Evaluation of consensus methods in predictive species distribution modelling

Diversity and Distributions - Tập 15 Số 1 - Trang 59-69 - 2009
Mathieu Marmion1, Miia Parviainen1, Miska Luoto1, Risto K. Heikkinen2, Wilfried Thuiller3
1Thule Institute, University of Oulu, PO Box 3000, FIN‐90014 Oulu, Finland,
2Finnish Environment Institute, Research Program for Biodiversity, PO Box 140, FIN-00251 Helsinki, Finland,
3Laboratoire d’Ecologie Alpine, UMR CNRS 5553, Université Joseph Fourier, BP 53, 38041, Grenoble Cedex 9, France

Tóm tắt

ABSTRACTAim  Spatial modelling techniques are increasingly used in species distribution modelling. However, the implemented techniques differ in their modelling performance, and some consensus methods are needed to reduce the uncertainty of predictions. In this study, we tested the predictive accuracies of five consensus methods, namely Weighted Average (WA), Mean(All), Median(All), Median(PCA), and Best, for 28 threatened plant species.Location  North‐eastern Finland, Europe.Methods  The spatial distributions of the plant species were forecasted using eight state‐of‐the‐art single‐modelling techniques providing an ensemble of predictions. The probability values of occurrence were then combined using five consensus algorithms. The predictive accuracies of the single‐model and consensus methods were assessed by computing the area under the curve (AUC) of the receiver‐operating characteristic plot.Results  The mean AUC values varied between 0.697 (classification tree analysis) and 0.813 (random forest) for the single‐models, and from 0.757 to 0.850 for the consensus methods. WA and Mean(All) consensus methods provided significantly more robust predictions than all the single‐models and the other consensus methods.Main conclusions  Consensus methods based on average function algorithms may increase significantly the accuracy of species distribution forecasts, and thus they show considerable promise for different conservation biological and biogeographical applications.

Từ khóa


Tài liệu tham khảo

Ahti T., 1968, Vegetation zones and their sections in northwestern Europe, Annales Botanici Fennici, 5, 169

10.1111/j.1365-2699.2006.01584.x

10.1016/j.tree.2006.09.010

10.1111/j.1365-2486.2005.01000.x

10.1111/j.1466-822X.2005.00182.x

10.1111/j.1365-2699.2006.01482.x

Atlas of Finland, 1987, Climatology, folio 131

10.1111/j.1365-2664.2006.01164.x

10.2307/1943043

10.1111/j.1365-2664.2006.01136.x

10.1111/j.1600-0870.2004.00039.x

10.2307/2845519

10.1023/A:1010933404324

Burnham K.P., 2002, Model selection and multimodel inference: a practical information‐theoretic approach

10.1046/j.0305-0270.2003.01006.x

10.1890/07-0539.1

10.1016/j.ecolmodel.2006.05.016

10.1016/S0304-3800(02)00202-8

10.1016/j.ecolmodel.2004.12.007

10.1111/j.2006.0906-7590.04596.x

10.1111/j.1472-4642.2007.00340.x

Environment Systems Research Institute (ESRI), 1991, ARC/INFO user's guide. Cell‐based modelling with GRID. Analysis, display and management

European Commission, 1994, EUR 12585 – CORINE land cover – technical guide

10.1016/j.jenvman.2004.04.007

10.1017/S0376892997000088

10.1214/aos/1176347963

10.1111/j.1523-1739.2001.00112.x

10.1111/j.1472-4642.2007.00365.x

10.1016/j.jhydrol.2006.10.002

10.1198/07350010152472599

10.1111/j.1461-0248.2005.00792.x

10.1890/06-0539

10.1111/j.1523-1739.2006.00354.x

10.1111/j.1461-0248.2006.00954.x

Hastie T.&Tibshirani R.(1996)S Archive: (mda). StatLib.http://lib.stat.cmu.edu/S/.

10.1177/0309133306071957

10.1111/j.1466-8238.2007.00345.x

10.1111/j.0906-7590.2006.04700.x

10.1016/j.tree.2003.10.013

Laplace P.S., 1820, Théorie analytique des probabilités

10.1111/j.1365-2486.2006.01191.x

10.1111/j.1523-1739.2003.00233.x

10.1046/j.1365-2664.1999.00440.x

McNees S.K., 1987, Consensus forecasts: tyranny of the majority?, New England Economic Review, 15

10.1111/j.1366-9516.2005.00188.x

10.1016/S0014-5793(00)02321-8

10.1110/ps.0226702

10.1111/j.1365-2699.2008.01922.x

10.1111/j.1365-2699.2006.01460.x

10.1007/s10021-005-0054-1

10.1111/j.1365-2699.2006.01466.x

Ridgeway G., 1999, The state of boosting, Computing Sciences and Statistics, 31, 172

10.1111/j.1472-4642.2007.00356.x

10.1201/9780203881095

10.1175/1520-0450(1963)002<0191:OSPF>2.0.CO;2

Scott J.M., 2002, Predicting species occurrences. Issues of accuracy and scale

10.1111/j.1365-2699.2004.01076.x

10.14512/gaia.14.1.20

10.1111/j.0906-7590.2004.03823.x

10.1002/(SICI)1097-0258(19980430)17:8<857::AID-SIM777>3.0.CO;2-E

10.1046/j.1365-2486.2003.00666.x

10.1111/j.1365-2486.2004.00859.x

10.1038/448550a

10.1111/j.1654-1103.2003.tb02199.x

10.1073/pnas.0409902102

10.1111/j.0906-7590.2006.04674.x

10.1016/S1474-7065(02)00140-7

10.1016/j.biocon.2004.07.004

Thông tin
Thông tin xuất bản

Diversity and Distributions

Tập 15 Số 1

59-69

Thông tin tác giả