Statistical modelling of individual animal movement: an overview of key methods and a discussion of practical challenges
 587 Downloads
 4 Citations
Abstract
With the influx of complex and detailed tracking data gathered from electronic tracking devices, the analysis of animal movement data has recently emerged as a cottage industry among biostatisticians. New approaches of ever greater complexity are continue to be added to the literature. In this paper, we review what we believe to be some of the most popular and most useful classes of statistical models used to analyse individual animal movement data. Specifically, we consider discretetime hidden Markov models, more general statespace models and diffusion processes. We argue that these models should be core components in the toolbox for quantitative researchers working on stochastic modelling of individual animal movement. The paper concludes by offering some general observations on the direction of statistical analysis of animal movement. There is a trend in movement ecology towards what are arguably overly complex modelling approaches which are inaccessible to ecologists, unwieldy with large data sets or not based on mainstream statistical practice. Additionally, some analysis methods developed within the ecological community ignore fundamental properties of movement data, potentially leading to misleading conclusions about animal movement. Corresponding approaches, e.g. based on Lévy walktype models, continue to be popular despite having been largely discredited. We contend that there is a need for an appropriate balance between the extremes of either being overly complex or being overly simplistic, whereby the discipline relies on models of intermediate complexity that are usable by general ecologists, but grounded in welldeveloped statistical practice and efficient to fit to large data sets.
Keywords
Hidden Markov model Measurement error Ornstein–Uhlenbeck process Statespace model Stochastic differential equation Time series1 Introduction
Movement ecology seeks to infer why organisms move through space and what constraints operate on them as they do. It is the study of how movement shapes their overall ecology, and the factors, both intrinsic and extrinsic, that influence movement. Movement ecology broadly concerns the study of both animals and plant movement and dispersal. While there are commonalities in some aspects of their study, there are also many differences. In this paper we concern ourselves purely with individual organismal movement as measured through instruments and sensors which record position at relatively short timescales. Although it is possible that some of the aspects we discuss also apply to plants, practically this means we are nearly always referring to the study of animal movement.
The discipline has been driven by the possibility of telemetering the paths of freemoving animals navigating their natural habitats. Devices such as satellite and GPS tags, radio tracking, radar and acoustic monitoring have generated large and, to ecologists and statisticians alike, largely unfamiliar data sets. Each technology has its limitations and strengths in terms of accuracy, frequency and longevity. One fundamental feature of movement ecology is that it takes a “bottomup” approach to understanding population processes: it works by tracking individuals and seeking to infer properties of populations. This brings several challenges, not least that these individuallevel data do not sit easily within the remit of the conventional biometric toolbox employed by field ecologists. Statistically, movement processes are reasonably described as noisy, nonlinear and highly spatially and temporally correlated. As a result, ecologists and statisticians alike have searched for new tools for understanding animal movement.
Yet, movement ecology has also grappled with its conceptual foundations. Despite being widely recognized as a fundamental process governing population dynamics, the rationale for studying movement can be somewhat illdefined. In other areas of ecological data analysis, say estimation of animal abundance, the motivation is clear, namely to determine population size. Moreover, the reasons for wanting such an estimate are clear. We maintain that this is not always the case in movement ecology. While observations of movement, especially for a new species, are generally interesting, the use of movement analyses, especially in applied ecological settings such as conservation or management, is not always coherently stated. Additionally, movement studies often suffer from low sample sizes and, even in an informal sense, a lack of statistical design (Patterson and Hartmann 2011; McGowan et al. 2016). While these problems can be difficult or even impossible to overcome, this is of obvious importance for arriving at a set of statistical methods which are suitable for purpose.
Statistical methods for the analysis of individual movements can be problematic in at least two ways. First, we contend that some of the models being developed arguably are overly complex, both structurally and in terms of the machinery required to fit them. In these cases, the complexity can be beyond what is required to address the study goals. Care is therefore needed that complex models are not constructed based on data from a small number of individuals or of short duration. The danger of this is that much effort is expended on capturing aspects of a possibly unrepresentative data set. At the other extreme lies another problem, namely that some movement models are hopelessly simplistic, e.g. relying on a singleparameter model to describe a vast array of complex behaviours. Yet, literal interpretation of the mathematical properties of such simple models has been offered as evidence for strong claims about animal movement.
While similar issues could be identified in many scientific endeavours, there is a need for movement ecology to recognize these problems. Addressing these requires the discipline clarifying its collective aims and consciously seeking to build workable and wellunderstood analysis approaches that can be widely applied. Part of this process is the identification of a set of models (a) that are reasonably appropriate to the nature of most individuals’ movement data and associated research questions, (b) whose statistical properties are well understood and (c) that are sufficiently computationally efficient that they may be applied to representative, i.e. sufficiently large, data sets.
Real animal movements and behaviour are, of course, highly complex and dynamic. There is a limit to what can be observed from position and sensor data alone. Therefore, to parse out gross features from the data, it often makes sense to assume movement processes to be driven by switches between behavioural modes, and several of the modelling approaches that we discuss below do allow for different phases or modes of movement. There is a mounting number of papers which seek to make interpretation of animals’ movements tractable by assuming that they typically move in a set of movement modes—e.g. rapid movements between regions (“transit” or “exploratory” movements) vs. highly resident (“encamped”) movements which are related to activities such as resting or foraging. These approaches are at the core of what we cover here.
From the outset we admit that our treatment is myopic in the sense that several other widely used statistical approaches are not discussed in detail—in particular those that look at broader spatial and temporal scales, at which behavioural state switching is most likely irrelevant. If considered at all, we provide only a brief overview of those other approaches and instead focus on three types of models—hidden Markov models (HMMs), more general statespace models (SSMs) and diffusion processes—in much more detail. We identified these as key tools for conducting statistical analyses of animal movement data collected at the individual level. Accordingly, the paper is therefore restricted mostly to consideration of models that analyse trajectories (or metrics derived from them). Most commonly, these trajectories are expressed as time series of geographical coordinates. Our lack of attention to other areas of movement ecology, or to ecological settings where movement is important, such as resource and habitat selection, is simply because we regard these as related, but separate branches of the discipline, characterized by different statistical problems and associated techniques. We also note that even when we consider animal trajectory data alone, many telemetry devices record concurrent sensor data that are useful for extracting behavioural signals. For instance, most instruments deployed on airbreathing marine predators (marine mammals, seabirds) collect not only position estimates, but also data describing diving behaviour. These sorts of data are obviously relevant to characterize the state of the animal in sufficient detail in SSMs (to name an example). In acknowledging this issue, we must also admit that we do not, in this review paper, consider in any detail techniques or models to tackle these combined data, although we note in passing that combining types of data is perhaps less of a conceptual and technical jump from existing techniques than is often appreciated. For an example of an analysis of such a more complex data set using essentially only standard methods, see DeRuiter et al. (2016), where time series comprising seven data streams, corresponding to different measures of blue whale activity, are analysed using a joint stateswitching model.
The goal of this paper is therefore to provide a relatively detailed examination of selected methods for analysis of individual animal tracking data. Our intended audience are the statistically minded ecologists and ecologically minded statisticians who are actively working with these data, day to day, although we hope that the material below might also provide a technically honest entry point for the uninitiated. This is in contrast to previous reviews in this area (e.g. Patterson et al. 2009), which have been for a broader ecological audience and by necessity have needed to omit the technical intricacies.
2 Animal movement data
Data sets on animal movement typically contain positions in space over a sequence of discrete points in time, observed by using global positioning system (GPS) telemetry technology, for instance. For landbased animals, this will usually be in the horizontal plane, while for aerial and marine life, geographical space studies also exist in one dimension, such as vertical movements of aquatic species—this choice clearly being dependent on the questions being raised. A few studies exist of where highresolution threedimensional movement data are available (e.g. Laplanche et al. 2015), but these are less common and we do not consider them in this review. Sampling of locations is often made at regular time intervals, and the hidden Markov model (HMM) and statespace model (SSM) approaches described below are, with some important exceptions, restricted to such data and are not generally well suited to observations that are irregularly spaced in time (but see Sect. 5.6). In contrast, continuoustime approaches, such as those based on diffusion models (Sect. 6), straightforwardly accommodate irregular time intervals, whether they arise by design, through missing data, or through the limitations of the sensor technology.
Sampling intervals vary considerably across studies, ranging from fractions of seconds up to days. The time difference between observations affects what types of inference can be made and what modelling approaches can be applied. It is therefore important that care should be taken when choosing the sampling interval and that researchers think ahead to the necessary analysis prior to deployment of telemetry instruments. If the goal of an analysis is to infer the behavioural states of an animal, or proxies thereof, then observations need to be made at a temporal scale that is meaningful with regard to the behavioural dynamics of the animal.

the bivariate positions themselves or increments of these (velocity or displacement) in either dimension;

distances between successively observed positions (usually referred to as the step lengths);

compass directions (headings);

changes of direction between successive relocations (usually referred to as the turning angles).
While this review primarily discusses the case of location data, there are many other types of animal movement data, such as location derived from light sensors, accelerometers, magnetometers, measurements of bearing, that are used to derive position information. Additionally, some deployments of instruments return a mixture of these. Finally, we note that a wide range of technologies exist that provide information on finescale behaviours indeterminable from locational data alone. Readers are directed to Cooke et al. (2004), Cooke et al. (2013), Rutz and Hays (2009), Wilmers et al. (2015) and LeosBarajas et al. (2016) for detailed reviews.
