Using Interactions among Species, Landscapes, and Climate to Inform Ecological Niche Models: A Case Study of American Marten (Martes americana) Distribution in Alaska

Abstract

Climate change is acting to reallocate biomes and shift the distribution of species in Alaska, where many animals exist near their thermodynamic limits. Machine-learning based ecological niche models that account for landscape characteristics and changes in climate have been effective tools for deciphering patterns in messy, presence-only datasets, and predicting shifts in wildlife distributions over time. Bioclimatic niche models are sometimes criticized for failing to include interspecific interactions into predictions of species distributions. Here I address this shortcoming by including the previously-modeled distributions of 17 species of small mammal prey as well as 36 environmental predictors to develop distribution models for a generalist predator, the American marten (Martes americana) in Alaska. I used TreeNet and a set of public, online, occurrence records as training data in 13 model variations to create the most accurate ecological niche model for marten in 2015. I also used Intergovernmental Panel on Climate Change A2 scenario climate forecasts and future small mammal distributions to forecast marten distribution in 2100. Additionally, I used TreeNet to quantify the magnitude of variable interactions, and network maps to visualize structure in predictor set relationships. I found that (1) sub-models with a reduced set of predictors are capable of achieving higher predicted accuracies than models based on the entire predictor set, (2) top predictors and interaction strengths can be disproportionately influenced by high-level categorical predictors, and (3) a landscape change analysis identified regions of Alaska where the distribution of marten is predicted to expand with climate change over the coming century. Incorporating the interactive influence of prey and other environmental variables in order to improve distribution change projections should aid wildlife and land managers in developing adaptive strategies for conserving dispersal corridors, biodiversity, and ecosystem function into the future.