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.
Keywords
- Boreal forest
- Machine learning
- Stochastic gradient boosting
- TreeNet
This is a preview of subscription content, access via your institution.
Buying options
References
Ai C, Norton EC (2003) Interaction terms in logit and probit models. Econ Lett 80:123–129
Alaska Department of Fish and Game. 2015. Alaska wildlife action plan. Juneau.
Armstrong RA, McGehee R (1980) Competitive-Exclusion. American Naturalist 115:151–170
Araujo MB, Guisan A (2006) Five (or so) challenges for species distribution modelling. J Biogeogr 33:1677–1688
Austin MP (2002) Spatial prediction of species distribution: an interface between ecological theory and statistical modelling. Ecol Model 157:101–118
Baltensperger AP, Huettmann F (2015) Predictive spatial niche and biodiversity hotspot models for small mammal communities in Alaska: Applying machine-learning to conservation planning. Landsc Ecol 30:681–697
Baltensperger AP, Morton J, Huettmann F (2017) Expansion of American marten (Martes americana) distribution in response to climate and landscape change on the Kenai Peninsula, Alaska. J Mammal 98:703–714
Bellman RE (1961) Adaptive control. Princeton University Press, Princeton
Breiman L (1996) Bagging predictors. Mach Learn 24:123–140
Breiman L (2001a) Random forests. Mach Learn 45:5–32
Breiman L (2001b) Statistical modeling: the two cultures. Stat Sci 16:199–231
Buchen T, Wohlrabe K (2010) Forecasting with many predictors - Is boosting a viable alternative. Munich Discussion Paper No. 2010–31, Ludwig-Maximilians-Universtät München, Munich, Germany, 1–7
Burnham K, Anderson D (2002) Model selection and multimodel inference: a practical information-theoretic approach. Springer, New York
Carroll C (2007) Interacting effects of climate change, landscape conversion, and harvest on carnivore populations at the range margin: Marten and Lynx in the northern Appalachians. Conserv Biol 21:1092–1104
Cutler DR, Edwards KH Jr, Cutler A., Hess K.T, Gibson J, Lawler J.J (2007) Random forests for classification in ecology. Ecology 88:2783–2792
Cox DR, Atkinson AC, Box GEP, Darroch JN, Spjotvoll E, Wahrendorf J (1984) Interaction. International Statistical Review 52:1–31
De’ath G, Fabricius KE (2000) Classification and regression trees: A powerful yet simple technique for ecological data analysis. Ecology 81:3178–3192
Deser C, Tomas R, Alexander M, Lawrence D (2010) The seasonal atmospheric response to projected Arctic sea ice loss in the late twenty-first century. J Clim 23:333–351
Dormann CF (2007) Promising the future? Global change projections of species distributions. Basic Appl Ecol 8:387–397
Elith J, Leathwick JR, Hastie T (2008) A working guide to boosted regression trees. J Anim Ecol 77:802–813
Evans JS, Murphy MA, Holden ZA, Cushman SA (2011) Modeling species distribution and change using Random Forest. In: Ashton Drew YFWC, Huettmann F (eds) Predictive species and habitat modeling in landscape ecology. Springer, Berlin, pp 139–160
Fielding AH (1999) An introduction to machine learning methods. In: Fielding AH (ed) Machine learning methods for ecological applications. Kluwer Academic Publishers, Norwell
Friedman JH (2002) Stochastic gradient boosting. Comput Stat Data Anal 38:367–378
Gotthardt T, et al (2013) Predicting the range and distribution of terrestrial vertebrate species in Alaska, The Alaska gap analysis project, University of Alaska
Hastie T, Tibshirani R (1990) Exploring the nature of covariate effects in the proportional hazards model. Biometrics 46:1005–1016
Hastie T, Tibshirani R, Friedman JH (2001) The elements of statistical learning: data mining, inference, and prediction. Springer, New York
IUCN (International Union for Conservation of Nature) 2016 Martes americana Version 2016–2. The IUCN Red List of Threatened Species
Jimenez-Valverde A, Lobo JM (2007) Threshold criteria for conversion of probability of species presence to either-or presence-absence. Acta Oecol Int J Ecol 31:361–369
Johnson CJ, Seip DR, Boyce MS (2004) A quantitative approach to conservation planning: using resource selection functions to map the distribution of mountain caribou at multiple spatial scales. J Appl Ecol 41:238–251
Magness DR, Huettmann F, Morton JM (2008) Using Random Forests to provide predicted species distribution maps as a metric for ecological inventory and monitoring. In: Smolinski TG, Milanova MG, Hassanien A-E (eds) Applications of computational intelligence in biology, Studies in computational intelligence, vol 122. Springer, Berlin/Heidelberg, pp 209–229
Manel S, Williams HC, Ormerod SJ (2001) Evaluating presence-absence models in ecology: the need to account for prevalence. J Appl Ecol 38:921–931
Mantyka-Pringle CS, Visconti P, Moreno DM, Martin TG, Rondinini C, Rhodes J (2015) Climate change modifies risk of global biodiversity loss due to land-cover change. Biol Conserv 187:103–111
Murphy K, Huettmann F, Fresco N, Morton J (2010) Connecting Alaska landscapes into the future: Results from an interagency climate modeling, land management and conservation project. Final Report, U.S. Fish and Wildlife Service, Anchorage, AK
Prasad AM, Iverson LR, Liaw A (2006) Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 9:181–199
Spencer WD (1987) Seasonal rest-site preferences of pine martens in the northern Sierra Nevada. J Wildl Manag 51:616–621
Steinberg D (2011) Dan Steinberg’s Blog [Internet]. San Diego: Salford Systems, Inc. Accessed 10 Oct 2016. Available from: https://www.salford-systems.com/blog/dan-steinberg/modeling-tricks-with-treenet-treating-categorical-variables-as-continuous
Strobl C, Boulesteix A-L, Zeileis A, Hothorn T (2007) Bias in random forest variable importance measures: illustrations, sources and a solution. BMC Bioinf 8:25
Thuiller W, Lavorel S, Araujo MB (2005) Niche properties and geographical extent as predictors of species sensitivity to climate change. Glob Ecol Biogeogr 14:347–357
Travis J, Brooker R, Dytham C (2005) The interplay of positive and negative species interactions across an environmental gradient: insights from an individual-based simulation model. Biol Lett 22:5–8
Wasserman TN, Cushman SA, Littell JS, Shirk AJ, Landguth EL (2013) Population connectivity and genetic diversity of American marten (Martes americana) in the United States northern Rocky Mountains in a climate change context. Conserv Genet 14:529–541
Wiebe PA, Thompson ID, McKague CI, Fryxell JM, Baker JA (2014) Fine-scale winter resource selection by American martens in boreal forests and the effect of snow depth on access to coarse woody debris. Ecoscience 21:123–132
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Baltensperger, A.P. (2018). Using Interactions among Species, Landscapes, and Climate to Inform Ecological Niche Models: A Case Study of American Marten (Martes americana) Distribution in Alaska. In: Humphries, G., Magness, D., Huettmann, F. (eds) Machine Learning for Ecology and Sustainable Natural Resource Management. Springer, Cham. https://doi.org/10.1007/978-3-319-96978-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-96978-7_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-96976-3
Online ISBN: 978-3-319-96978-7
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)