3 Overview of individuallevel models for animal movement
In most cases, the type of data at hand largely dictates which modelling approach to use. Given data, a decision whether to use HMMs, SSMs or diffusion processes can broadly be summarized as follows.
If the data are collected at regular sampling units, e.g. hourly, daily or every time a marine mammal comes to the surface to breathe, then most often a discretetime model would be used. If in addition the measurement error is negligible, then HMMs represent a natural, accessible and most likely computationally feasible approach, which would typically be used to make inference, for example, on how animals interact with their environment (see Sect. 4). If, however, the measurement error is nonnegligible, then SSMs account for this, at the cost of an increase in complexity, regarding both the implementation and the computational effort. Like HMMs, SSMs can be used for making general inference, though in some cases they are applied simply to filter the noisy locations (see Sect. 5).
If the data are not equally spaced, i.e. if there is no regularity in the sampling process, then continuoustime models such as diffusion processes constitute the most natural choice. Of course, these models can also be applied to regularly sampled data. The main drawback of those models, from a user’s perspective anyway, is that they are less accessible than HMMs and SSMs (see Sect. 6).
There are, of course, exceptions to the above crude classification of how different types of data are tied to specific modelling approaches. For example, for irregularly spaced data, instead of using a continuoustime approach, it has been suggested to interpolate the recorded locations on the required grid, then fitting an SSM that accounts for the corresponding error due to the interpolation.
4 Hidden Markov models: discrete time, no measurement error
4.1 Model formulation
HMMs are natural candidates for modelling animal movement data. Indeed, HMMs have successfully been used to analyse the movement of, inter alia, caribou (Franke et al. 2004), fruit flies (Holzmann et al. 2006), tuna (Patterson et al. 2009), panthers (van de Kerk et al. 2015), woodpeckers (McKellar et al. 2015) and white sharks (Towner et al. 2016). One typically considers bivariate time series comprising step lengths and turning angles, regularly spaced in time and assumed to be observed with no or only negligible error. Within the HMM framework, such a time series is typically referred to as the statedependent process, since each of the corresponding observations is assumed to be generated by one of N distributions as determined by the state of an underlying hidden (i.e. unobserved) Nstate Markov chain. The states of the Markov chain can be interpreted as providing rough classifications of the behavioural dynamics (e.g. more active vs. less active). In the following, we describe the key assumptions involved in basic HMMs and also how model fitting for this class of models can easily be accomplished. Almost all the methods described below are implemented in the recently released R package moveHMM (Michelot et al. 2016).
Most of the HMMs considered in movement ecology thus far involve a twostate Markov chain, where each state is associated with a different correlated random walk (CRW) pattern. CRWs involve correlation in directionality and can be expressed by a turning angle distribution with mass centred either on zero (for positive correlation) or on \(\pi \) (for negative correlation). The two states of the corresponding models are often associated with the animal being either “encamped” (with mostly short step lengths and many turnings) or “exploring” (with, on average, longer step lengths and more directed movement, as expressed by smaller turning angles). This kind of labelling of the states should be made with caution; it is generally accepted that these states merely provide convenient proxies of an animal’s actual behavioural state (see Sect. 7.4).
4.2 Inference for HMMs
A popular likelihoodbased alternative is given by the expectationmaximization (EM) algorithm. The EM algorithm also involves an iterative scheme for finding the maximum likelihood estimate, by alternating between updating the conditional expectation of the states (given the data and the current model parameters), and updating the model parameters based on the completedata loglikelihood where the unknown states are replaced by their conditional expectations. We do not elaborate on EM here, since we agree with MacDonald (2014) in there being no apparent reasons to prefer it over direct likelihood maximization, which is easier to implement.
From a Bayesian perspective, the efficient evaluation of the likelihood is also a great advantage. There is then no need to augment the data with the unknown states: we can simply use the likelihood as above, applying the forward algorithm, and carry out either a simple MCMC algorithm over the parameter space, such as random walk Metropolis–Hastings, or direct numerical maximization over the (log) posterior density, if approximating the posterior distribution near its mode is adequate.
Of course, an analysis of movement data using HMMs does not end with estimating the model parameters, and the HMM toolbox offers a variety of additional inferential techniques. In particular, this includes the Viterbi algorithm, which is a recursive algorithm for “state decoding”—i.e. identifying the most likely state sequence to have generated the observed time series, under the fitted model. Furthermore, the forward and backward probabilities can be used to perform state prediction (i.e. calculate the state probabilities at a given time) and to calculate “pseudoresiduals” (also known as quantile residuals) for model checking. For more details, we refer to Zucchini et al. (2016).
4.3 Real data example: daily movement of elk
To illustrate the HMM approach to modelling animal movement, we reanalyse the elk data discussed in Morales et al. (2004). The data set was downloaded from the Ecological Archives (http://www.esapubs.org/archive/ecol/E085/072/elk_data.txt). We note that this new analysis is neither an attempt to replicate nor an attempt to improve the models discussed in detail by Morales et al. (2004). The data set comprises four tracks, each with daily observations and several associated habitat covariates. There are 735 observed locations in total. For more details, see Morales et al. (2004).
We fitted a joint twostate HMM, with von Mises turning angle and gamma step length distributions, to all four elk’s tracking data, assuming all model parameters to be common to all individuals. About 2% of the step lengths were exactly equal to 0, which we accounted for following McKellar et al. (2015) by including additional parameters specifying statedependent point masses on 0 in the otherwise strictly positive (gamma) step length distributions. To illustrate the type of ecological inference that can be made using HMMs, we additionally implemented an AICbased forward selection of covariates influencing the stateswitching dynamics, as in (1), which led to the inclusion of exactly one covariate, namely “distance to water” (\(\Delta \)AIC compared to the baseline model without covariates: 11.3). This latter type of inference, i.e. the fact that HMMs can easily be used to relate the evolution of an animal’s behavioural states to environmental and habitat conditions, is what most often motivates the use of HMMs for analysing individual animal movement data (see, for example, Morales et al., 2004, Patterson et al., 2009, McKellar et al., 2015, DeRuiter et al., 2016).
Figure 3 displays, for elk287, the state sequence that is most likely to have generated this elk’s observations, under the fitted model. This sequence was obtained using the Viterbi algorithm. Notably, this elk was within 1 km of water for the first 89 days of observation (not shown in the figure)—during which the animal frequently switched between the “encamped” and the “exploratory” state—and \(>1\) km away from water on days 90–164—during which the animal only occupied the “encamped” state.
4.4 Limitations of the HMM framework
The HMM framework is well suited to deal with animal positions that (a) are observed at regular temporal spacings (and where the sampling unit needs to be meaningful with respect to the biological question of interest) and (b) are observed with only negligible observation, or in this specific case, positional, error.
Regarding (a), it is straightforward to fit HMMs when data are missing at random on an otherwise regular grid. However, if the sampling protocol varies, or if observations are made essentially at random times, then the HMM machinery is not suitable. Discretetime Markov chains are meaningless without reference to a sampling unit, and with irregular sampling there is also no obvious way to formulate, for example, a step length distribution that takes into account the amount of time passed between consecutive observations in a sensible way. (Note, however, that there can be meaningful sampling units that do not involve a regular temporal grid, e.g. positions observed each time a marine mammal comes to the sea surface, such that the sampling is done on a divebydive basis.) Continuoustime HMMs, with the underlying Markov process operating in continuous time, do exist (see, for example, Jackson and Sharples, 2002), but they are only suitable if the observed process has the “snapshot” property, such that the kth observation, made at time \(t_k\), depends only on the state active at time \(t_k\) and not on the entire state trajectory over the interval \((t_{k1},t_k]\). While this snapshot property is often naturally met in medical studies, this is generally not the case for the kind of movement data typically analysed.
Regarding (b), when there is nonnegligible measurement error in the locations—i.e. error that is too large relative to the step lengths and/or the question of interest to be ignored—then the basic HMM machinery is also not suitable. (If the locations are observed with error, then there is error in the step lengths and turning angles, and the way this error is generated does not allow for the use of, say, a simple convolution of step length and error distributions to be accommodated within the statedependent process.) In the next section, we will first discuss how a class of models that is closely related to HMMs, namely statespace models (SSMs), can be utilized in order to deal with such positional error. At the end of that section, we will also return to (a), the problem of irregularly spaced observations.
5 Statespace models: discrete time, measurement error
5.1 Model formulation
Some authors regard HMMs and SSMs as the same (Cappé et al. 2009). However, the label HMM is usually used to indicate a model with a finite number of possible states, whereas in SSMs, the underlying state process typically takes continuous values and hence involves an infinite number of states. In the literature on movement modelling via stateswitching processes, SSM approaches typically include both the (true) continuous movement metrics and the discrete states in the hidden component of the model, using the link to the observations to describe potential measurement error (see Jonsen et al., 2005 or Patterson et al., 2008). In contrast, in HMM approaches, as applied to GPS data, the measurement error is often assumed to be negligible, so that the hidden component of the model involves only the behavioural states, with the observed process giving the observed movement metrics, typically step lengths and turning angles. While this may be acceptable for GPS data, which are generally very precise, it will not be for other types of tag data such as that involving the use of satellite tags or lightbased geolocators.
