A Model for Animal Home Range Estimation Based on the Active Learning Method

Abstract

Home range estimation is the basis of ecology and animal behavior research. Some popular estimators have been presented; however, they have not fully considered the impacts of terrain and obstacles. To address this defect, a novel estimator named the density-based fuzzy home range estimator (DFHRE) is proposed in this study, based on the active learning method (ALM). The Euclidean distance is replaced by the cost distance-induced geodesic distance transformation to account for the effects of terrain and obstacles. Three datasets are used to verify the proposed method, and comparisons with the kernel density-based estimator (KDE) and the local convex hulls (LoCoH) estimators and the cross validation test indicate that the proposed estimator outperforms the KDE and the LoCoH estimators.

Autocorrelation-informed home range estimation: a review and practical guide

“…Although AKDEs provide reliable home range area estimations in the conditions presented in this manuscript, there are scenarios in which they fail. A known issue of KDE methods is that their estimates extend beyond hard boundaries (or other covariate dependences), and have difficulties resolving narrow movement corridors (Guo et al, 2019;Péron, 2019;Silverman, 1986;Worton, 1995); nevertheless, the positive bias from boundary spillover is likely less influential than the negative bias due to unmodeled autocorrelation (Noonan et al, 2019). Kernel density methods also fail to adequately resolve non-stationary behavior and nomadism (Lichti & Swihart, 2011;Nandintsetseg et al, 2019), as nomadic species lack site fidelity to movement pathways or key sites (e.g., breeding or wintering areas).…”

Building fuzzy areal geographical objects from point sets

“…An animal's home range can be modeled as a common fuzzy phenomenon. In this section, a subset of a GPS dataset acquired by a GPS locator attached to a rescued oriental white stork is used ( Ciconia boyciana ) (Guo et al., 2019). This bird was rescued by our university's migratory bird rescue team in the spring of 2016.…”

“…Then, the points located in the southern zone of Beidagang Reservoir were extracted from the trajectory data to construct the bird's home range, as shown in Figure 4. For detailed information about data processing and fuzzy membership surface estimation, we refer the reader to the literature (Guo et al., 2019).…”

“…For fuzzy regions, many methods have been adopted to generate fuzzy objects from point sets (Almadani, 2016; Brindley, 2016; Guo, Du, Ma, Huo, & Peng, 2019; Jones, Purves, Clough, & Joho, 2008; Wang, Liu, Chen, Shi, & Zhang, 2018; Wu, Wang, Shi, Gao, & Liu, 2019). In particular, density estimation methods are adopted to generate a density surface, and then translation methods are implemented to generate fuzzy membership functions from the density surface.…”

“…Typically, fuzzy regions generated by existing methods may have several core areas in which the membership degree of any location is equal to 1, and they are surrounded by a connected boundary; this kind of fuzzy object may be complex, and it is difficult to provide detailed spatial information. For example, Figure 1 is a fuzzy expression of a bird's home range (Guo et al., 2019); in this kind of application, the core areas and boundary areas are typically distinguished within the 50 and 90 or 95% isopleths (Chirima & Owen‐Smith, 2017; Downs et al., 2012), respectively. For fuzzy region A , its core areas 1–5 are surrounded by a connected boundary.…”