Making better Maxent models of species distributions: complexity, overfitting and evaluation

Models of species niches and distributions have become invaluable to biogeographers over the past decade, yet several outstanding methodological issues remain. Here we address three critical ones: selecting appropriate evaluation data, detecting overfitting, and tuning program settings to approximate optimal model complexity. We integrate solutions to these issues for Maxent models, using the Caribbean spiny pocket mouse, Heteromys anomalus, as an example.

[1]  Antoine Guisan,et al.  Predictive habitat distribution models in ecology , 2000 .

[2]  Anthony Lehmann,et al.  GRASP: generalized regression analysis and spatial prediction , 2002 .

[3]  M. Boyce,et al.  Evaluating resource selection functions , 2002 .

[4]  Robert P. Anderson,et al.  Geographical distributions of spiny pocket mice in South America: insights from predictive models , 2002 .

[5]  Patrick E. Osborne,et al.  Should data be partitioned spatially before building large-scale distribution models? , 2002 .

[6]  Robert P. Anderson,et al.  Using niche-based GIS modeling to test geographic predictions of competitive exclusion and competitive release in South American pocket mice , 2002 .

[7]  S. Reddy,et al.  Geographical sampling bias and its implications for conservation priorities in Africa , 2003 .

[8]  A. Peterson.  Predicting the Geography of Species’ Invasions via Ecological Niche Modeling , 2003, The Quarterly Review of Biology.

[9]  Robert P. Anderson,et al.  Taxonomy, Distribution, and Natural History of the Genus Heteromys (Rodentia: Heteromyidae) in Western Venezuela, with the Description of a Dwarf Species from the Península de Paraguaná , 2003 .

[10]  Robert P. Anderson,et al.  Real vs. artefactual absences in species distributions: tests for Oryzomys albigularis (Rodentia: Muridae) in Venezuela , 2003 .

[11]  T. Dawson,et al.  Predicting the impacts of climate change on the distribution of species: are bioclimate envelope models useful? , 2003 .

[12]  Lisette Cantú-Salazar,et al.  Historical and present distribution of coyote (Canis latrans) in Mexico and Central America , 2004 .

[13]  A. Townsend Peterson,et al.  Predicting invasions of North American basses in Japan using native range data and a genetic algorithm , 2004 .

[14]  S. Lavorel,et al.  Effects of restricting environmental range of data to project current and future species distributions , 2004 .

[15]  M. Araújo,et al.  Reducing uncertainty in projections of extinction risk from climate change , 2005 .

[16]  W. Thuiller,et al.  Predicting species distribution: offering more than simple habitat models. , 2005, Ecology letters.

[17]  Jane Elith,et al.  Fauna habitat modelling and mapping: A review and case study in the Lower Hunter Central Coast region of NSW , 2005 .

[18]  M. Araújo,et al.  Validation of species–climate impact models under climate change , 2005 .

[19]  R. Pearson,et al.  Predicting species distributions from small numbers of occurrence records: A test case using cryptic geckos in Madagascar , 2006 .

[20]  A. Townsend Peterson,et al.  Novel methods improve prediction of species' distributions from occurrence data , 2006 .

[21]  A. Peterson.  Uses and requirements of ecological niche models and related distributional models , 2006 .

[22]  P. Hernandez,et al.  The effect of sample size and species characteristics on performance of different species distribution modeling methods , 2006 .

[23]  M. Zappa,et al.  Are niche‐based species distribution models transferable in space? , 2006 .

[24]  M. Araújo,et al.  How Does Climate Change Affect Biodiversity? , 2006, Science.

[25]  Robert P. Anderson,et al.  Maximum entropy modeling of species geographic distributions , 2006 .

[26]  M. Araújo,et al.  Five (or so) challenges for species distribution modelling , 2006 .

[27]  Helen T. Murphy,et al.  Accounting for regional niche variation in habitat suitability models , 2007 .

[28]  Bette A. Loiselle,et al.  Predicting species distributions from herbarium collections: does climate bias in collection sampling influence model outcomes? , 2007 .

[29]  R. Pearson,et al.  Applications of ecological niche modeling for species delimitation: a review and empirical evaluation using day geckos (Phelsuma) from Madagascar. , 2007, Systematic biology.

[30]  K. J. Willis,et al.  The ability of climate envelope models to predict the effect of climate change on species distributions , 2007 .

[31]  S. Suárez‐Seoane,et al.  Non‐stationarity and local approaches to modelling the distributions of wildlife , 2007 .