5.2 Kalman filters
The Kalman filter (Kalman 1960) is applicable in the special case of an SSM where the posterior distribution of the state, conditional on the previous observations, is analytically tractable. This tractability stems from two crucial assumptions: (1) that both the process and observation models are linear and (2) that their respective error processes are Gaussian. The Kalman filter also is a recursive (and inherently Bayesian; see Wikle and Berliner, 2007) algorithm, updating state estimates while stepbystep traversing along the time series. Again analogous to the forward–backward algorithm in case of HMMs, the socalled Kalman smoother can be used to obtain state estimates given all observations and a fitted model. A good exposition of the Kalman filter is given by Harvey (1990). Its development was a huge breakthrough in the application of statespace models to problems in engineering such as radar tracking and has been applied to a vast number of problems in many fields. The Kalman filter and associated variants thereof have also been applied to animal movement data. In particular, one of the most widely used Kalman filters has been developed by Sibert et al. (2003), Nielsen et al. (2006); Nielsen and Sibert (2007) in a series of papers which tackle the problem of estimating the position of animals (chiefly marine species) using ambient light data. Patterson et al. (2010) and Johnson et al. (2008) used Kalman filtering to correct positional errors in satellite telemetry data from Service Argos. Indeed, Service Argos now employs Kalman filtering routinely to infer a most likely path from Doppler measurements from Platform Terminal Transmitter (PTT) devices (Lopez et al. 2014).
5.3 Random effects approaches to SSMs
The SSM formulation is a natural way to view the joint problem of estimation of latent states given uncertain data, and it fits very naturally to animal movement problems. The major barrier to the widespread use of SSMs by ecologists is technical difficulties in their implementation. Even the simplest linear SSMs are relatively complex for “endusers”, whose capacity to deploy SSMs may be limited by complexity of the necessary statistical machinery used to fit them. A relatively new approach to fitting SSMs offers analysts a more straightforward and flexible path to develop relatively flexible SSMs via mixed effects modelling. In this section we closely follow the description given in Fournier et al. (2012).
While these methods are well recognized in some disciplines, in particular in applied contexts such as fisheries science for fitting population dynamics models (Maunder et al. 2009), they are only starting to be more widely used in general ecology and only very recently in movement ecology. A recent paper of Albertsen et al. (2015) has applied these estimation methods to demonstrate estimation of a CRW model which incorporates an Ornstein–Uhlenbeck process on the velocity component. The authors provide an R package argosTrack which applies these methods to Service Argos satellite telemetry data. This model is essentially an extension of the CRAWL package (Johnson et al. 2008), which used Kalman filtering/smoothing of speed filtered Service Argos data. However, by specifying the movement model within a mixed effects model framework, the restriction of Gaussian error terms no longer applies, and Albertsen et al. (2015) demonstrate a model with tdistributed errors. We feel the mixed effects approach to fitting SSMs in movement ecology is an exciting and productive way forward as it offers a fast and flexible method for estimating a range of movement models. Initially, and like the Albertsen et al. (2015) paper, the primary application will be in constructing more flexible error correction filters. However, it is likely that models with more ecologically interesting process dynamics could be constructed within this modelling approach. This sort of hierarchical statespace modelling has previously only been available via complicated and bespoke modifications to Kalman filters (see, for example, Meinhold and Singpurwalla, 1989) or with MCMC software (e.g. WinBUGS, OpenBUGS, JAGS). These are discussed in papers by Jonsen et al. (2013) and Jonsen et al. (2006) (and see Pedersen et al., 2011b, for a general comparison of techniques and software).
5.4 Discretizing space in SSMs
In this approach, the continuous latent variables are finely discretized, so that the complexities of integrating over hidden states are reduced to a summation. The standard HMM machinery can then be applied as described in Sect. 4. This is a powerful and underutilized approach which also has the advantages of being able to incorporate nontrivial spatial constraints such as animals having to avoid barriers to movement (i.e. water masses for ground dwelling animals that do not swim, or conversely landavoidance in marine species). These methods were first demonstrated for geolocation from depth and temperature sensing tags by Thygesen et al. (2009) and Pedersen et al. (2008) and typically involve the use of data from sensors as well as (or instead of) noisy estimates of x–y position. The sensor data may be compared to spatial fields, and a data likelihood can be generated for all states in the state space. From there the standard HMM routines can be applied. The case with Markov switching between diffusive and ballistic travel modes was shown by Pedersen et al. (2011a). In all these studies, the transitions between latent states is governed by a PDE which is solved numerically to predict movement. A comparison of these methods to nonspatial/behaviouronly HMMs and switching CRWs fitted using MCMC is given in Jonsen et al. (2013). A limitation of spatial HMM approaches is that, given the large number of states which may need to be stored, computational aspects can be important.
5.5 Particle filters
Particle filtering is a widely used technique in computational statistics for making Bayesian inference from nonlinear SSMs where the emphasis is on “online” (i.e. realtime or near realtime) estimation of the underlying states—in our case, the true, but unknown, animal positions and behavioural states (where the application would be realtime tracking or location forecasting). It is less commonly applied to offline or parameter estimation problems, although it can be used for both. The nomenclature is not standardized in this area, and particle filtering is also referred to as sequential importance sampling and sequential Monte Carlo. Like Markov chain Monte Carlo (MCMC, described in Sect. 5.6), particle filters can be used to make inference from very complex multistate movement models. Two strong advantages of particle filtering are (1) that it is very easy to set up the algorithm, requiring simply that one can simulate from the movement model and can evaluate the likelihood of observations given states, and (2) that particle filtering can be fast to run compared with MCMC. However, when parameter inference is required, as is commonly the case in movement modelling, these advantages typically disappear. A practical disadvantage for practitioners is that general particle filtering software is not typically available, requiring customwritten code.
Particle filtering (and MCMC) both work by generating samples from the posterior distribution \(\pi (\mathbf {\theta },\mathbf {x}\mathbf {y})\). Inferences about model parameters, including latent states, are then made readily using techniques of Monte Carlo integration—for example, the posterior mean of \(\mathbf {\theta }\), \(\mathbf {z}\) or s can be estimated from the mean of the sample values. Both methods are described in many texts, but a good general introduction is Liu (2004). Introductory articles to particle filtering include Doucet et al. (2000), Doucet et al. (2001) and Arulampalam et al. (2002), and a very basic application to a stateswitching animal movement model is given by Patterson et al. (2008).
 1.
Advantage is taken of the Markovian nature of the model, so that the algorithm proceeds one time step at a time, starting by proposing values for time 1 based on an initial sample for time 0, calculating timespecific weights, \(w_1\), and resampling (see next extension, below), then proposing values for time 2 based on the samples at time 1, calculating weights \(w_2\) and resampling, etc.
 2.
There is a resampling step at each time period, where the weighted particles are resampled with replacement with probability proportional to the weight, to yield an unweighted set of particles that can be used for inference.
 3.
The initial sample at time 0 comes from the prior \(p(\theta , \mathbf {x}_0)\), and the proposal each time step is based on the process model \(q_t = f(\mathbf {x}_t\mathbf {x}_{t1}, \mathbf {\theta })\). This results in a weight of a very simple form: \(w_t = g(\mathbf {y}_t\mathbf {x}_t,\mathbf {\theta })\), i.e. the observation process density.
Hence, all that is required to implement the most basic particle filter (and smoother) is the ability to sample from the prior distributions of model parameters and latent states, to simulate realizations from the process model, and to evaluate the observation process density given values of the latent variables.
Unfortunately, the basic method can suffer from high Monte Carlo error, because resampling with replacement at each time step from the particles simulated at time 0 inevitably means that there are fewer and fewer of the unique “ancestral” particle remaining at each time period—a phenomenon known as “particle depletion”. This is not typically a serious problem for latent variables that are dynamic (i.e. timevarying) components of the process model, such as animal locations \(\mathbf {z}_t\) and behavioural states \(s_t\), because simulating stochastically from the proposal distribution (i.e. the process model) at each time step generates new diversity among the simulated particles. However, for the static model parameters, \(\mathbf {\theta }\), each time resampling is performed, fewer and fewer unique values from the original simulated set remain, resulting in an increasingly poor approximation to the posterior distribution. One solution to this is to make the model parameters timevarying, for example by having expected speed and turn angle evolve slowly over time according to a firstorder Markovian process. This is the solution adopted by some authors, e.g. Dowd and Joy (2011). Another solution is to extend the particle filtering algorithm to maintain diversity among particles in static parameter values, for example by resampling from kernel smoothed estimates of the joint posterior distribution of parameters or by introducing an MCMC step. An example of an MCMC step, applied after particle filtering in order to facilitate static parameter estimation, is Andersen et al. (2007). Many other techniques are available (see review by Kantas et al., 2015); however, these methods tend to loose the advantages of simplicity and speed. Perhaps because of this, or perhaps because of the absence of general software for particle filtering animal movement data, MCMC (as described in the next section) has been historically the more popular approach.
5.6 Markov chain Monte Carlo
Markov chain Monte Carlo (MCMC) is a very popular approach for obtaining inference on the model parameters within a Bayesian analysis by simulating (dependent) samples from the posterior distribution (Eq. 11). Standard easytouse computer packages exist which implement an MCMC algorithm for a given model, prior specification and associated data. The MCMC algorithm is performed within a closed “blackbox”, so that indepth computational details of the algorithm are not required. The most widely used packages for movement models are BUGS and JAGS (Lunn et al. 2000; Plummer 2003). Jonsen et al. (2005) provide BUGS code for fitting SSMs with multiple CRWs to animal movement data, which has been employed widely. However, we discuss below why such general software packages can perform poorly. Alternatively, bespoke MCMC computer codes can be written with complete control over the updating algorithm, permitting more general updating algorithms (McClintock et al. 2012). Typically, this is a nontrivial endeavour.
