Skip to main content

Advertisement

SpringerLink
Log in

Effect of Classification Procedure on the Performance of Numerically Defined Ecological Regions

  • Published:
Environmental Management Aims and scope Submit manuscript

Abstract

Ecological regionalizations define geographic regions exhibiting relative homogeneity in ecological (i.e., environmental and biotic) characteristics. Multivariate clustering methods have been used to define ecological regions based on subjectively chosen environmental variables. We developed and tested three procedures for defining ecological regions based on spatial modeling of a multivariate target pattern that is represented by compositional dissimilarities between locations (e.g., taxonomic dissimilarities). The procedures use a “training dataset” representing the target pattern and models this as a function of environmental variables. The model is then extrapolated to the entire domain of interest. Environmental data for our analysis were drawn from a 400 m grid covering all of Switzerland and consisted of 12 variables describing climate, topography and lithology. Our target patterns comprised land cover composition of each grid cell that was derived from interpretation of aerial photographs. For Regionalization 1 we used conventional cluster analysis of the environmental variables to define 60 hierarchically organized levels comprising from 5 to 300 regions. Regionalization 1 provided a base-case for comparison with the model-based regionalizations. Regionalization 2, 3 and 4 also comprised 60 hierarchically organized levels and were derived by modeling land cover composition for 4000 randomly selected “training” cells. Regionalization 2 was based on cluster analysis of environmental variables that were transformed based on a Generalized Dissimilarity Model (GDM). Regionalization 3 and 4 were defined by clustering the training cells based on their land cover composition followed by predictive modeling of the distribution of the land cover clusters using Classification and Regression Tree (CART) and Random Forest (RF) models. Independent test data (i.e. not used to train the models) were used to test the discrimination of land cover composition at all hierarchical levels of the regionalizations using the classification strength (CS) statistic. CS for all the model-based regionalizations was significantly higher than for Regionalization 1. Regionalization 3 and 4 performed significantly better than Regionalization 2 at finer hierarchical levels (many regions) and Regionalization 4 performed significantly better than Regionalization 3 for coarse levels of detail (few regions). Compositional modeling can significantly increase the performance of numerically defined ecological regionalizations. CART and RF-based models appear to produce stronger regionalizations because discriminating variables are able to change at each hierarchic level.

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
Fig. 6
Fig. 7

Similar content being viewed by others

References

  • Andréfouët S, Claereboudt M (2000) Objective class definitions using correlation of similarities between remotely sensed and environmental data. International Journal of Remote Sensing 21(9):1925

    Article  Google Scholar 

  • Bailey RG (1983) Delineation of ecosystem regions. Environmental Management 7:365–373

    Article  Google Scholar 

  • Bailey RG (1984) Testing an ecosystem regionalization. Journal of Environmental Management 19:239–248

    Google Scholar 

  • Bailey RG (1996) Ecosystem geography. Springer, New York, 216 pp

    Google Scholar 

  • Belbin L (1993) Environmental representativeness: regional partitioning and reserve selection. Biological Conservation 66:223–230

    Article  Google Scholar 

  • Breiman L (2001) Random forests. Machine Learning 45(1):5–32

    Article  Google Scholar 

  • Bunce RGH, Barr CJ, Clarke RT, Howard DC, Lane AMJ (1996) Land classification for strategic ecological survey. Journal of Environmental Management 47:37–60

    Article  Google Scholar 

  • Burrough PA, McDonell RA (1998) Principles of geographical information systems. Oxford University Press, New York, 190 pp

    Google Scholar 

  • Clarke KR (1993) Non-parametric multivariate analyses of changes in commmunity structure. Australian Journal of Ecology 18:117–143

    Article  Google Scholar 

  • Cumming G, Fidler F, Vaux DL (2007) Error bars in experimental biology. Journal of Cell Biology 177(1):7–11

    Article  CAS  Google Scholar 

  • Cutler DR, Edwards JTC, Beard KH, Cutler A, Hess KT, Gibson J, Lawler JJ (2007) Random forests for classification in ecology. Ecology 88(11):2783–2792

    Article  Google Scholar 

  • De’ath G (1999) Extended dissimilarity: a method of robust estimation of ecological distances from high beta diversity data. Plant Ecology 144:191–199

    Article  Google Scholar 

  • De’ath GK, Fabricius E (2002) Classification and regression trees: A powerful yet simple technique for ecological data analysis. Ecology 81(11):3178–3192

    Article  Google Scholar 

  • Ferrier S, Guisan A (2006) Spatial modeling of biodiversity at the community level. Journal of Applied Ecology 43:393–404

    Article  Google Scholar 

  • Ferrier S, Manion G, Elith J, Richardson K (2007) Using generalized dissimilarity modeling to analyse and predict patterns of beta diversity in regional biodiversity assessment. Diversity and Distributions 13:252–264

