Assessing the reliability of species distribution projections in climate change research
作者： Luca Santini , Ana Benítez-López , Luigi Maiorano , Mirza Čengić , Mark A.J. Huijbregts
DOI: 10.1101/2020.06.10.143917
关键词: Econometrics 、 Climate change 、 Reliability (statistics) 、 Computer science 、 Field (geography) 、 Species distribution 、 Random forest
摘要: Forecasting changes in species distribution under future scenarios is one of the most prolific areas application for models (SDMs). However, no consensus yet exists on reliability such drawing conclusions response to changing climate. In this study we first provide an overview common modelling practices field by reviewing papers published last 5 years. Then, use a virtual approach and three commonly applied SDM algorithms (GLM, MaxEnt Random Forest) assess estimated (cross-validated) actual predictive performance parameterized with different settings violations assumptions. Our literature review shows that model climate change rely single (65%), include fitted small samples (
sci-hub.st 参考文章(100)
Matthew Wiener, Andy Liaw, Classification and Regression by randomForest ,(2007)
Carsten Meyer, Patrick Weigelt, Holger Kreft, Multidimensional biases, gaps and uncertainties in global plant occurrence information Ecology Letters. ,vol. 19, pp. 992- 1006 ,(2016) , 10.1111/ELE.12624
Mike P. Austin, Kimberly P. Van Niel, Improving species distribution models for climate change studies: variable selection and scale Journal of Biogeography. ,vol. 38, pp. 1- 8 ,(2011) , 10.1111/J.1365-2699.2010.02416.X
Nicholas W Synes, Patrick E Osborne, None, Choice of predictor variables as a source of uncertainty in continental‐scale species distribution modelling under climate change Global Ecology and Biogeography. ,vol. 20, pp. 904- 914 ,(2011) , 10.1111/J.1466-8238.2010.00635.X
Morgane Barbet-Massin, Frédéric Jiguet, Cécile Hélène Albert, Wilfried Thuiller, Selecting pseudo-absences for species distribution models: how, where and how many? Methods in Ecology and Evolution. ,vol. 3, pp. 327- 338 ,(2012) , 10.1111/J.2041-210X.2011.00172.X
OMRI ALLOUCHE, ASAF TSOAR, RONEN KADMON, Assessing the accuracy of species distribution models: prevalence, kappa and the true skill statistic (TSS) Journal of Applied Ecology. ,vol. 43, pp. 1223- 1232 ,(2006) , 10.1111/J.1365-2664.2006.01214.X
Piero Visconti, Michel Bakkenes, Daniele Baisero, Thomas Brooks, Stuart H. M. Butchart, Lucas Joppa, Rob Alkemade, Moreno Di Marco, Luca Santini, Michael Hoffmann, Luigi Maiorano, Robert L. Pressey, Anni Arponen, Luigi Boitani, April E. Reside, Detlef P. van Vuuren, Carlo Rondinini, Projecting Global Biodiversity Indicators under Future Development Scenarios Conservation Letters. ,vol. 9, pp. 5- 13 ,(2016) , 10.1111/CONL.12159
Boris Leroy, Christine N. Meynard, Céline Bellard, Franck Courchamp, virtualspecies, an R package to generate virtual species distributions Ecography. ,vol. 39, pp. 599- 607 ,(2016) , 10.1111/ECOG.01388
André S. J. Proosdij, Marc S. M. Sosef, Jan J. Wieringa, Niels Raes, Minimum required number of specimen records to develop accurate species distribution models Ecography. ,vol. 39, pp. 542- 552 ,(2016) , 10.1111/ECOG.01509
Catherine H Graham, Jane Elith, Robert J Hijmans, Antoine Guisan, A Townsend Peterson, Bette A Loiselle, NCEAS Predicting Species Distributions Working Group, None, The influence of spatial errors in species occurrence data used in distribution models Journal of Applied Ecology. ,vol. 45, pp. 239- 247 ,(2007) , 10.1111/J.1365-2664.2007.01408.X