The general structure of the MCMC algorithm for sampling from the joint posterior distribution specified in Eq. (11) is as follows. At each iteration of the MCMC algorithm, the model parameters, \(\mathbf {\theta }\), and auxiliary variables, \(\mathbf {x}\), are updated. For animal movement models, a mixture of single and block updates is generally used. Single updates are typically used for the model parameters, \(\mathbf {\theta }\), and discrete behavioural state, \(s_t\), at time t; and block updates for the true location of an individual at a given time t, \(\mathbf {z}_t\) (i.e. the cartesian coordinates are updated simultaneously). Within the constructed Markov chain, each iteration involves cycling through each individual model parameter, behavioural state and location parameter (at time t) to update their values.
This form of updating leads to very high autocorrelation in the Markov chain for the simulated true location states, \(\mathbf {z}_t\). This is a direct result of the high correlation between the location of an individual at time t, with their corresponding locations at time \(t1\) and \(t+1\) (animals do not teleport). This can be immediately seen in the above acceptance probability for the Metropolis–Hastings algorithm for updating the location of an individual at time t—the acceptance probability is a function of the underlying density function for the movement of the individual in the intervals \([t1,t]\) and \([t,t+1]\). This leads to generally very poor mixing within the Markov chain, and low effective sample sizes, so that large numbers of iterations are needed to obtain converged posterior estimates with small Monte Carlo error. Consequently, extensive posterior checking should be conducted to assess the convergence of the Markov chain, for example, using multiple Markov chains with overdispersed initial values for the model parameters and auxiliary variables. For further discussion of these issues for general SSMs, see, for example, Fearnhead (2011).
Approaches have been proposed to improve the mixing of MCMC algorithms for SSMs. The most notable (and promising) approach considers a particle MCMC algorithm that combines particle filtering with MCMC (Andrieu et al. 2010). The model parameters, \(\mathbf {\theta }\), and discrete states, \(\mathbf {s}\), are updated using an MCMCtype algorithm (for example a singleupdate Metropolis–Hastings within Gibbs algorithm), and the true locations, \(\mathbf {z}\), updated using a particle filter. In addition, the behavioural states do not necessarily need to be imputed within the MCMC algorithm. Assuming firstorder Markovian transitions between states, we can use the efficient HMM machinery to write down an explicit expression for the joint density (i.e. likelihood) of the true locations, given the model parameters (see Eq. 3). In other words the behavioural states do not need to be treated as auxiliary variables and imputed within the MCMC algorithm.
Finally, we note that SSMs generally assume observations are recorded at a set of equally spaced discretetime intervals. In practice, irregularly spaced time steps can be forced into the regular time interval SSM framework by linearly interpolating the recorded location observations at the required time steps (Jonsen et al. 2005; McClintock et al. 2012). Discretetime models have the advantage of accessible modelfitting tools (albeit potentially very inefficient) and immediately interpretable model parameters. However, issues arise, for example, if there is a mismatch between times between observation and the scale at which transitions occur between states. See McClintock et al. (2014) for an indepth discussion of the issues of discretizing time. An alternative and more natural approach in many situations (though at the expense of mathematical simplicity) is to consider continuoustime models, discussed in the next section.
6 Diffusion models: continuous time
Continuoustime modelling of movement almost always makes use of diffusion processes—Markov processes with continuous sample paths. We distinguish two broad approaches: one is to build models from the limited selection of tractable diffusion models (Sects. 6.1–6.4) and the other is to define models directly in terms of the stochastic differential equations that they satisfy (Sect. 6.5). Our emphasis here is on the former, with animals switching between different movement modes—the direct equivalent in continuous time of the HMMs of Sect. 4.
6.1 Brownian motion
6.2 The Ornstein–Uhlenbeck position model
The OU process is perhaps the simplest continuoustime model that is of use in its own right. It arises from ecologists’ interest in learning about the home range of an animal, the spatial range in which it performs its daily survival activities (Börger et al. 2008)—often mathematically defined as the smallest geographical area in which the animal spends a fixed proportion of time (Jennrich and Turner 1969). Approaches to estimating the home range include that in Jennrich and Turner (1969), proposing that an animal’s utilization distribution (see Sect. 6.1) can be represented as a bivariate normal distribution. This led to the first method for modelling animal positions in continuous time—given by Dunn and Gipson (1977), who model the (X, Y) coordinate positions of an animal by a 2D OU process. The longterm position of the animal is described by the equilibrium distribution of an OU process—see (13). Movement therefore has a random element to it, but the animal is ultimately attracted to a centre, and so has a welldefined home range. Autocorrelation of successive observations is accounted for by the conditional distribution of the OU process—see (14).
In the application of the OU process to animal movement, the matrix B is often taken to be isotropic—uniform in all orientations—with \(B=bI_d\) for \(b<0\) to ensure stability. More general classes of B may be used, but note that the class must be symmetric under rotation and reflection; otherwise, there would be some significance placed on the coordinate system chosen (Dunn and Gipson 1977; Blackwell 1997). For example, the general diagonal case is not appropriate, for this reason.
Inference for the OU parameters governing movement in Dunn and Gipson (1977) is carried out by maximum likelihood methods. A difficulty presented by this method is the choice of likelihood for the initial observation. Dunn and Gipson (1977) explore two approaches. One is to ignore the information provided by the initial observation, effectively conditioning on that observation; this is the approach used most widely in movement analysis. The other is to use the tractability of the equilibrium distribution for the animal’s position and add a likelihood term assuming that the initial observation comes from that equilibrium distribution. They discuss the implications in terms of statistical information, and the relationship with the actual sampling scheme for the data.
The OU process addresses the problem of autocorrelation of position, meaning highfrequency “bursts” of observations can be modelled. The OU process, however, will always result in an estimate of home range being elliptical and unimodal. For some animals and habitats this will clearly not be an appropriate assumption (Blackwell 1997). Again, this limits the usefulness of the model on its own, but it is an important component in constructing more realistic models (Sect. 6.4).
6.3 The Ornstein–Uhlenbeck velocity model
The persistent movement modelled using correlated random walks (Sect. 4.1) can be extended to a continuoustime framework. One such approach is given by Johnson et al. (2008) and applied to data from northern fur seals in Kuhn et al. (2009). Johnson et al. (2008) model positions over time indirectly, by formulating a model in terms of velocity—the instantaneous rate of change of location. The behaviour of the velocity vector over time is then described by a bivariate OU process—in practice, Johnson et al. (2008) use two independent 1D OU processes. The persistence assumption on how animals move is thus incorporated as a result of the autocorrelation of the OU process.
The location of the animal at any time, t, can then be found by integrating the velocity process up to time t. This results in the location process no longer being Markovian—as in the OU position model above—as it depends on the entire velocity process prior to time t. However, the combined process of position and velocity is Markovian in this model. Observation error in position is incorporated into Johnson et al. (2008) via a SSM with Gaussian distributed errors and extended in Albertsen et al. (2015) to allow for nonGaussian errors.
Statistical inference for all unknown parameters in Johnson et al. (2008) is carried out using maximum likelihood techniques. Kalman filtering—see Sect. 5.2—is used to find these maximum likelihood estimates, along with prediction intervals for the velocity and location of the animal at unobserved times. In Albertsen et al. (2015) inference is carried out via the Laplace approximation using the R package TMB.
6.4 Modelling switching behaviour in continuous time
Blackwell (1997) suggests an extension to the Brownian and OU models in order to allow for behavioural “switching”. As in the HMMs of Sect. 4, it is assumed that at any point in time an animal exhibits one of a finite set of behavioural states. The process describing the behavioural state of the animal is assumed to follow a continuoustime Markov process. The animal’s movement is modelled in the same way as in Dunn and Gipson (1977) by an OU process. The OU process parameters, however, are dependent on the behaviour process; when the animal is in behavioural state i it moves according to an OU process with the parameters \(\mu _i\), \(\Lambda _i\), \(B_i\) (Blackwell 1997)—see (14). Brownian motion can be recovered as a limiting special case.
The Markov process M(t) taking values from a finite state space of size N can be fully described by its generator matrix, \(G=\lbrace g_{ij} \rbrace \) for \(i,~j~=~1,\ldots ,N\). The values \(g_{ij}, i\ne j\) describe the infinitesimal transition rate from state i to state j; the rate of transitions out of state i is given by \(g_{ii}\). The process can therefore be thought of as being in a state i for a length of time exponentially distributed with mean \({1}/{g_{ii}}\), and then “switching” to another state j for \(i \ne j\). An alternative parametrization (Guttorp 1995) of the process is therefore given by the transition rates out of each state, \(\varvec{\lambda } =\lbrace \lambda _i \rbrace = \lbrace g_{ii} \rbrace \), and the set of jump probabilities \(Q=\lbrace q_{ij}\rbrace = \left\{ \frac{g_{ij}}{g_{ii}} \right\} \) for \(i \ne j\).
It is important to note that, while it is convenient to refer to the “behaviour process”, the behavioural state potentially has the same limitations as in the HMMs of Sect. 4; that is, the state may reflect a statistical description of movement rather than necessarily being “behaviour” in true biological sense. See Sect. 7.4 for further discussion.
