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.
Variation among demographic rates for a population reflects the allocation of available energy by individuals to competing life-history strategies. Species exhibiting slow-paced life histories often prioritize energy allocation to adult survival over any single reproductive event, therefore maximizing future reproductive potential. Survival of adult female ungulates is generally high with little variability, whereas survival of young is lower and often highly variable. When adult survival is high with low variability, juvenile survival may have a proportionally greater effect on population growth or decline. Weather also may affect population dynamics directly by influencing survival of young or adults, or indirectly through changes in nutritional condition of adult females that influence population growth rates. We experimentally manipulated forage availability during winter, by supplementing native forage with high-energy pelleted feed ad libitum, to a subset of a population of mule deer (Odocoileus hemionus) to understand the effects of winter nutrition on survival of adult females and their young born the subsequent summer. We evaluated the effects of winter nutrition, individual-based parameters, and environmental covariates on survival of adult female mule deer from 2013 to 2018, and neonatal mule deer from 2014 to 2016. We documented a 26% decrease in annual survival of adult female mule deer in 2017 in response to increased snowpack during the preceding winter. Neonates born to females that receive enhanced nutrition during winter preceding parturition had higher survival to weaning (0.49, SE = 0.12), compared to neonates born to females that did not receive enhanced nutrition (0.29, SE = 0.07). We observed no effect of enhanced winter nutrition on survival of adult females. Our results suggested winter nutrition of maternal females may influence juvenile survival and demonstrates the importance of forage quality available to adult females during mid-pregnancy. Although we were unable to detect an effect of winter forage on survival of adults, direct effects of deep winter snow resulted in lower survival of adult females. Low survival of adult females in our study population is indicative of a declining population.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.