Skip to main content
SpringerLink
Log in

Comparing multi- and single-scale species distribution and abundance models built with the boosted regression tree algorithm

  • Research Article
  • Published:
Landscape Ecology Aims and scope Submit manuscript

Abstract

Context

Species are influenced by factors operating at multiple scales, but multi-scale species distribution and abundance models are rarely used. Though multi-scale species distribution models outperform single-scale models, when compared through model selection, multi- and single-scale models built with computer learning algorithms have not been compared.

Objectives

We compared the performance of models using a simple and accessible, multi-scale, machine learning, species distribution and abundance modeling framework to pseudo-optimized and unoptimized single-scale models.

Methods

We characterized environmental variables at four spatial scales and used boosted regression trees to build multi-scale and single-scale distribution and abundance models for 28 bird species. For each species and across species, we compared the performance of multi-scale models to pseudo-optimized and lowest-performing unoptimized single-scale models.

Results

Multi-scale distribution models consistently performed as well or better than pseudo-optimized single-scale models and significantly better than unoptimized single-scale models. Abundance model performance showed a similar, but less pronounced pattern. Mixed-effects models, that controlled for species, provided strong evidence that multi-scale models performed better than unoptimized single-scale models. Although mean improvement in model performance across species appeared minor, for individual species, arbitrary selection of scale could result in discrepancies of up to fourteen percent for area of suitable habitat and population estimates.

Conclusions

Scale selection should be explicitly addressed in distribution and abundance modeling. The multi-scale species distribution and abundance modeling framework presented here provides a concise and accessible alternative to standard pseudo-scale optimization while addressing the scale-dependent response of species to their environment.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  • Araújo MB, Luoto M (2007) The importance of biotic interactions for modelling species distributions under climate change. Global Ecol Biogeogr 16:743–753

    Article  Google Scholar 

  • Baladrón AV, Isacch JP, Cavalli M, Bó MS (2016) Habitat selection by burrowing owls Athene cunicularia in the pampas of Argentina: a multiple-scale assessment. Acta Ornithol 51:137–150

    Article  Google Scholar 

  • Barker N, Cumming S, Darveau M (2014) Models to predict the distribution and abundance of breeding ducks in Canada. Avian Conserv and Ecol. https://doi.org/10.5751/ACE-00699-090207

    Article  Google Scholar 

  • Benítez-López A, Viñuela J, Mougeot F, García JT (2017) A multi-scale approach for identifying conservation needs of two threatened sympatric steppe birds. Biodivers Conserv 26:63–83

    Article  Google Scholar 

  • Blois JL, Zarnetske PL, Fitzpatrick MC, Finnegan S (2013) Climate change and the past, present, and future of biotic interactions. Science 341:499–504

    Article  CAS  PubMed  Google Scholar 

  • Boscolo D, Metzger JP (2009) Is bird incidence in Atlantic forest fragments influenced by landscape patterns at multiple scales? Landsc Ecol 24:907–918

    Article  Google Scholar 

  • Dalgarno S, Mersey J, Gedalof Z, Lemon M (2017) Species-environment associations and predicted distribution of Black Oystercatcher breeding pairs in Haida Gwaii, British Columbia. Canada Avian Conserv Ecol. https://doi.org/10.5751/ACE-01094-120209

    Article  Google Scholar 

  • Dormann CF, Elith J, Bacher S, Buchmann C, Carl G, Carré G, Marquéz JRG, Gruber B, Lafourcade B, Leitão PJ, Münkemüller T (2012) Collinearity: a review of methods to deal with it and a simulation study evaluating their performance. Ecography 36:27–46

    Article  Google Scholar 

  • Edrén SMC, Wisz MS, Teilmann J, Dietz R, Söderkvist J (2010) Modelling spatial patterns in harbour porpoise satellite telemetry data using maximum entropy. Ecography 33:698–708

    Article  Google Scholar 

  • Elith J, Graham CH (2009) Do they? How do they? WHY do they differ? On finding reasons for differing performances of species distribution models. Ecography 32:66–77

