A machine‐learning approach for extending classical wildlife resource selection analyses. Issue 6 (28th February 2018)

• Record Type: Journal Article
• Authors: Shoemaker, Kevin T.; Heffelfinger, Levi J.; Jackson, Nathan J.; Blum, Marcus E.; Wasley, Tony; Stewart, Kelley M.
• Is Part Of: Ecology and evolution. Volume 8:Issue 6(2018)
• Page Start: 3556
• Page End: 3569
• Publication Date: 2018-02-28
• Subjects: habitat suitability -- logistic regression -- machine learning -- Odocoileus hemionus -- random forest -- resource selection function; Ecology -- Periodicals; Evolution -- Periodicals; 577.05
• DOI: 10.1002/ece3.3936
• Languages: English
• ISSNs: 2045-7758

Abstract

Abstract: Resource selection functions (RSFs) are tremendously valuable for ecologists and resource managers because they quantify spatial patterns in resource utilization by wildlife, thereby facilitating identification of critical habitat areas and characterizing specific habitat features that are selected or avoided. RSFs discriminate between known‐use resource units (e.g., telemetry locations) and available (or randomly selected) resource units based on an array of environmental features, and in their standard form are performed using logistic regression. As generalized linear models, standard RSFs have some notable limitations, such as difficulties in accommodating nonlinear (e.g., humped or threshold) relationships and complex interactions. Increasingly, ecologists are using flexible machine‐learning methods (e.g., random forests, neural networks) to overcome these limitations. Herein, we investigate the seasonal resource selection patterns of mule deer ( Odocoileus hemionus ) by comparing a logistic regression framework with random forest (RF), a popular machine‐learning algorithm. Random forest (RF) models detected nonlinear relationships (e.g., optimal ranges for slope and elevation) and complex interactions which would have been very challenging to discover and characterize using standard model‐based approaches. Compared with standard RSF models, RF models exhibited improved predictive skill, provided novel insights about resource selection patterns of mule deer, and, when projected across a relevant geographic space, manifested notable differences in predicted habitat suitability. We recommend that wildlife researchers harness the strengths of machine‐learning tools like RF in addition to "classical" tools (e.g., mixed‐effects logistic regression) for evaluating resource selection, especially in cases where extensive telemetry data sets are available. Abstract : Resource selection functions (RSFs, which discriminate between used and available habitats on the basis of environmental features) are widely used by ecologists and resource managers but traditional approaches (generalized linear models) have limited power to detect and characterize nonlinear responses and complex interactions. Using a population of GPS‐collared migratory mule deer in Nevada, USA, as a case study, we contrasted a classical RSF approach (mixed‐effects logistic regression) with a more flexible machine‐learning approach (random forest). The machine‐learning approach provided important insights about seasonal resource selection patterns of mule deer that would have been difficult or impossible to achieve using classical RSF methods, leading us to conclude that machine‐learning methods can complement and extend classical RSF approaches, especially in cases where extensive telemetry data sets are available.