    Article  Google Scholar 

  • Franklin J (1995) Predictive vegetation mapping: Geographic modeling of biospatial patterns in relation to environmental gradients. Progress in Physical Geography 4:474–499

    Article  Google Scholar 

  • Friedman JH, Meulman JJ (2003) Multiple additive regression trees with application in epidemiology. Statistics in Medicine 22:1365–1381

    Article  Google Scholar 

  • Guisan A, Zimmermann NE (2000) Predictive habitat distribution models in ecology. Ecological Modeling 135:147–186

    Article  Google Scholar 

  • Hargrove WW, Hoffman FM (2004) The potential of multivariate quantitative methods for delineation and visualization of ecoregions. Environmental Management 34(5):S39–S60

    Article  Google Scholar 

  • Hastie T, Tibshirani R, Friedman JH (2001) The elements of statistical learning: Data mining, inference, and prediction. Springer, New York, 552 pp

    Google Scholar 

  • Hawkins CP, Norris RH, Gerritsen J, Hughes RM, Jackson SK, Johnson RK, Stevenson RJ (2000) Evaluation of the use of landscape classifications for the prediction of freshwater biota: Synthesis and recommendations. Journal of the North American Benthological Society 19(3):541–556

    Article  Google Scholar 

  • Kaufman L, Rousseeuw PJ (1990) Finding groups in data An introduction to cluster analysis. Wiley and sons Inc, New-York, 342 pp

    Google Scholar 

  • Klijn F, Udo de Haes HA (1994) A hierarchical approach to ecosystems and its implications for ecological land classification. Landscape Ecology 9(2):89–104

    Google Scholar 

  • Leathwick JR, Overton JM, McLeod M (2003) An environmental domain analysis of New Zealand, and its application to biodiversity conservation. Conservation Biology 17(6):1612–1623

    Article  Google Scholar 

  • Legendre P, Legendre L (1998) Numerical ecology. Elsevier, Amsterdam, 853 pp

    Google Scholar 

  • Legendre P, Lapointe F-J, Casgrain P (1994) Modeling brain evolution from behavior: A permutational regression approach. Evolution 48:1487–1499

    Article  Google Scholar 

  • Levin SA (1992) The problem of pattern and scale in ecology. Ecology 73(6):1967–1993

    Article  Google Scholar 

  • Loveland TR, Merchant JM (2004) Ecoregions and ecoregionalization: Geographical and ecological perspectives. Environmental Management 34(Suppl. 1):1–13

    Article  Google Scholar 

  • Mackey BG, Nix HA, Hutchinson MF, McMahon JP, Fleming PM (1988a) Assessing representativeness of places for conservation reservation and heritage listing. Environmental Management 12:501–514

    Article  Google Scholar 

  • Mackey BG, Nix HA, Hutchinson MF, McMahon JP, Fleming PM (1988b) Assessing representativeness of places for conservation reservation and heritage listing. Environmental Management 12(4):501–514

    Article  Google Scholar 

  • Mackey BG, Nix HA, Stein J, Cork E, Bullen FT (1989) Assessing the representativeness of the wet tropics of Queensland world heritage property. Biological Conservation 50(1–4):279–303

    Article  Google Scholar 

  • Mackey BG, Berry SL, Brown T (2008) Reconciling approaches to biogeographical regionalization: A systematic and generic framework examined with a case study of the Australian continent. Journal of Biogeography 35(2):213–229

    Google Scholar 

  • Margules CR, Pressey RL (2000) Systematic conservation planning. Nature 405:243–253

    Article  CAS  Google Scholar 

  • Metzger MJ, Bunce RGH, Jongman RHG, Mücher CA, Watkins JW (2005) A climatic stratification of the environment of Europe. Global Ecology and Biogeography 14:549–563

    Article  Google Scholar 

  • Mielke PWJ (1979) On the asymptotic nonnormality of null distributions of MRRP statistics. Communications in Statistical Theory and Methods 8:1541–1550

    Article  Google Scholar 

  • Moore DM, Lees BG, Davey SM (1991) A new method for predicting vegetation distributions using decision tree analysis in a geographic information system. Environmental Management 15:59–71

    Article  Google Scholar 

  • O’Neill RV, DeAngelis DL, Waide JB, Allen TFH (1986) A hierarchical concept of ecosystems. Princeton University Press, Princeton, 249 pp

    Google Scholar 

  • Oliver I, Holmes A, Dangerfield JM, Gillings M, Pik AJ, Britton DR, Holley M, Montgomery ME, Raison M, Logan V, Pressey RL, Beattie AJ (2004) Land systems as surrogates for biodiversity in conservation planning. Ecological Applications 14(2):485–503

    Article  Google Scholar 

  • Olson DM, Dinerstein E (1998) The global 200: A representation approach to conserving the earth’s most biologically valuable ecoregions. Conservation Biology 12:502–515