    Article  Google Scholar 

  • Elith J, Leathwick JR, Hastie T (2008) A working guide to boosted regression trees. J Anim Ecol 77:802–813

    Article  CAS  PubMed  Google Scholar 

  • Evangelista PH, Mohamed AM, Hussein IA, Saied AH, Mohammed AH, Young NE (2018) Integrating indigenous local knowledge and species distribution modeling to detect wildlife in Somaliland. Ecosphere. https://doi.org/10.1002/ecs2.2134

    Article  Google Scholar 

  • Fournier A, Barbet-Massin M, Rome Q, Courchamp F (2017) Predicting species distribution combining multi-scale drivers. Glob Ecol Conserv 12:215–226. https://doi.org/10.1016/j.gecco.2017.11.002

    Article  Google Scholar 

  • García-Callejas D, Araújo MB (2016) The effects of model and data complexity on predictions from species distributions models. Ecol Model 326:4–12

    Article  Google Scholar 

  • Godsoe W, Franklin J, Blanchet FG (2016) Effects of biotic interactions on modeled species’ distribution can be masked by environmental gradients. Ecol Evol 7:654–664

    Article  PubMed  PubMed Central  Google Scholar 

  • Guisan A, Graham CH, Elith J, Huettmann F (2007) Sensitivity of predictive species distribution models to change in grain size. Divers Distrib 13:332–340

    Article  Google Scholar 

  • Hallman TA, Robinson WD (2020) Deciphering ecology from statistical artefacts: competing influence of sample size, prevalence and habitat specialization on species distribution models and how small evaluation datasets can inflate metrics of performance. Divers Distrib. https://doi.org/10.1111/ddi.13030

    Article  Google Scholar 

  • Halstead KE, Alexander JD, Hadley AS, Stephens JL, Yang Z, Betts MG (2019) Using a species-centered approach to predict bird community responses to habitat fragmentation. Landsc Ecol 34:1919–1935

    Article  Google Scholar 

  • Hudson M-AR, Francis CM, Campbell KJ, Downes CM, Smith AC, Pardieck KL (2017) The role of the North American breeding bird survey in conservation. Condor 119:526–545

    Article  Google Scholar 

  • Illan JG, Thomas CD, Jones JA, Wong WK, Shirley SM, Betts, MG (2014) Precipitation and winter temperature predict long-term range-scale abundance changes in Western North American birds. Glob Change Biol 20:3351–3364

    Article  Google Scholar 

  • Johnston A, Fink D, Reynolds MD, Hochachka WM, Sullivan BL, Bruns NE, Hallstein E, Merrifield MS, Matsumoto S, Kelling S (2015) Abundance models improve spatial and temporal prioritization of conservation resources. Ecol Appl 25:1749–1756

    Article  PubMed  Google Scholar 

  • Kulhanek SA, Leung B, Ricciardi A (2011) Using ecological niche models to predict the abundance and impact of invasive species: application to the common carp. Ecol Appl 21:203–213

    Article  PubMed  Google Scholar 

  • Landscape Ecology, Modeling, Mapping, and Analysis (2014) GNN Structure Maps. https://lemma.forestry.oregonstate.edu/data/structure-maps. Accessed 6 Sep 2016

  • Levin SA (1992) The problem of pattern and scale in ecology: the Robert H. MacArthur award lecture. Ecology 73:1943–1967

    Article  Google Scholar 

  • Liu C, Berry PM, Dawson TP, Pearson RG (2005) Selecting thresholds of occurrence in the prediction of species distributions. Ecography 28:385–393

    Article  Google Scholar 

  • Lobo JM, Jiménez-Valverde A, Real R (2008) AUC: a misleading measure of the performance of predictive distribution models. Global Ecol Biogeogr 17:145–151

    Article  Google Scholar 

  • Mayor SJ, Schneider DC, Schaefer JA, Mahoney SP (2009) Habitat selection at multiple scales. Ecoscience 16:238–247

