Predictive spatial niche and biodiversity hotspot models for small mammal communities in Alaska: applying machine-learning to conservation planning
- 782 Downloads
Changing global environmental conditions, especially at northern latitudes, are threatening to shift species distributions and alter wildlife communities.
We aimed to establish current distributions and community arrangements of small mammals to provide important baselines for monitoring and conserving biodiversity into the future.
We used 4,408 archived museum and open-access records and the machine learning algorithm, RandomForests, to create high-resolution spatial niche models for 17 species of rodents and shrews in Alaska. Models were validated using independent trapping results from 20 locations stratified along statewide mega-transects, and an average species richness curve was calculated for field samples. Community cluster analyses (varclus) identified geographic patterns of sympatry among species. Species models were summed to create the first small-mammal species richness map for Alaska.
Species richness increased logarithmically to a mean of 3.3 species per location over 1,500 trap-nights. Distribution models yielded mean accuracies of 71 % (45–90 %), and maps correctly predicted a mean of 75 % (60–95 %) of occurrences correctly in the field. Top predictors included Soil Type, Ecoregion, Landfire Land-cover, December Sea Ice, and July Temperature at the geographic scale. Cluster analysis delineated five community groups (3–4 species/group), and species richness was highest (11–13 species) over the Yukon-Tanana Uplands.
Models presented here provide spatial predictions of current small mammal biodiversity in Alaska and an initial framework for mapping and monitoring wildlife distributions across broad landscapes into the future.
KeywordsArctic Boreal Forest Ecological niche modeling Lemmings Machine learning Mega-transect sampling Open-access data RandomForests Shrews Voles
We are deeply indebted to everyone who assisted AB in the field, especially David Keiter, Edward Corp, Jessica Jordan, Alex Nicely, Casey Brown, Tim Mullet, László Kövér, and Dmitry Korobitsyn for their tireless efforts on the trap-lines. Thank you also to Link Olson, Stephen MacDonald, Joseph Cook, and GBIF for compiling and contributing valuable occurrence datasets and lending traps and equipment. Logistical support, field gear, and transportation were also generously provided by David Payer, Mark Bertram, Tom Paragi, Dashiel Feierabend, Joshua Jerome, Chris Long, Jeff Melegari, Jeremy Carlson, the Russian Mission Village Council and Kako Retreat Center. Finally, thank you to everyone who so generously offered help, advice, and fish along the Yukon River.
- Arctic Climate Impact Assessment (2005) Impacts of a warming Arctic. Arctic Climate Impact Assessment (ACIA), CambridgeGoogle Scholar
- Assogbadjo A, Sinsin B, Codjia J, Damme PV (2005) Ecological diversity and pulp, seed, and kernel production of the Baobab (Adansonia digitata) in Benin. Belg J Bot 138:47–56Google Scholar
- Breiman L (1996) Bagging predictors. Mach Learn 24:123–140Google Scholar
- Burnham K, Anderson D (2002) Model selection and multimodel inference: a practical information-theoretic approach. Springer, New York, p 488Google Scholar
- Bush MB (2002) Distributional change and conservation on the Andean flank: a palaeoecological perspective. Clim Change Conserv Spec Issue 11:463–473Google Scholar
- Evans JS, Murphy MA, Holden ZA, Cushman SA (2011) Modeling species distribution and change using Random Forest. In: Drew CA, Wiersma YF, Huettmann F (eds) Predictive species and habitat modeling in landscape ecology. Springer, Berlin, p 22Google Scholar
- Fritts E, Burch M, Rabe M, Schwarber J, McCracken B (2006) Our wealth maintained: a strategy for conserving Alaska’s diverse wildlife and fish resources. Alaska Department of Fish and Game, Juneau, AK, p 852Google Scholar
- Gotthardt T, Pyare S, Huettmann F et al (2013) Predicting the range and distribution of terrestrial vertebrate species in Alaska. The Alaska Gap Analysis Project, University of Alaska, Anchorage, p 40Google Scholar
- Hallett J, O’Connell M, Maguire C (2003) Ecological relationships of terrestrial small mammals in western coniferous forests. In: Zabel CJ, Anthony RG (eds) Mammal community dynamics: management and conservation in the coniferous forests of western North America. Cambridge University Press, New York, p 22Google Scholar
- Huettmann F, Gottschalk T (2010) Simplicity, model fit, complexity and uncertainty in spatial prediction models applied over time: we are quite sure, aren’t we? In: Drew CA, Wiersma YF, Huettmann F (eds) Predictive species and habitat modeling in landscape ecology. Springer, Berlin, p 31Google Scholar
- IPCC (2007) Climate Change 2007: The physical science basis. In: Solomon S, Qin D, Manning M et al (eds) Contribution of Working Group I to the Fourth Assessment Report of the Intergovernmental Panel on Climate Change. Cambridge University Press, Cambridge, p 52Google Scholar
- Kelling S, Hochachka WM, Fink D et al (2009) Data-intensive science: a new paradigm for biodiversity studies. Prof Biol 59:613–620Google Scholar
- Kerr JT, Kulkarni M, Algar A (2011) Integrating theory and predictive modeling for conservation research. In: Drew CA, Wiersma YF, Huettmann F (eds) Predictive species and habitat modeling in landscape ecology. Springer, New York, p 19Google Scholar
- Lovejoy TE, Hannah L (2005) Climate change and biodiversity. Yale University Press, New Haven, p 440Google Scholar
- MacDonald SO, Cook JA (2009) Recent mammals of Alaska. University of Alaska Press, Fairbanks, p 387Google Scholar
- 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. Springer, New York, p 229Google Scholar
- Molina B (2001) Glaciers of Alaska. Alaska Geographic, 2. Alaska Geographic Society, Anchorage, p 128Google Scholar
- 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. Fairbanks, p 100Google Scholar
- Newton I (1979) Population ecology of raptors. A&C Black Publishers Ltd, London, p 273Google Scholar
- R Core Team (2013) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna. http://www.R-project.org/
- Viereck LA, Dyrness CT, Batten AR, Wenzlick KJ (1992) The Alaska vegetation classification. PNW-GTR-286. U.S. Department of Agriculture, Forest Service, Pacific Northwest Research Station, Portland, p 278Google Scholar
- Wiersma YF, Huettmann F, Drew CA (2011) Landscape modeling of species and their habitats: history, uncertainty, and complexity. In: Drew CA, Wiersma YF, Huettmann F (eds) Predictive species and habitat modeling in landscape ecology. Springer, New York, p 8Google Scholar
- Wilson EO (2006) The creation: an appeal to save life on earth. W.W. Norton & Company Inc, New YorkGoogle Scholar
- Zar JH (2010) Biostatistical analysis. Prentice Hall, New JerseyGoogle Scholar