experiencing a significant level of adoption. The present work extensively reviews the literature on intelligent systems incorporating sensor technologies and/or machine learning methods to mitigate WVCs. Included in our review is an investigation of key factors contributing to human-wildlife conflicts, as well as a discussion of dominant state-of-the-art datasets used in the mitigation of WVCs. Our study combines a systematic review with bibliometric analysis. We find that most animal detection systems (excluding autonomous vehicles) are relying neither on state-of-the-art datasets nor on recent breakthrough machine learning approaches. We, therefore, argue that the use of the latest datasets and machine learning techniques will minimize false detection and improve model performance. In addition, the present work covers a comprehensive list of associated challenges ranging from failure to detect hotspot areas to limitations in training datasets. Future research directions identified include the design and development of algorithms for real-time animal detection systems. The latter provides a rationale for the applicability of our proposed solutions, for which we designed a continuous product development lifecycle to determine their feasibility.

Decision rules for determining terrestrial movement and the consequences for filtering high-resolution global positioning system tracks: a case study using the African lion (Panthera leo)

The combined use of global positioning system (GPS) technology and motion sensors within the discipline of movement ecology has increased over recent years. This is particularly the case for instrumented wildlife, with many studies now opting to record parameters at high (infra-second) sampling frequencies. However, the detail with which GPS loggers can elucidate fine-scale movement depends on the precision and accuracy of fixes, with accuracy being affected by signal reception. We hypothesized that animal behaviour was the main factor affecting fix inaccuracy, with inherent GPS positional noise (jitter) being most apparent during GPS fixes for non-moving locations, thereby producing disproportionate error during rest periods. A movement-verified filtering (MVF) protocol was constructed to compare GPS-derived speed data with dynamic body acceleration, to provide a computationally quick method for identifying genuine travelling movement. This method was tested on 11 free-ranging lions (Panthera leo) fitted with collar-mounted GPS units and tri-axial motion sensors recording at 1 and 40 Hz, respectively. The findings support the hypothesis and show that distance moved estimates were, on average, overestimated by greater than 80% prior to GPS screening. We present the conceptual and mathematical protocols for screening fix inaccuracy within high-resolution GPS datasets and demonstrate the importance that MVF has for avoiding inaccurate and biased estimates of movement.

The Relationship Between GPS Sampling Interval and Estimated Daily Travel Distances in Chacma Baboons (Papio ursinus)

Modern studies of animal movement use the Global Positioning System (GPS) to estimate animals’ distance traveled. The temporal resolution of GPS fixes recorded should match those of the behavior of interest; otherwise estimates are likely to be inappropriate. Here, we investigate how different GPS sampling intervals affect estimated daily travel distances for wild chacma baboons (Papio ursinus). By subsampling GPS data collected at one fix per second for 143 daily travel distances (12 baboons over 11–12 days), we found that less frequent GPS fixes result in smaller estimated travel distances. Moving from a GPS frequency of one fix every second to one fix every 30 s resulted in a 33% reduction in estimated daily travel distance, while using hourly GPS fixes resulted in a 66% reduction. We then use the relationship we find between estimated travel distance and GPS sampling interval to recalculate published baboon daily travel distances and find that accounting for the predicted effect of sampling interval does not affect conclusions of previous comparative analyses. However, if short-interval or continuous GPS data—which are becoming more common in studies of primate movement ecology—are compared with historical (longer interval) GPS data in future work, controlling for sampling interval is necessary.

"HerdGPS-Preprocessor"-A Tool to Preprocess Herd Animal GPS Data; Applied to Evaluate Contact Structures in Loose-Housing Horses