    Article  Google Scholar 

  • McGarigal K, Wan HY, Zeller KA, Timm BC, Cushman SA (2016) Multi-scale habitat selection modeling: a review and outlook. Landsc Ecol 31:1161–1175

    Article  Google Scholar 

  • Meyer CB, Thuiller W (2006) Accuracy of resource selection functions across spatial scales. Divers Distrib 12:288–297

    Article  Google Scholar 

  • Miguet P, Fahrig L, Lavigne C (2017) How to quantify a distance-dependent landscape effect on a biological response. Methods Ecol Evol 8:1717–1724

    Article  Google Scholar 

  • Moll RJ, Cepek JD, Lorch PD, Dennis PM, Robison T, Montgomery RA (2020) At what spatial scale(s) do mammals respond to urbanization? Ecography. https://doi.org/10.1111/ecog.04762

    Article  Google Scholar 

  • Nadeau CP, Urban MC, Bridle JR (2017) Coarse climate change projections for species living in a fine-scaled world. Glob Change Biol 23:12–24

    Article  Google Scholar 

  • Nichols JD, Thomas L, Conn PB (2009) Inferences about landbird abundance from count data: recent advances and future directions. Model Demogr Process Mark Popul. https://doi.org/10.1007/978-0-387-78151-8_9

    Article  Google Scholar 

  • Oppel S, Meirinho A, Ramirez I, Gardner B, O'Connell AF, Miller PI, Louzao M (2012) Comparison of five modelling techniques to predict the spatial distribution and abundance of seabirds. Biol Conserv 156:94–104

    Article  Google Scholar 

  • Oregon Spatial Data Library (2017) Oregon 10m digital elevation model (DEM). https://spatialdata.oregonexplorer.info/geoportal/details;id=7a82c1be50504f56a9d49d13c7b4d9aa. Accessed 30 Nov 2015

  • Oregon Spatial Data Library (2016) Oregon rivers. https://spatialdata.oregonexplorer.info/geoportal/details;id=01606665b1034dc6877fbad58bb9879a. Accessed 28 Jun 2016

  • Pearson RG, Dawson TP (2003) Predicting the impacts of climate change on the distribution of species: are bioclimate envelope models useful? Global Ecol Biogeogr 12:361–371

    Article  Google Scholar 

  • Pennington DN, Blair RB (2011) Habitat selection of breeding riparian birds in an urban environment: untangling the relative importance of biophysical elements and spatial scale. Divers Distrib 17:506–518

    Article  Google Scholar 

  • Qiao H, Soberón J, Peterson AT (2015) No silver bullets in correlative ecological niche modelling: insights from testing among many potential algorithms for niche estimation. Methods Ecol Evol 6:1126–1136

    Article  Google Scholar 

  • Reino L, Triviño M, Beja P, Araújo MB, Figueira R, Segurado P (2018) Modelling landscape constraints on farmland bird species range shifts under climate change. Sci Total Environ 625:1596–1605

    Article  CAS  PubMed  Google Scholar 

  • Shirley SM, Yang Z, Hutchinson RA, Alexander JD, McGarigal K, Betts MG (2013) Species distribution modelling for the people: unclassified landsat TM imagery predicts bird occurrence at fine resolutions. Divers Distrib 19:855–866

    Article  Google Scholar 

  • Sólymos P, Matsuoka SM, Bayne EM, Lele SR, Fontaine P, Cumming SG, Stralberg D, Schmiegelow FKA, Song SJ (2013) Calibrating indices of avian density from non-standardized survey data: making the most of a messy situation. Methods Ecol Evol 4:1047–1058

    Article  Google Scholar 

  • Stevens BS, Conway CJ (2019) Predicting species distributions: unifying model selection and scale optimization for multi-scale occupancy models. Ecosphere 10:e02748

    Article  Google Scholar 

  • Stevens BS, Conway CJ (2020) Predictive multi-scale occupancy models at range-wide extents: Effects of habitat and human disturbance on distributions of wetland birds. Divers Distrib 26:34–48

