U.S. Geological Survey, Western Ecological Research Center, 4165 Spruance Road, San Diego, California 92101, USA.
Ecol Appl. 2013 Apr;23(3):654-69. doi: 10.1890/12-0687.1.
Because of its role in many ecological processes, movement of animals in response to landscape features is an important subject in ecology and conservation biology. In this paper, we develop models of animal movement in relation to objects or fields in a landscape. We took a finite mixture modeling approach in which the component densities are conceptually related to different choices for movement in response to a landscape feature, and the mixing proportions are related to the probability of selecting each response as a function of one or more covariates. We combined particle swarm optimization and an expectation-maximization (EM) algorithm to obtain maximum-likelihood estimates of the model parameters. We used this approach to analyze data for movement of three bobcats in relation to urban areas in southern California, USA. A behavioral interpretation of the models revealed similarities and differences in bobcat movement response to urbanization. All three bobcats avoided urbanization by moving either parallel to urban boundaries or toward less urban areas as the proportion of urban land cover in the surrounding area increased. However, one bobcat, a male with a dispersal-like large-scale movement pattern, avoided urbanization at lower densities and responded strictly by moving parallel to the urban edge. The other two bobcats, which were both residents and occupied similar geographic areas, avoided urban areas using a combination of movements parallel to the urban edge and movement toward areas of less urbanization. However, the resident female appeared to exhibit greater repulsion at lower levels of urbanization than the resident male, consistent with empirical observations of bobcats in southern California. Using the parameterized finite mixture models, we mapped behavioral states to geographic space, creating a representation of a behavioral landscape. This approach can provide guidance for conservation planning based on analysis of animal movement data using statistical models, thereby linking connectivity evaluations to empirical data.
由于动物在许多生态过程中的作用，动物对景观特征的运动是生态学和保护生物学中的一个重要课题。在本文中，我们建立了与景观中物体或场相关的动物运动模型。我们采用有限混合建模方法，其中分量密度在概念上与对景观特征的运动的不同选择有关，混合比例与选择每种响应的概率有关，该概率是一个或多个协变量的函数。我们结合粒子群优化和期望最大化 (EM) 算法来获得模型参数的最大似然估计。我们使用这种方法来分析在美国加利福尼亚州南部与城市地区相关的三只山猫的运动数据。对模型的行为解释揭示了山猫对城市化的运动反应的相似性和差异性。所有三只山猫都通过平行于城市边界移动或随着周围地区城市土地覆盖比例的增加而向城市化程度较低的地区移动来避免城市化。然而，一只山猫，一只具有类似扩散的大规模运动模式的雄性，在较低的城市化密度下避免城市化，并严格通过平行于城市边缘移动来响应。另外两只山猫，它们都是居民并且占据了相似的地理区域，通过平行于城市边缘的运动和向城市化程度较低的区域的运动来避免城市区域。然而，居住的雌性似乎比居住的雄性在较低的城市化水平下表现出更大的排斥性，这与加利福尼亚州南部的山猫的实证观察结果一致。使用参数化的有限混合模型，我们将行为状态映射到地理空间中，创建了行为景观的表示。这种方法可以为基于统计模型分析动物运动数据的保护规划提供指导，从而将连通性评估与实证数据联系起来。