It is also worth pointing out that a “behaviour” here simply refers to a set of parameter values, and so different behavioural states may simply represent, for example, similar kinds of movement centred on different points of attraction. Combined with dependence of the switching probabilities on location, this means that these models can represent quite varied interactions with spatially complex environments. See Harris and Blackwell (2013) for a range of examples, and Blackwell et al. (2015) for statistical analysis (using the methods outlined in Sect. 6.4.2) of movement in a habitat known from satellite imaging.
6.4.1 Simulation of a switching diffusion process
To understand the basis of the estimation approaches described previously, it is instructive to consider how to simulate from a switching diffusion process.
6.4.2 Inference for switching diffusions
6.4.3 Computation for switching diffusions
The computation for the method of Sect. 6.4.2 is very timeconsuming, as it involves MCMC sampling of behavioural trajectories, conditional on data, which have varying numbers of change points and can typically only be updated a short segment at a time. As such, these methods are limited in their application at present and are certainly not yet feasible for data sets with very large numbers of observations, or large numbers of individuals. However, high computational cost is not inherent in these models; improving the algorithms and their implementation, and developing fast and efficient approximations, is a very fastmoving area of research, making use of computational ideas from other strands of movement modelling, broader advances in Bayesian computation and techniques from stochastic modelling generally. We include this approach since we believe it has a place in movement modelling which will only increase.
6.5 Stochastic differential equations
The diffusion models described so far are tractable because they are linear and Gaussian. A more flexible modelling approach is to describe movement within a state implicitly, in terms of a stochastic differential equation (SDE).
SDEs can describe much more flexible movement models, generally at the expense of computational, and hence statistical, tractability. For example, Brillinger and Stewart (1998), Brillinger et al. (2002), Preisler et al. (2004) and Preisler et al. (2013) all consider the case where the SDE derives from a potential function, by taking A(t, X(t)) in 17 to be minus the gradient of the potential function, representing an animal’s attraction to or avoidance of a particular point, line or region in a completely general way. Brillinger and Stewart (1998) and Brillinger et al. (2002) also use models for movement that are defined through SDEs incorporating spherical geometry, allowing a natural representation of longrange migration along “great circle” routes.
All the SDE models above take the state of the process to be the animal’s location. Recent work (Parton et al. 2016) explores a different representation, with the animal’s bearing and speed following SDEs to give a continuoustime version of the stepandturn models described earlier. Implementation involves reconstructing the animal’s path using MCMC on a finer timescale than that of the observations, avoiding the arbitrariness of the latter at some computational cost.
7 Discussion
Given the numerous approaches that have been proposed for the analysis of animal movement data, our review is necessarily myopic in order to avoid superficiality. Thus, our review does not cover all relevant existing approaches to animal movement modelling, instead focusing on what we believe to be a few of the key tools for conducting meaningful biological inference from movement data collected at a relatively fine temporal scale. The rationale behind this was to provide researchers working on this type of data with a concise overview of the basic toolbox of which we think they ought to be aware of. We will organize the discussion in the same spirit, not attempting to cover a wide range of topics, including, for example, the various future directions of research on animal movement. Instead, we focus on the discussion of what we consider to be crucial, but sometimes neglected, issues concerning good practice in animal movement modelling.
7.1 Formulation of study aims and study design
An area that receives very little attention is that of design of movement studies. This in itself may cover a variety of aspects. One example is estimation of data throughput—the amount of data we expect to retrieve from a single instrument. Another is how to optimize data returns given constraints of bandwidth limitations (e.g. from satellite tags) against expected longevity. Various aspects of this were tackled by Patterson and Hartmann (2011) with regard to Service Argos. In that work, a model of failure rates was fitted to previous tag deployment data, and a simple model of transmission schedules dependent on the location on the globe was presented. Musyl et al. (2011) also examined failure rates of similar instruments given various aspects of the subject animal and tagging protocol. Breed et al. (2011) examined how the choice of dutycycling in satellite tags drastically affects the results from Bayesian switching models (in the spirit of Jonsen et al. (2005)). Another study, by Bidder et al. (2014), examined the use of engineering approaches to analysis of failure events in biotelemetry. Indeed, many of these are “engineering” issues, rather than statistical or ecological issues, although they are crucially important to determining what ecological inferences may safely be drawn from a particular data set.
More broadly, we are not currently aware of a study that seeks to ask “How many tags on species X are required to estimate an effect Y?”. Here, Y could be the influence of habitat type on movement behaviour or characterizing sexspecific movement rates, or a multitude of other questions. A possible exception to this is the work by Pagendam et al. (2011), which looks at using Doptimal designs to examine how many satellite tags are required to estimate dispersal rates between metapopulations. Examining these questions a priori and as part of the design of field programs, and even the vetting of proposals, ought to become standard practice. However, as yet, the minutiae of such approaches are not being considered. We feel this is an important missing link in the dialogue between statisticians and ecological researchers. At present, analysis of animal movement data is often reactive or opportunistic, and the statistics are seen as a secondary step, only to be engaged in once data are streaming in from tagged individuals in the field. A recent paper (McGowan et al. 2016) has considered how conservation efforts can usefully use animal tracking data. Such assessments are not new in other areas of applied ecology—evaluation of tagging studies has been frequently employed in fisheries management (e.g. see Sippel et al. 2015; Eveson et al. 2012). We hope this paper is indicative of a trend towards more quantitative assessments of the design of tagging studies.
7.2 Retrograde steps in movement analysis
Animal movement patterns continue to be analysed by an array of new statistical techniques that seek to classify behavioural states (e.g. Madon and Hingrat 2014; Sur et al. 2014; Zhang et al. 2015). Those that we have discussed here are merely the tip of the iceberg, relative to the number available in the ecological literature. The approaches considered here were chosen because we feel that they are currently the best statistical approaches for analysis of behaviour in relatively highaccuracy individual movement tracks. We do not have space to consider the larger literature here, but there are some general points to be made about model complexity. In this section we consider the general pitfalls of using what many consider to be too simple a model.
An example of a relatively simple statistical approach that has gained high prominence (see, for example, Sims et al. 2008; Humphries et al. 2010; de Jager et al. 2011) is the Lévy flight (or Lévy walk) hypothesis. This was first proposed as ubiquitous model of random searching behaviour by Viswanathan et al. (1999). Under this model a simple power function is used to model the distribution of step lengths. Several papers have argued for the ubiquity of the model and claimed that animal search strategies that employ stochastic movements in accordance with the model will be optimal (i.e. lead to the best foraging success in the long run relative to a Brownian motion model). But the approach has also courted controversy (Edwards 2007, 2011; Pyke 2015). Pyke (2015) criticizes the approach on theoretical and largely nonstatistical grounds and states that the controversies regarding statistical methods for Lévy flights, as discussed, for example, in Edwards (2007), are largely a “red herring”. This may be true in this particular case. Nonetheless, if statistical inference is used to guide scientific inference, then it is critical to align the statistical models with the biological inference so that the two are commensurate and that biological conclusions are well supported by empirical evidence (Edwards et al. 2012). We believe there are two critiques of Lévylike approaches that are not generally appreciated by ecologists. The temporal dependence in movement data is a crucial factor that must be accounted for in inference and model selection. Since movement data are often fundamentally autocorrelated, the samples from any distribution of step lengths are not independent. This is ignored at the researcher’s peril when attempting to discriminate between candidate models/hypotheses. Spurious tests of significance are highly likely, and the size of animal movement data sets increases the power of any significance test to discriminate between what could be biologically irrelevant differences. This criticism applies to both sides of the debate around Lévylike models. Edwards (2007), in an article critical of much of the foregoing estimation of Lévy models, details likelihoodbased approaches, but largely ignores the crucial issue of autocorrelation. This is why such importance should be placed on time series approaches. The methods considered which do account for temporal dependence are still merely caricatures of the real processes that influence how animals make decisions about movement. Nonetheless, they constitute progress towards capturing reality and are often sufficient for capturing the broad features in the data via a timedependent (e.g. using Markov assumptions) likelihood function.
In that sense, we, along with other authors (Pyke 2015), question whether the strong claims about animal movement (such as ubiquity and optimality) have been strongly tested by the use of simple models such as those based on power laws. The set of candidate models in such papers is often pitifully small (e.g. Lévy vs. Brownian models), and little is to be gained by comparing the merits of two obviously oversimplified models. In addition, simple models are highly limited in their ability to encode the results of previous studies. In comparison, and simply as an example, the HMM framework we considered here can incorporate factors such as energetic reserves altering behavioural choices (Zucchini et al. 2016), environmental drivers (Patterson et al. 2009) and individual variation (Langrock et al. 2012).
7.3 Dependence between individuals
The vast majority of statistical analysis of movement focuses on one individual at a time. Historically, this made sense give the sparsity of data, but modern global positioning system (GPS) technology means that it is increasingly common to have multiple individuals that are simultaneously tracked and potentially interdependent, either because they interact directly or because they respond to the same events or variations in their environment. Statistical treatment of this case lags behind the data collection, notwithstanding the early mention by Dunn and Gipson (1977) and recent papers using approaches outside the set of statistical techniques considered here (Scharf et al. 2015; Russell et al. 2016). Within the HMM context Langrock et al. (2014) described a discretetime model with state switching, building on the ideas in Sect. 4 to describe intermittent dependence between animals in a parsimonious way. Niu et al. (2016) developed this approach in continuous time using the diffusion approach of Sect. 6, jointly representing the locations of interacting individuals as the state of a single highdimensional process. Appropriate allowance for dependence is crucial for statistically valid exploitation of data currently being generated.