    Article  Google Scholar 

  • Sullivan BL, Wood CL, Iliff MJ, Bonney RE, Fink D, Kelling S (2009) eBird: A citizen-based bird observation network in the biological sciences. Biol Conserv 142:2282–2292

    Article  Google Scholar 

  • Thorson TD, Bryce SA, Lammers DA, Woods AJ, Omernik JM, Kagan J, Pater DE, Comstock JA (2003) Ecoregions of Oregon

  • Timm BC, McGarigal K, Cushman SA, Ganey JL (2016) Multi-scale Mexican spotted owl (Strix occidentalis lucida) nest/roost habitat selection in Arizona and a comparison with single-scale modeling results. Landsc Ecol 31:1209–1225

    Article  Google Scholar 

  • Toms JD, Schmiegelow FKA, Hannon SJ, Villard M-A (2006) Are point counts of boreal songbirds reliable proxies for more intensive abundance estimators? Auk 123:438

    Article  Google Scholar 

  • United States Geological Survey (2011) National gap analysis project. https://gapanalysis.usgs.gov/gaplandcover/data/download/. Accessed 7 Dec 2015

  • Welsh AH, Lindenmayer DB, Donnelly CF (2013) Fitting and Interpreting Occupancy Models. PLoS ONE 8:e52015

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Wiens JA (1989) Spatial scaling in ecology. Funct Ecol 3:385–397

    Article  Google Scholar 

  • Wiens JA, Milne BT (1989) Scaling of ‘landscapes’ in landscape ecology, or, landscape ecology from a beetle’s perspective. Landsc Ecol 3:87–96

    Article  Google Scholar 

  • Wiens JA, Stralberg D, Jongsomjit D, Howell CA, Snyder MA (2009) Niches, models, and climate change: assessing the assumptions and uncertainties. P Natl Acad Sci 106:19729–19736

    Article  CAS  Google Scholar 

  • Wilsey CB, Jensen CM, Miller N (2016) Quantifying avian relative abundance and ecosystem service value to identify conservation opportunities in the Midwestern US. Avian Conserv Ecol. https://doi.org/10.5751/ACE-00902-110207

    Article  Google Scholar 

  • Wisz MS, Pottier J, Kissling WD, Pellissier L, Lenoir J, Damgaard CF, Dormann CF, Forchhammer MC, Grytnes JA, Guisan A, Heikkinen RK, Høye TT, Kühn I, Luoto M, Maiorano L, Nilsson MC, Normand S, Öckinger E, Schmidt NM, Termansen M, Timmermann A, Wardle DA, Aastrup P, Svenning JS (2013) The role of biotic interactions in shaping distributions and realised assemblages of species: implications for species distribution modelling. Biol Rev 88:15–30

    Article  PubMed  Google Scholar 

  • Yang X, Chapman GA, Young MA, Gray JM (2005) Using compound topographic index to delineate soil landscape facets from digital elevation models for comprehensive coastal assessment. MODSIM 2005 International Congress on Modelling and Simulation. Modelling and Simulation Society of Australia and New Zealand, Canberra, pp 1511–1517

    Google Scholar 

Download references

Acknowledgements

We appreciate assistance with surveys from R. Moore, database work and maintenance from R. DeMoss, and data entry from the Robinson Lab. The Robinson graduate lab provided helpful comments and discussion. The work was supported by the generous endowment of the Bob and Phyllis Mace Watchable Wildlife Professorship.

Author information

Authors and Affiliations

  1. Department of Fisheries and Wildlife, Oregon State University, Oregon State University, 104 Nash Hall, Corvallis, OR, 97331, USA

    Tyler A. Hallman & W. Douglas Robinson

Authors
  1. Tyler A. Hallman
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. W. Douglas Robinson
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tyler A. Hallman.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hallman, T.A., Robinson, W.D. Comparing multi- and single-scale species distribution and abundance models built with the boosted regression tree algorithm. Landscape Ecol 35, 1161–1174 (2020). https://doi.org/10.1007/s10980-020-01007-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10980-020-01007-7

Keywords

Search

Navigation