Overcoming limitations of modelling rare species by using ensembles of small models

Methods in Ecology and Evolution - Tập 6 Số 10 - Trang 1210-1218 - 2015
Frank T. Breiner1,2, Antoine Guisan1,3, Ariel Bergamini2, Michael P. Nobis2
1Department of Ecology and Evolution, University of Lausanne, 1015 Lausanne, Switzerland
2Swiss Federal Research Institute WSL, Zürcherstrasse 111, 8903 Birmensdorf, Switzerland
3Institute of Earth Surface Dynamics. University of Lausanne, 1015 Lausanne, Switzerland

Tóm tắt

SummarySpecies distribution models (SDMs) have become a standard tool in ecology and applied conservation biology. Modelling rare and threatened species is particularly important for conservation purposes. However, modelling rare species is difficult because the combination of few occurrences and many predictor variables easily leads to model overfitting. A new strategy using ensembles of small models was recently developed in an attempt to overcome this limitation of rare species modelling and has been tested successfully for only a single species so far. Here, we aim to test the approach more comprehensively on a large number of species including a transferability assessment.For each species, numerous small (here bivariate) models were calibrated, evaluated and averaged to an ensemble weighted byAUCscores. These ‘ensembles of small models’ (ESMs) were compared to standardSDMs using three commonly used modelling techniques (GLM,GBMand Maxent) and their ensemble prediction. We tested 107 rare and under‐sampled plant species of conservation concern in Switzerland.We show thatESMs performed significantly better than standardSDMs. The rarer the species, the more pronounced the effects were.ESMs were also superior to standardSDMs and their ensemble when they were evaluated using a transferability assessment.By averaging simple small models to an ensemble,ESMs avoid overfitting without losing explanatory power through reducing the number of predictor variables. They further improve the reliability of species distribution models, especially for rare species, and thus help to overcome limitations of modelling rare species.

Từ khóa


Tài liệu tham khảo

10.1109/TAC.1974.1100705

10.1111/j.1365-2664.2006.01214.x

10.1016/j.tree.2006.09.010

10.1111/j.1365-2486.2005.01000.x

10.1111/j.1365-2664.2006.01136.x

10.1111/j.1600-0587.2011.06545.x

10.1007/s101130000018

Burnham K.P., 2002, Model Selection and Multimodel Inference: A Practical Information‐Theoretic Approach

10.1111/avsc.12028

10.1111/j.1466-8238.2009.00485.x

10.1111/j.1600-0587.2012.07348.x

10.1111/j.2007.0906-7590.05171.x

10.1111/j.1600-0587.2008.05505.x

10.1111/j.2006.0906-7590.04596.x

10.1017/CBO9780511810602

10.1111/j.1472-4642.2008.00536.x

10.1890/09-1190.1

10.1111/j.1472-4642.2007.00342.x

10.1111/j.1461-0248.2005.00792.x

10.1111/ele.12189

10.1002/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4

10.1111/j.1600-0587.2011.06999.x

10.1111/j.0906-7590.2006.04700.x

10.1016/j.ecolmodel.2006.05.017

10.1111/j.1466-8238.2011.00683.x

10.1080/136588197242266

Lehmann A. Allenbach K. Maggini R. Richard J.‐P. Jacquet J.‐M.&Dao H.(2010)Swiss environmental domains: a new spatial framework for reporting on the environment Environment. Federal Office for the Environment FOEN Environmental studies no. 1024 Bern.

10.1111/j.1466-8238.2007.00358.x

10.1016/j.biocon.2010.07.007

10.1111/j.1472-4642.2008.00491.x

Moser D., 2002, Rote Liste der gefährdeten Farn‐ und Blütenpflanzen der Schweiz

10.1111/j.1472-4642.2011.00793.x

10.1111/j.1365-2664.2008.01516.x

10.1111/j.1365-2699.2008.01922.x

10.1016/j.ecolmodel.2007.11.008

10.23943/princeton/9780691136868.001.0001

10.1126/science.1215933

10.1111/j.1365-2699.2006.01466.x

10.1214/aos/1176344136

10.1111/j.1365-2699.2004.01076.x

10.1111/j.1365-2664.2006.01162.x

10.1111/ddi.12031

10.1016/S0304-3800(01)00388-X

10.1029/96WR03137

10.1111/j.1600-0587.2008.05742.x

10.1038/nature09705

Tibshirani R., 1996, Regression shrinkage and selection via the lasso, Journal of the Royal Statistical Society, 58, 267, 10.1111/j.2517-6161.1996.tb02080.x

10.1016/j.ecolmodel.2008.11.010

10.1111/j.1365-2664.2005.01052.x

10.1111/j.2041-210X.2011.00170.x

10.1111/j.1472-4642.2008.00482.x

10.2307/3237182

Thông tin
Thông tin xuất bản

Methods in Ecology and Evolution

Tập 6 Số 10

1210-1218

Thông tin tác giả