7.4 Interpretation of model states in HMMs and SSMs
In the literature on animal movement modelling using stateswitching models, whether HMMs, SSMs or diffusions, the states of the Markov chain are often interpreted as behavioural states of the animals considered. While the general sentiment of relating the models’ states to the animals’ underlying motivation clearly makes sense, there is, in our view, a tendency to overinterpret these types of models. The probabilistic features within states are data driven in the sense that when fitting the model to the data there is no mechanism that would guarantee that the patterns that will be picked up by the model are in any way biologically meaningful with regard to behavioural states. The model simply picks up the strongest patterns in the data. For example, there could be three biologically meaningful behavioural states, say resting, feeding and travelling, but the fitted threestate model is such that resting and feeding are lumped together into one model state (due to the step lengths and turning angles being of similar magnitude), while shortdistance and longdistance travelling activities are differentiated by the remaining two states (possibly due to insufficient flexibility of the statedependent distributions considered). Perhaps even more importantly, the temporal resolution of the observations will often not allow for any direct interpretation of the states (e.g. if time intervals between successive observations are such that animals will often exhibit several different behaviours within each interval).
Blackwell et al. (2015) give examples of various kinds. In their spatially heterogeneous model of fisher movement, the model states are constrained to have a onetoone correspondence with habitat types and are shown to have a much improved fit compared with a spatially homogeneous model, strongly suggesting that the states represent some biologically meaningful aspect of movement behaviour in response to environment. Their analysis of wild boar movement has a small supervised element, partly to tackle statistical issues with label switching; this also has the effect of ensuring that particular states correspond to some features of the data that are both obvious and biologically interpretable, namely clusters of locations during periods of inactivity. The same analysis also illustrates the caveats above; some of the states, originally envisaged as “foraging” and “travelling” states, clearly improve the fit of the model, but their pattern of occurrence suggests that they do not have such a direct interpretation, but rather capture less interpretable heterogeneity in movement over time.
7.5 Final remarks
Although considerable progress has been made over the last decade, the development of statistical tools for modelling animal movement data is only beginning to catch up with the explosion in the volume of corresponding data and associated modelling challenges. There has been, and still is, a huge demand for statistical expertise. Crucially, we believe that the endusers (i.e. ecologists) mostly do not need more sophisticated but casespecific and technically intractable models, but instead need intuitive and practical tools which they can implement and handle themselves. The main challenge clearly lies in identifying the right balance between overly complex yet inaccessible and accessible yet overly simplistic modelling approaches. Progress towards this end will require close collaboration between statisticians and movement ecologists. Such a process ought to inform all parts of movement ecology, from the design of tags, sensors and instruments, to study design and ultimate analysis.
Notes
Acknowledgements
We thank Geoff Hosack and two anonymous referees for their useful feedback on this manuscript. We also gratefully acknowledge the editorial input of David Borchers which greatly improved and clarified the points made in this paper.
References
 Albertsen, C.M., Whoriskey, K., Yurkowski, D., Nielsen, A., Mills, J.: Fast fitting of nongaussian statespace models to animal movement data via template model builder. Ecology 96, 2598–2604 (2015). doi: 10.1890/142101.1 CrossRefGoogle Scholar
 Anderson, T., Stephens, M.: The continuous and discrete Brownian bridges: representations and applications. Technical report, Department of Statistics, Stanford University, Stanford, California (1996)Google Scholar
 Andersen, K., Nielsen, A., Thygesen, U., Hinrichsen, H.H., Neuenfeldt, S.: Using the particle filter to geolocate atlantic cod (gadus morhua) in the baltic sea, with special emphasis on determining uncertainty. Can. J. Fish. Aquat. Sci. 64, 618–627 (2007)CrossRefGoogle Scholar
 Andrieu, C., Doucet, A., Holenstein, R.: Particle Markov chain Monte Carlo (with discussion). J. R. Stat. Soc. B 62, 269–342 (2010)MATHCrossRefGoogle Scholar
 Arulampalam, S., Maskell, S., Gordon, N., Clapp, T.: A tutorial on particle filters for online nonlinear/nongaussian bayesian tracking. IEEE Trans. Signal Process. 10, 174–188 (2002)CrossRefGoogle Scholar
 Bidder, O., Arandjelović, O., Almutairi, F., Shepard, E., Lambertucci, S., Qasem, L., Wilson, R.: A risky business or a safe bet? A fuzzy set event tree for estimating hazard in biotelemetry studies. Anim. Behav. 93, 143–150 (2014)CrossRefGoogle Scholar
 Blackwell, P.G.: Random diffusion models for animal movement. Ecol. Model. 100(1–3), 87–102 (1997). doi: 10.1016/S03043800(97)001531 CrossRefGoogle Scholar
 Blackwell, P.G.: Bayesian inference for Markov processes with diffusion and discrete components. Biometrika 90(3), 613–627 (2003). doi: 10.1093/biomet/90.3.613 MathSciNetMATHCrossRefGoogle Scholar
 Blackwell, P.G., Niu, N., Lambert, C., LaPoint, S.: Exact Bayesian inference for animal movement in continuous time. Methods Ecol. Evolut. (2015). doi: 10.1111/2041210X.12460 Google Scholar
 Börger, L., Dalziel, B., Fryxell, J.: Are there general mechanisms of animal home range behaviour? A review and prospects for future research. Ecol. Lett. 11(6), 637–650 (2008). doi: 10.1111/j.14610248.2008.01182.x CrossRefGoogle Scholar
 Breed, G.A., Costa, D.P., Goebel, M.E., Robinson, P.W.: Electronic tracking tag programming is critical to data collection for behavioral timeseries analysis. Ecosphere 2(1), art10 (2011)CrossRefGoogle Scholar
 Brillinger, D., Stewart, B.: Elephantseal movements: modelling migration. Can. J. Stat. 26(3), 431–443 (1998). doi: 10.2307/3315767 MATHCrossRefGoogle Scholar
 Brillinger, D., Preisler, H., Ager, A., Kie, J., Stewart, B.: Employing stochastic differential equations to model wildlife motion. Bull. Braz. Math. Soc. 33(3), 385–408 (2002). doi: 10.1007/s005740200021 MathSciNetMATHCrossRefGoogle Scholar
 Cappé, O., Moulines, E., Rydén, T.: Inference in Hidden Markov Models. Springer, New York (2009)MATHGoogle Scholar
 Cooke, S., Hinch, S., Wikelski, M., Andrews, R., Kuchel, T., Wolcott, L.J., Butler, P.: Biotelemetry: a mechanistic approach to ecology. Trends Ecol. Evolut. 19(6), 334–343 (2004). doi: 10.1016/j.tree.2004.04.003 CrossRefGoogle Scholar
 Cooke, S., Midwood, J., Thiem, J., Klimley, P., Lucas, M., Thorstad, E., Eiler, J., Holbrook, C., Ebner, B.: Tracking animals in freshwater with electronic tags: past, present and future. Anim. Biotelem. 1(1), 1–1 (2013). doi: 10.1186/2050338515 CrossRefGoogle Scholar
 de Jager, M., Weissing, F.J., Herman, P.M., Nolet, B.A., van de Koppel, J.: Lévy walks evolve through interaction between movement and environmental complexity. Science 332(6037), 1551–1553 (2011)CrossRefGoogle Scholar
 DeRuiter, S., Langrock, R., Skirbutas, T., Goldbogen, J., Calambokidis, J., Friedlaender, A., Southall, B.: A multivariate mixed hmm for analyzing the effect of sonar exposure on the behavioural stateswitching dynamics of blue whales. arXiv preprint, arXiv:1602.06570 (2016)
 Doucet, A., Godsill, S., Andrieu, C.: On sequential monte carlo sampling methods for bayesian filtering. Stat. Comput. 10, 197–208 (2000)CrossRefGoogle Scholar
