全球变化知识资源中心

Conservation planning for wildlife species requires mapping and assessment of habitat suitability across broad areas, often relying on a diverse suite, or stack, of geospatial data presenting multidimensional controls on a species. Stacks of univariate, independently developed vegetation layers may not represent relationships between each variable that can be characterized by multivariate modeling techniques, leading to inaccurate inferences on the distribution of suitable habitat. In this paper, we examine the role of variable combining in mapping multiple dimensions of greater sage-grouse (Centrocercus urophasianus, GRSG) habitat as a basis for GRSG conservation in the great basin ecoregion within southeastern Oregon. We compare two modeling approaches: a univariate random forest regression model (RF regression) and a multivariate random forest nearest neighbor (RFNN) imputation model , across an array of variables. These include five GRSG habitat descriptor variables: percent cover of trees, juniper, sagebrush, and GRSG food forbs, and the proportion of grasses that are exotic annuals. We also model species distributions of 51 common species in the sage steppe and combine these predictions to estimate alpha diversity. Our results show that RF regression and RFNN can yield univariate predictions with similar performance, but RF regression predictions tend to contain slightly more bias at broader spatial scales. Stacking univariate predictions from RF regression yields covariance errors that manifest as logical errors (juniper cover > tree cover), biases in estimates of GRSG habitat area, and biases in estimates of alpha diversity. Combining variables from the RFNN model does not introduce covariance errors. We conclude that multivariate modeling approaches are better suited to map multidimensional habitat niches at broader spatial scales, and also better suited to provide information for defining multivariable adaptive management triggers at the population level or above.