    Article  Google Scholar 

  • Omernik JM (1995) Ecoregions: a spatial framework for environmental management. In: Davis WS, Simon TP (eds) Biological assessment and criteria: tools for water resource planning and decision making. Lewis Publishers, Boca Raton, pp 49–62

    Google Scholar 

  • Omernik JM, Bailey RG (1997) Distinguishing between watersheds and ecoregions. Journal of the American Water Resources Association 33(5):935–949

    Article  Google Scholar 

  • Pressey RL, Hager TC, Ryan KM, Schwarz J, Wall S, Ferrier S, Creaser PM (2000) Using abiotic data for conservation assessments over extensive regions: Quantitative methods applied across New South Wales, Australia. Biological Conservation 96:55–82

    Article  Google Scholar 

  • RDevelopmentCoreTeam (2004) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna

    Google Scholar 

  • Sheail J, Bunce RGH (2003) The development and scientific principles of an environmental classification for strategic ecological survey in the United Kingdom. Environmental Conservation 30(2):147–159

    Article  Google Scholar 

  • Snelder TH, Hughey KFD (2005) On the use of an ecological classification to improve water resource planning in New Zealand. Environmental Management 36(5):741–756

    Article  CAS  Google Scholar 

  • Snelder TH, Leathwick JR, Dey KL, Rowden AA, Weatherhead MA, Fenwick GD, Francis MP, Gorman RM, Grieve JM, Hadfield MG, Hewitt JE, Richardson KM, Uddstrom MJ, Zeldis JR (2006) Development of an ecologic marine classification in the New Zealand region. Environmental Management 39(1):12–29

    Article  Google Scholar 

  • Snelder T, Leathwick JR, Dey K (2007) A procedure for making optimal selection of input variables for multivariate environmental classifications. Conservation Biology 21(2):365–375

    Article  Google Scholar 

  • Snelder TH, Pella H, Wasson J, Lamouroux N (2008) Definition procedures have little effect on performance of environmental classifications of streams and rivers. Environmental Management 42:771–788

    Article  Google Scholar 

  • Snelder TH, Lehmann A, Lamouroux N, Leathwick JR, Allenbach K (2009) Strong influence of variable treatment on the performance of numerically defined ecological regions. Environmental Management 44:658–670

    Article  Google Scholar 

  • Trakhtenbrot A, Kadmon R (2005) Environmental cluster analysis as a tool for selecting complementary networks of conservation sites. Ecological Applications 15(1):335–345

    Article  Google Scholar 

  • Van Sickle J (1997) Using mean similarity dendrograms to evaluate classifications. Journal of Agricultural Biological and Environmental Statistics 2(4):370–388

    Article  Google Scholar 

  • Zar JH (1999) Biostatistical analysis. Prentice-Hall, Upper Saddle River, 718 pp

    Google Scholar 

  • Zhou YS, Narumalani WJ, Waltman W, Waltman S, Palecki M (2003) A GIS-based spatial pattern analysis model for ecoregion mapping and characterization. International Journal of Geographic Information Science 17(5):445–462

    Article  Google Scholar 

  • Zimmermann NE, Kienast F (1999) Predictive mapping of alpine grasslands in Switzerland: Species versus community approach. Journal of Vegetation Science 10(4):469–482

    Article  Google Scholar 

Download references

Acknowledgments

Ton Snelder was supported by Marie Curie Incoming International Fellowship within the 6th European Community Framework Programme. We thank Niklaus Zimmermann of WSL (Swiss Federal Institute for Forest, Snow and Landscape Research) for climatic data and Mario Sartori and Daniel Ariztegui from the University of Geneva, as well as Andreas Baumeler from the Schweizerische Geotechnische Kommission for their help in preparing the geological data. Credit goes also to Ramona Maggini (University of Lausanne) for her initial work on this project. Finally, we acknowledge the scientific and financial support of the Swiss Federal Office for the Environment.

Author information

Authors and Affiliations

  1. Biologie des Ecosystèmes Aquatiques, CEMAGREF, Lyon, France

    Ton Snelder & Nicolas Lamouroux

  2. UNEP/DEWA/GRID-Europe, Geneva, Switzerland

    Anthony Lehmann & Karin Allenbach

  3. University of Geneva, Geneva, Switzerland

    Anthony Lehmann

  4. National Institute of Water and Atmosphere (NIWA), Christchurch, New Zealand

    Ton Snelder

  5. National Institute of Water and Atmosphere (NIWA), Hamilton, New Zealand

    John Leathwick

Authors
  1. Ton Snelder
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Anthony Lehmann
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nicolas Lamouroux
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. John Leathwick
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Karin Allenbach
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ton Snelder.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Snelder, T., Lehmann, A., Lamouroux, N. et al. Effect of Classification Procedure on the Performance of Numerically Defined Ecological Regions. Environmental Management 45, 939–952 (2010). https://doi.org/10.1007/s00267-010-9465-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00267-010-9465-7

Keywords

Search

Navigation