Sensors delivering information on the position of farm animals have been widely used in precision livestock farming. Global Positioning System (GPS) sensors are already known from applications in military, private and commercial environments, and their application in animal science is increasing. However, as trade-offs between sensor cost, battery life and sensor weight have to be made, GPS based studies scheduling long data collection periods and including a high number of animals, have to deal with problems like high hardware costs and data disruption during recharging of sensors. Furthermore, human-animal interaction due to sensor changing at the end of battery life interferes with the animal behaviour under analysis. The present study thus proposes a setting to deal with these challenges and offers the software tool "HerdGPS-Preprocessor", because collecting position data from multiple animals nonstop for several weeks produces a high amount of raw data which needs to be sorted, preprocessed and provided in a suitable format per animal and day. The software tool "HerdGPS-Preprocessor" additionally outputs contact lists to enable a straight analysis of animal contacts. The software tool was exemplarily deployed for one month of daily and continuous GPS data of 40 horses in a loose-housing boarding facility in northern Germany. Contact lists were used to generate separate networks for every hour, which are then analysed with regard to the network parameter density, diameter and clique structure. Differences depending on the day and the day time could be observed. More dense networks with more and larger cliques were determined in the hours prior to the opening of additional pasture.

Distances Walked by Long Established and Newcomer Horses in an Open Stable System in Northern Germany

Group housing is claimed to possibly provide horses with a species-appropriate movement possibility, and hence, better welfare. Thus, this study analyzed the daily walked distances of 51 horses held in one group in a "HIT Active Stable" (Hinrichs Innovation + Technik) in Northern Germany by using global positioning system (GPS) technology during a 7 ½-month time span. The daily walking distances of the whole group, as well as newcomers, were investigated. The horses traveled an average of 8.43 km/day. Linear mixed models were applied. The observation day had a significant effect on the daily walking distances (P < .01) due to season and the available area per horse. The age as covariate also had a significant effect (P < .01). The breed had no significant effect (P = .96). No significant differences were found in sex (P = .69), which can be explained by the fact that only mares and geldings were investigated, which do not show increasing locomotion caused by sexual behavior as stallions do. On six of the first nine days, new horses moved significantly more compared to the remaining 24 of the 30 observation days directly after individuals' inclusion. This is probably due to more exploration and rank-fighting behavior. Similar walking distances were seen among the horses on the single observation days because all horses had to travel the same distance to reach resources. Further, it is suspected that not all horses can sufficiently live out their urges to move, especially in winter, when pasture is inaccessible.

Elucidating three-way interactions between soil, pasture and animals that regulate nitrous oxide emissions from temperate grazing systems

Pasture-based livestock farming contributes considerably to global emissions of nitrous oxide (N2O), a powerful greenhouse gas approximately 265 times more potent than carbon dioxide. Traditionally, the estimation of N2O emissions from grasslands is carried out by means of plot-scale experiments, where externally sourced animal excreta are applied to soils to simulate grazing conditions. This approach, however, fails to account for the impact of different sward types on the composition of excreta and thus the functionality of soil microbiomes, creating unrealistic situations that are seldom observed under commercial agriculture. Using three farming systems under contrasting pasture management strategies at the North Wyke Farm Platform, an instrumented ruminant grazing trial in Devon, UK, this study measured N2O emissions from soils treated with cattle urine and dung collected within each system as well as standard synthetic urine shared across all systems, and compared these values against those from two forms of controls with and without inorganic nitrogen fertiliser applications. Soil microbial activity was regularly monitored through gene abundance to evaluate interactions between sward types, soil amendments, soil microbiomes and, ultimately, N2O production. Across all systems, N2O emissions attributable to cattle urine and standard synthetic urine were found to be inconsistent with one another due to discrepancy in nitrogen content. Despite previous findings that grasses with elevated levels of water-soluble carbohydrates tend to generate lower levels of N2O, the soil under high sugar grass monoculture in this study recorded higher emissions when receiving excreta from cattle fed the same grass. Combined together, our results demonstrate the importance of evaluating environmental impacts of agriculture at a system scale, so that the feedback mechanisms linking soil, pasture, animals and microbiomes are appropriately considered.