 Doucet, A., de Freitas, N., Gordon, N. (eds.): An introduction to sequential monte carlo methods. In: Sequential Monte Carlo Methods in Practice, pp. 582. Springer, New York (2001)Google Scholar
 Dowd, M., Joy, R.: Estimating behavioural parameters in animal movement models using a stateaugmented particle filter. Ecology 92, 568–575 (2011)CrossRefGoogle Scholar
 Dunn, J., Gipson, P.: Analysis of radio telemetry data in studies of home range. Biometrics 33(1), 85–101 (1977). doi: 10.2307/2529305 MATHCrossRefGoogle Scholar
 Edwards, A.: Revisiting lévy flight search patterns of wandering albatrosses, bumblebees and deer. Nature 449, 1044–1048 (2007). doi: 10.1038/nature06199 CrossRefGoogle Scholar
 Edwards, A.: Overturning conclusions of lévy flight movement patterns by fishing boats and foraging animals. Ecology 92(6), 1247–1257 (2011). doi: 10.1890/101182.1 CrossRefGoogle Scholar
 Edwards, A.M., Freeman, M.P., Breed, G.A., Jonsen, I.D.: Incorrect likelihood methods were used to infer scaling laws of marine predator search behaviour. PLoS ONE 7(10), e45174–e45174 (2012)CrossRefGoogle Scholar
 Eveson, J.P., Basson, M., Hobday, A.J.: Using electronic tag data to improve mortality and movement estimates in a tagbased spatial fisheries assessment model. Can. J. Fish. Aquat. Sci. 69(5), 869–883 (2012)CrossRefGoogle Scholar
 Fearnhead, P.: Mcmc for statespace models. In: Brooks, S.P., Gelman, A., Jones, G.L., Meng, X. (eds.) Handbook of Markov Chain Monte Carlo, Handbook of Modern Statistical Methods, pp. 513–529. Chapman & Hall/CRC, Boca Raton (2011)Google Scholar
 Fournier, D.A., Skaug, H.J., Ancheta, J., Ianelli, J., Magnusson, A., Maunder, M.N., Nielsen, A., Sibert, J.: Ad model builder: using automatic differentiation for statistical inference of highly parameterized complex nonlinear models. Optim. Methods Softw. 27(2), 233–249 (2012)MathSciNetMATHCrossRefGoogle Scholar
 Franke, A., Caelli, T., Hudson, R.: Analysis of movements and behavior of caribou (Rangifer tarandus) using hidden Markov models. Ecol. Model. 173(2–3), 259–270 (2004). doi: 10.1016/j.ecolmodel.2003.06.004 CrossRefGoogle Scholar
 Guttorp, P.: Stochastic Modelling of Scientific Data. Chapman and Hall/CRC, Boca Raton (1995)MATHCrossRefGoogle Scholar
 Harris, K.J., Blackwell, P.G.: Flexible continuoustime modelling for heterogeneous animal movement. Ecol. Model. 255, 29–37 (2013). doi: 10.1016/j.ecolmodel.2013.01.020 CrossRefGoogle Scholar
 Harvey, A.: Forecasting, Structural Time Series Models and the Kalman Filter. Cambridge University Press, Cambridge (1990)MATHCrossRefGoogle Scholar
 Holzmann, H., Munk, A., Suster, M., Zucchini, W.: Hidden markov models for circular and linearcircular time series. Environ. Ecol. Stat. 13(3), 325–347 (2006). doi: 10.1007/s1065100600157 MathSciNetCrossRefGoogle Scholar
 Horne, J., Garton, E., Krone, S., Lewis, J.: Analyzing animal movements using Brownian bridges. Ecology 88(9), 2354–2363 (2007). doi: 10.1890/060957.1 CrossRefGoogle Scholar
 Humphries, N.E., Queiroz, N., Dyer, J.R., Pade, N.G., Musyl, M.K., Schaefer, K.M., Fuller, D.W., Brunnschweiler, J.M., Doyle, T.K., Houghton, J.D., et al.: Environmental context explains lévy and brownian movement patterns of marine predators. Nature 465(7301), 1066–1069 (2010)CrossRefGoogle Scholar
 Jackson, C., Sharples, L.: Hidden markov models for the onset and progression of bronchiolitis obliterans syndrome in lung transplant recipients. Stat. Med. 21(1), 113–128 (2002). doi: 10.1002/sim.886 CrossRefGoogle Scholar
 Jennrich, R., Turner, F.: Measurement of noncircular home range. J. Theor. Biol. 22(2), 227–237 (1969). doi: 10.1016/00225193(69)900022 CrossRefGoogle Scholar
 Johnson, D., London, J., Lea, M., Durban, J.: Continuoustime correlated random walk model for animal telemetry data. Ecology 89(5), 1208–1215 (2008). doi: 10.1890/071032.1 CrossRefGoogle Scholar
 Jonsen, I., Flemming, J., Myers, R.: Robust statespace modeling of animal movement data. Ecology 86(11), 2874–2880 (2005). doi: 10.1890/041852 CrossRefGoogle Scholar
 Jonsen, I., Myers, R., James, M.: Robust hierarchical statespace models reveal diel variation in travel rates of migrating leatherback turtles. J. Anim. Ecol. 75(5), 1046–1057 (2006). doi: 10.1111/j.13652656.2006.01129.x CrossRefGoogle Scholar
 Jonsen, I., Basson, M., Bestley, S., Bravington, M., Patterson, T., Pedersen, M., Thomson, R., Thygesen, U., Wotherspoon, S.: Statespace models for biologgers: a methodological road map. Deep Sea Res. II Top. Stud. Oceanogr. 88–89, 34–46 (2013). doi: 10.1016/j.dsr2.2012.07.008 CrossRefGoogle Scholar
 Kalman, R.: A new approach to linear filtering and prediction problems. J. Basic Eng. 82(1), 35–45 (1960). doi: 10.1115/1.3662552 CrossRefGoogle Scholar
 Kantas, N., Doucet, A., Singh, S., Maciejowski, J., Chopin, N.: On particle methods for parameter estimation in statespace models. Stat. Sci. 30, 328–351 (2015)MathSciNetMATHCrossRefGoogle Scholar
 Kuhn, C., Johnson, D., Ream, R., Gelatt, T.: Advances in the tracking of marine species: using GPS locations to evaluate satellite track data and a continuoustime movement model. Mar. Ecol. Prog. Ser. 393, 97–109 (2009). doi: 10.3354/meps08229 CrossRefGoogle Scholar
 Langrock, R., King, R., Matthiopoulos, J., Thomas, L., Fortin, D., Morales, J.: Flexible and practical modeling of animal telemetry data: hidden Markov models and extensions. Ecology 93(11), 2336–2342 (2012). doi: 10.1890/112241.1 CrossRefGoogle Scholar
 Langrock, R., Hopcraft, J., Blackwell, P., Goodall, V., King, R., Niu, M., Patterson, T., Pedersen, M., Skarin, A., Schick, R.: Modelling group dynamic animal movement. Methods Ecol. Evolut. 5(2), 190–199 (2014). doi: 10.1111/2041210X.12155 CrossRefGoogle Scholar
 Laplanche, C., Marques, T.A., Thomas, L.: Tracking marine mammals in 3D using electronic tag data. Methods Ecol. Evolut. 6(9), 987–996 (2015)CrossRefGoogle Scholar
 LeosBarajas, V., Photopoulou, T., Langrock, R., Patterson, T.A., Watanabe, Y., Murgatroyd, M., Papastamatiou, Y.: Analysis of animal accelerometer data using hidden Markov models. Methods Ecol. Evolut. (2016). doi: 10.1111/2041210X.12657 Google Scholar
 Liu, J.S.: Monte Carlo Strategies in Scientific Computing. Springer, New York (2004)CrossRefGoogle Scholar
 Lopez, R., Malarde, J.P., Royer, F., Gaspar, P.: Improving argos doppler location using multiplemodel kalman filtering. IEEE Trans. Geosci. Remote Sens. 52(8), 4744–4755 (2014)CrossRefGoogle Scholar
 Lunn, D., Thomas, A., Best, N., Spiegelhalter, D.: WinBUGSa Bayesian modelling framework: concepts, structure, and extensibility. Stat. Comput. 10(4), 325–337 (2000). doi: 10.1023/A:1008929526011 CrossRefGoogle Scholar
 MacDonald, I.: Numerical maximisation of likelihood: a neglected alternative to em? Int. Stat. Rev. 82(2), 296–308 (2014). doi: 10.1111/insr.12041 MathSciNetCrossRefGoogle Scholar
 Madon, B., Hingrat, Y.: Deciphering behavioral changes in animal movement with a ‘multiple change point algorithmclassification tree’ framework. Front. Ecol. Evolut. 2, 30 (2014)Google Scholar
 Marsh, L., Jones, R.: The form and consequences of random walk movement models. J. Theor. Biol. 133(1), 113–131 (1988). doi: 10.1016/S00225193(88)800286 CrossRefGoogle Scholar
 Maunder, M.N., Schnute, J.T., Ianelli, J.: Computers in fisheries population dynamics. In: Megrey, B.A., Moksness, E. (eds.) Computers in Fisheries Research, 2nd edn. Springer, New York (2009)Google Scholar
 McClintock, B., King, R., Thomas, L., Matthiopoulos, J., McConnell, B., Morales, J.: A general discretetime modeling framework for animal movement using multistate random walks. Ecol. Monogr. 82(3), 335–349 (2012). doi: 10.1890/110326.1 CrossRefGoogle Scholar
 McClintock, B., Johnson, D., Hooten, M., Ver Hoef, J., Morales, J.: When to be discrete: the importance of time formulation in understanding animal movement. Mov. Ecol. 2(1), 1–21 (2014). doi: 10.1186/s4046201400216 CrossRefGoogle Scholar
 McGowan, J., Beger, M., Lewison, R.L., Harcourt, R., Campbell, H., Priest, M., Dwyer, R.G., Lin, H.Y., Lentini, P., Dudgeon, C., et al.: Integrating research using animalborne telemetry with the needs of conservation management. J. Appl. Ecol. 54(2), 423–429 (2016)CrossRefGoogle Scholar
