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

Guo Guo,Ma Ma,Peng Peng,Du Du,Huo Huo

doi:10.3390/ijgi8110490

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.

Highlights

Home range (HR) estimation is a central topic in spatial ecology studies and is fundamental to understanding animal behavior [1,2,3]
Because the Beidagang Reservoir is very flat and there are no obstacles in this reservoir that can interfere with the activities of the oriental white stork, the effects of terrain and obstacles are not taken into account
The sample layer is digitalized into a raster layer with a resolution of 20 m, and the Euclidean distance is used, which means that k = 0 in Equations (2) and (3)

Summary

Introduction

Home range (HR) estimation is a central topic in spatial ecology studies and is fundamental to understanding animal behavior [1,2,3]. Fleming et al defined the HR area as a percent coverage of the region encompassing the probability distribution of all possible locations [4]. Chirima and Owen-Smith [9] introduced several criteria to assess the performance of alternative HR estimation methods. These criteria are as follows: (1) ability to naturally represent the probability or possibility of the distribution of an animal; (2) ability to bypass obstacles such as cliffs, mountains, rivers and roads for some types of animals; (3) ability to consider the impact of the terrain; and (4) minimal bias in the size of the HR. Criterion 3 indicates that different topographic features have different effects on animal activities; for example, deer prefer relatively flat marginal areas of forest to rough

Methods

Results

Conclusion