Use of Predicted Behavior from Accelerometer Data Combined with GPS Data to Explore the Relationship between Dairy Cow Behavior and Pasture Characteristics

Our aim in this study was to investigate whether the behaviors of dairy cows on pasture, predicted with accelerometer data and combined with GPS data, can be used to better understand the relationship between behaviors and pasture characteristics. During spring 2018, 26 Holstein cows were equipped with a 3D-accelerometer and a GPS sensor fixed on a neck-collar for five days. The cows grazed alternatively in permanent and in temporary grasslands. The structural elements, soil moisture, slope and botanical characteristics were identified. Behaviors were predicted every 10 s from the accelerometer data and combined with the GPS data. The time-budgets expressed in each characterized zone of 8 m × 8 m were calculated. The relation between the time-budgets and pasture characteristics was explored with a linear mixed model. In the permanent grassland, dairy cows spent more time under a tree to ruminate (p < 0.001) and to rest (p < 0.001) and more time to graze in areas with Holcus lanatus (p < 0.001). In the temporary grassland, behavior was influenced by the external environment (presence of other animals on the farm; p < 0.05). Thus, this methodology seems relevant to better understand the relationship between the behaviors of dairy cows and grazing conditions to develop precision grazing.

Method for Classifying Behavior of Livestock on Fenced Temperate Rangeland in Northern China

Different livestock behaviors have distinct effects on grassland degradation. However, because direct observation of livestock behavior is time- and labor-intensive, an automated methodology to classify livestock behavior according to animal position and posture is necessary. We applied the Random Forest algorithm to predict livestock behaviors in the Horqin Sand Land by using Global Positioning System (GPS) and tri-axis accelerometer data and then confirmed the results through field observations. The overall accuracy of GPS models was 85% to 90% when the time interval was greater than 300–800 s, which was approximated to the tri-axis model (96%) and GPS-tri models (96%). In the GPS model, the linear backward or forward distance were the most important determinants of behavior classification, and nongrazing was less than 30% when livestock travelled more than 30–50 m over a 5-min interval. For the tri-axis accelerometer model, the anteroposterior acceleration (–3 m/s²) of neck movement was the most accurate determinant of livestock behavior classification. Using instantaneous acceleration of livestock body movement more precisely classified livestock behaviors than did GPS location-based distance metrics. When a tri-axis model is unavailable, GPS models will yield sufficiently reliable classification accuracy when an appropriate time interval is defined.

LG, Flores-Martínez JJ, Wilkinson GS, Yovel Y. Acoustic evaluation of behavioral states predicted from GPS tracking: a case study of a marine fishing bat

BACKGROUND

Multiple methods have been developed to infer behavioral states from animal movement data, but rarely has their accuracy been assessed from independent evidence, especially for location data sampled with high temporal resolution. Here we evaluate the performance of behavioral segmentation methods using acoustic recordings that monitor prey capture attempts.

METHODS

We recorded GPS locations and ultrasonic audio during the foraging trips of 11 Mexican fish-eating bats, Myotis vivesi, using miniature bio-loggers. We then applied five different segmentation algorithms (k-means clustering, expectation-maximization and binary clustering, first-passage time, hidden Markov models, and correlated velocity change point analysis) to infer two behavioral states, foraging and commuting, from the GPS data. To evaluate the inference, we independently identified characteristic patterns of biosonar calls ("feeding buzzes") that occur during foraging in the audio recordings. We then compared segmentation methods on how well they correctly identified the two behaviors and if their estimates of foraging movement parameters matched those for locations with buzzes.

RESULTS

While the five methods differed in the median percentage of buzzes occurring during predicted foraging events, or true positive rate (44-75%), a two-state hidden Markov model had the highest median balanced accuracy (67%). Hidden Markov models and first-passage time predicted foraging flight speeds and turn angles similar to those measured at locations with feeding buzzes and did not differ in the number or duration of predicted foraging events.

CONCLUSION

The hidden Markov model method performed best at identifying fish-eating bat foraging segments; however, first-passage time was not significantly different and gave similar parameter estimates. This is the first attempt to evaluate segmentation methodologies in echolocating bats and provides an evaluation framework that can be used on other species.

Modelling animal movement as Brownian bridges with covariates

BACKGROUND

The ability to observe animal movement and possible correlates has increased strongly over the past decades. Methods to analyze trajectories have developed in parallel, but many tools fail to make an immediate connection between a movement model, covariates of the movement, and animal space use.