 McKellar, A., Langrock, R., Walters, J., Kesler, D.: Using mixed hidden Markov models to examine behavioral states in a cooperatively breeding bird. Behav. Ecol. 26(1), 148–157 (2015). doi: 10.1093/beheco/aru171 CrossRefGoogle Scholar
 Meinhold, R.J., Singpurwalla, N.D.: Robustification of kalman filter models. J. Am. Stat. Assoc. 84(406), 479–486 (1989)MathSciNetCrossRefGoogle Scholar
 Michelot, T., Langrock, R., Patterson, T.A.: moveHMM: an R package for analysing animal movement data using hidden markov models. Methods Ecol. Evolut. 7, 1308–1315 (2016)CrossRefGoogle Scholar
 Morales, J., Haydon, D., Frair, J., Holsiner, K., Fryxell, J.: Extracting more out of relocation data: building movement models as mixtures of random walks. Ecology 85(9), 2436–2445 (2004). doi: 10.1890/030269 CrossRefGoogle Scholar
 Musyl, M., Domeier, M., NasbyLucas, N., Brill, R., McNaughton, L., Swimmer, J., Lutcavage, M., Wilson, S., Galuardi, B., Liddle, J.: Performance of popup satellite archival tags. Mar. Ecol. Prog. Ser. 433, 1–28 (2011)CrossRefGoogle Scholar
 Nielsen, A., Sibert, J.R.: Statespace model for lightbased tracking of marine animals. Can. J. Fish. Aquat. Sci. 64(8), 1055–1068 (2007)CrossRefGoogle Scholar
 Nielsen, A., Bigelow, K.A., Musyl, M.K., Sibert, J.R.: Improving lightbased geolocation by including sea surface temperature. Fish. Oceanogr. 15(4), 314–325 (2006)CrossRefGoogle Scholar
 Niu, M., Blackwell, P.G., Skarin, A.: Modeling interdependent animal movement in continuous time. Biometrics 72, 315–324 (2016). doi: 10.1111/biom.12454 MathSciNetMATHCrossRefGoogle Scholar
 Pagendam, D., Ross, J., Chan, F., Marinova, D., Anderssen, R.: Optimal GPS tracking for estimating species movements. In: International Congress on Modelling and Simulation (19th: 2011: Perth, Australia) (2011)Google Scholar
 Parton, A., Blackwell, P., Skarin, A.: Bayesian inference for continuous time animal movement based on steps and turns. arXiv preprint, arXiv:1608.05583 (2016)
 Patterson, T.A., Hartmann, K.: Designing satellite tagging studies: estimating and optimizing data recovery. Fish. Oceanogr. 20(6), 449–461 (2011)CrossRefGoogle Scholar
 Patterson, T., Thomas, L., Wilcox, C., Ovaskainen, O., Matthiopoulos, J.: Statespace models of individual animal movement. Trends Ecol. Evolut. 23(2), 87–94 (2008). doi: 10.1016/j.tree.2007.10.009 CrossRefGoogle Scholar
 Patterson, T., Basson, M., Bravington, M., Gunn, J.: Classifying movement behaviour in relation to environmental conditions using hidden Markov models. J. Anim. Ecol. 78(6), 1113–1123 (2009). doi: 10.1111/j.13652656.2009.01583.x CrossRefGoogle Scholar
 Patterson, T., McConnell, B., Fedak, M., Bravington, M., Hindell, M.: Using GPS data to evaluate the accuracy of statespace methods for correction of Argos satellite telemetry error. Ecology 91(1), 273–285 (2010). doi: 10.1890/081480.1 CrossRefGoogle Scholar
 Pedersen, M.W., Righton, D., Thygesen, U.H., Andersen, K.H., Madsen, H.: Geolocation of North Sea cod (Gadus morhua) using hidden markov models and behavioural switching. Can. J. Fish. Aquat. Sci. 65(11), 2367–2377 (2008)CrossRefGoogle Scholar
 Pedersen, M., Patterson, T., Thygesen, U., Madsen, H.: Estimating animal behaviour and residency from movement data. Oikos 120(9), 1281–1290 (2011). doi: 10.1111/j.16000706.2011.19044.x CrossRefGoogle Scholar
 Pedersen, M.W., Berg, C.W., Thygesen, U.H., Nielsen, A., Madsen, H.: Estimation methods for nonlinear statespace models in ecology. Ecol. Model. 222(8), 1394–1400 (2011b)CrossRefGoogle Scholar
 Plummer, M.: JAGS: a program for analysis of Bayesian graphical models using Gibbs sampling. In: Proceedings of the 3rd International Workshop on Distributed Statistical Computing (2003)Google Scholar
 Preisler, H., Ager, A., Johnson, B., Kie, J.: Modeling animal movements using stochastic differential equations. Environmetrics 15(7), 643–657 (2004). doi: 10.1002/env.636 CrossRefGoogle Scholar
 Preisler, H., Ager, A., Wisdom, M.: Analyzing animal movement patterns using potential functions. Ecosphere 4(3), art32 (2013). doi: 10.1890/ES1200286.1 CrossRefGoogle Scholar
 Pyke, G.: Understanding movements of organisms: it’s time to abandon the lévy foraging hypothesis. Methods Ecol. Evolut. 6(1), 1–16 (2015). doi: 10.1111/2041210X.12298 CrossRefGoogle Scholar
 Russell, J.C., Hanks, E.M., Haran, M.: Dynamic models of animal movement with spatial point process interactions. J. Agric. Biol. Environ. Stat. 21(1), 22–40 (2016)MathSciNetMATHCrossRefGoogle Scholar
 Rutz, C., Hays, G.: New frontiers in biologging science. Biol. Lett. 5(3), 289–292 (2009). doi: 10.1098/rsbl.2009.0089 CrossRefGoogle Scholar
 Scharf, H.R., Hooten, M.B., Fosdick, B.K., Johnson, D.S., London, J.M., Durban, J.W.: Dynamic social networks based on movement. arXiv preprint arXiv: 1512.07607 (2015)
 Sibert, J.R., Musyl, M.K., Brill, R.W.: Horizontal movements of bigeye tuna (Thunnus obesus) near hawaii determined by Kalman filter analysis of archival tagging data. Fish. Oceanogr. 12(3), 141–151 (2003)CrossRefGoogle Scholar
 Sims, D.W., Southall, E.J., Humphries, N.E., Hays, G.C., Bradshaw, C.J., Pitchford, J.W., James, A., Ahmed, M.Z., Brierley, A.S., Hindell, M.A., et al.: Scaling laws of marine predator search behaviour. Nature 451(7182), 1098–1102 (2008)CrossRefGoogle Scholar
 Sippel, T., Eveson, J.P., Galuardi, B., Lam, C., Hoyle, S., Maunder, M., Kleiber, P., Carvalho, F., Tsontos, V., Teo, S.L., et al.: Using movement data from electronic tags in fisheries stock assessment: a review of models, technology and experimental design. Fish. Res. 163, 152–160 (2015)CrossRefGoogle Scholar
 Stepanov, S.S.: Stochastic World. Springer, New York (2013)MATHCrossRefGoogle Scholar
 Sur, M., Skidmore, A.K., Exo, K.M., Wang, T., Ens, B.J., Toxopeus, A.: Change detection in animal movement using discrete wavelet analysis. Ecol. Inform. 20, 47–57 (2014)CrossRefGoogle Scholar
 Thygesen, U.H., Pedersen, M.W., Madsen, H.: Geolocating fish using hidden markov models and data storage tags. In: Nielsen, J.L., Arrizabalaga, H., Fragoso, N., Hobday, A., Lutcavage, M., Sibert, J. (eds.) Tagging and Tracking of Marine Animals with Electronic Devices, pp. 277–293. Springer, Netherlands (2009)CrossRefGoogle Scholar
 Towner, A., LeosBarajas, V., Langrock, R., Schick, R., Smale, M., Jewell, O., Kaschke, T., Papastamatiou, Y.: Sexspecific and individual preferences for hunting strategies in white sharks. Funct. Ecol. 30, 1397–1407 (2016)CrossRefGoogle Scholar
 Uhlenbeck, G., Ornstein, L.: On the theory of the Brownian motion. Phys. Rev. 36(5), 0823–0841 (1930). doi: 10.1103/PhysRev.36.823 CrossRefGoogle Scholar
 van de Kerk, M., Onorato, D., Criffield, M., Bolker, B., Augustine, B., McKinley, S., Oli, M.: Hidden semimarkov models reveal multiphasic movement of the endangered florida panther. J. Anim. Ecol. 84(2), 576–585 (2015). doi: 10.1111/13652656.12290 CrossRefGoogle Scholar
 Viswanathan, G., Buldyrev, S.V., Havlin, S., Da Luz, M., Raposo, E., Stanley, H.E.: Optimizing the success of random searches. Nature 401(6756), 911–914 (1999)CrossRefGoogle Scholar
 Wikle, C.K., Berliner, L.M.: A bayesian tutorial for data assimilation. Phys. D Nonlinear Phenom. 230(1), 1–16 (2007)MathSciNetMATHCrossRefGoogle Scholar
 Wilmers, C., Nickel, B., Bryce, C., Smith, J., Wheat, R., Yovovich, V.: The golden age of biologging: how animalborne sensors are advancing the frontiers of ecology. Ecology 96(7), 1741–1753 (2015). doi: 10.1890/141401.1 CrossRefGoogle Scholar
 Zhang, J., O’Reilly, K.M., Perry, G.L., Taylor, G.A., Dennis, T.E.: Extending the functionality of behavioural changepoint analysis with kmeans clustering: a case study with the little penguin (Eudyptula minor). PLoS ONE 10, e0122811 (2015)CrossRefGoogle Scholar
 Zucchini, W., MacDonald, I., Langrock, R.: Hidden Markov Models for Time Series: An Introduction Using R, 2nd edn. Chapman and Hall/CRC, Boca Raton (2016)MATHGoogle Scholar