METHODS

Here I develop a novel method based on the Brownian Bridge Movement Model that facilitates investigating and testing covariates of movement. The model makes it possible to flexibly investigate different covariates including, for example, periodic movement patterns.

RESULTS

I applied the Brownian Bridge Covariates Model (BBCM) to simulated trajectories demonstrating its ability to reproduce the parameters used for the simulation. I also applied the model to a GPS trajectory of a meerkat, showing its application to empirical data. The value of the model was shown by testing the interaction between maximal daily temperature and the daily movement pattern.

CONCLUSION

This model produces accurate parameter estimates for covariates of the movements and location error in simulated trajectories. Application to the meerkat trajectory also produced plausible parameter estimates. This new method opens the possibility to directly test hypotheses about the influence of covariates on animal movement while linking these to space-use estimates.

How much can we trust GPS wildlife tracking? An assessment in semi-free-ranging Crested Ibis Nipponia nippon

GPS tracking has been increasingly used for wildlife studies in recent decades, but its performance has not been fully assessed, especially for newly developed lightweight transmitters. We assessed the performance of eight GPS transmitters developed in China by attaching them to Crested Ibises Nipponia nippon confined to two acclimation cages mimicking real habitats. We calculated the distance between GPS locations and the centroid of the cages as the positioning error, and used the 95% (95th percentile) positioning errors to define the accuracy. The positioning success averaged 92.0%, which is much higher than that of previous studies. Locations were not evenly distributed by Location Class (LC), with the LC A and B locations accounting for 88.7%. The observed 95% positioning error in the locations of LC A (9-39 m) and B (11-41 m) was quite accurate, while up to 6.9-8.8% of poor-quality locations were detected in LC C and D with >100 m or even >1, 000 m positioning error. Positioning success and accuracy were different between the test sites, probably due to the difference in vegetation structure. Thus, we argue that the tested transmitters could provide a large proportion of high-quality data for fine-scale studies, and a number of poor-quality locations that need attention. We suggest that the HPOD (horizontal dilution of precision) or PDOP (positional dilution of precision) be reported instead of the LC as a measurement of location accuracy for each location to ensure identification and filtering of implausible locations.

A novel behavioral model of the pasture-based dairy cow from GPS data using data mining and machine learning techniques

A better understanding of the behavior of individual grazing dairy cattle will assist in improving productivity and welfare. Global positioning systems (GPS) applied to cows could provide a means of monitoring grazing herds while overcoming the substantial efforts required for manual observation. Any model of behavioral prediction using GPS needs to be accurate and robust by accounting for inter-cow variation as well as atmospheric effects. We evaluated the performance using a series of machine learning algorithms on GPS data collected from 40 pasture-based dairy cows over 4 mo. A feature extraction step was performed on the collected raw GPS data, which resulted in 43 different attributes. The evaluated behaviors were grazing, resting, and walking. Classifier learners were built using 10 times 10-fold cross validation and tested on an independent test set. Results were evaluated using a variety of statistical significance tests across all parameters. We found that final model selection depended upon level of performance and model complexity. The classifier learner deemed most suitable for this particular problem was JRip, a rule-based learner (classification accuracy=0.85; false positive rate=0.10; F-measure=0.76; area under the receiver operating curve=0.87). This model will be used in further studies to assess the behavior and welfare of pasture-based dairy cows.

Developing and Integrating Advanced Movement Features Improves Automated Classification of Ciliate Species

Recent advances in tracking technologies such as GPS or video tracking systems describe the movement paths of individuals in unprecedented details and are increasingly used in different fields, including ecology. However, extracting information from raw movement data requires advanced analysis techniques, for instance to infer behaviors expressed during a certain period of the recorded trajectory, or gender or species identity in case data is obtained from remote tracking. In this paper, we address how different movement features affect the ability to automatically classify the species identity, using a dataset of unicellular microbes (i.e., ciliates). Previously, morphological attributes and simple movement metrics, such as speed, were used for classifying ciliate species. Here, we demonstrate that adding advanced movement features, in particular such based on discrete wavelet transform, to morphological features can improve classification. These results may have practical applications in automated monitoring of waste water facilities as well as environmental monitoring of aquatic systems.