[32]  S. Jackson,et al.  Novel climates, no‐analog communities, and ecological surprises , 2007 .

[33]  A. Townsend Peterson,et al.  Transferability and model evaluation in ecological niche modeling: a comparison of GARP and Maxent , 2007 .

[34]  Miroslav Dudík,et al.  Modeling of species distributions with Maxent: new extensions and a comprehensive evaluation , 2008 .

[35]  J. Lobo,et al.  Historical bias in biodiversity inventories affects the observed environmental niche of the species , 2008 .

[36]  R. Real,et al.  AUC: a misleading measure of the performance of predictive distribution models , 2008 .

[37]  C. Graham,et al.  Integrating GIS-based environmental data into evolutionary biology. , 2008, Trends in ecology & evolution.

[38]  A. Peterson,et al.  Effects of sample size on the performance of species distribution models , 2008 .

[39]  Steven J. Phillips.  Transferability, sample selection bias and background data in presence‐only modelling: a response to Peterson et al. (2007) , 2008 .

[40]  A. Townsend Peterson,et al.  Rethinking receiver operating characteristic analysis applications in ecological niche modeling , 2008 .

[41]  Robert P. Anderson,et al.  Chapter 2. Taxonomy, Distribution, and Natural History of the Genus Heteromys (Rodentia: Heteromyidae) in Central and Eastern Venezuela, with the Description of a New Species from the Cordillera de la Costa , 2009 .

[42]  Steven J. Phillips,et al.  Sample selection bias and presence-only distribution models: implications for background and pseudo-absence data. , 2009, Ecological applications : a publication of the Ecological Society of America.

[43]  Sam Veloz,et al.  Spatially autocorrelated sampling falsely inflates measures of accuracy for presence‐only niche models , 2009 .

[44]  D. Nogues‐Bravo,et al.  Predicting the past distribution of species climatic niches. , 2009 .

[45]  T. Jezkova,et al.  Pleistocene Impacts on the Phylogeography of the Desert Pocket Mouse (Chaetodipus penicillatus) , 2009 .

[46]  F. Jiguet,et al.  How much do we overestimate future local extinction rates when restricting the range of occurrence data in climate suitability models , 2010 .

[47]  Steven J. Phillips,et al.  The art of modelling range‐shifting species , 2010 .

[48]  Jane Elith,et al.  POC plots: calibrating species distribution models with presence-only data. , 2010, Ecology.

[49]  Robert P. Anderson,et al.  The effect of the extent of the study region on GIS models of species geographic distributions and estimates of niche evolution: preliminary tests with montane rodents (genus Nephelomys) in Venezuela , 2010 .

[50]  Georgina M. Mace,et al.  Distorted Views of Biodiversity: Spatial and Temporal Bias in Species Occurrence Data , 2010, PLoS biology.

[51]  Dan L Warren,et al.  Ecological niche modeling in Maxent: the importance of model complexity and the performance of model selection criteria. , 2011, Ecological applications : a publication of the Ecological Society of America.

[52]  Trevor Hastie,et al.  A statistical explanation of MaxEnt for ecologists , 2011 .

[53]  A. Peterson,et al.  Use of niche models in invasive species risk assessments , 2011, Biological Invasions.

[54]  Robert P. Anderson,et al.  Species-specific tuning increases robustness to sampling bias in models of species distributions: An implementation with Maxent , 2011 .

[55]  A. Peterson,et al.  The crucial role of the accessible area in ecological niche modeling and species distribution modeling , 2011 .

[56]  Robert P. Anderson,et al.  Ecological Niches and Geographic Distributions , 2011 .

[57]  Robert P. Anderson,et al.  Harnessing the world's biodiversity data: promise and peril in ecological niche modeling of species distributions , 2012, Annals of the New York Academy of Sciences.

[58]  R. Hijmans,et al.  Cross-validation of species distribution models: removing spatial sorting bias and calibration with a null model. , 2012, Ecology.

[59]  B. McGill,et al.  Testing the predictive performance of distribution models , 2013 .

[60]  D. Warton,et al.  Equivalence of MAXENT and Poisson Point Process Models for Species Distribution Modeling in Ecology , 2013, Biometrics.

[61]  Robert P. Anderson,et al.  Estimating optimal complexity for ecological niche models: A jackknife approach for species with small sample sizes , 2013 .

[62]  Robert P. Anderson,et al.  A framework for using niche models to estimate impacts of climate change on species distributions , 2013, Annals of the New York Academy of Sciences.

[63]  Steven J. Phillips,et al.  Shifts in Arctic vegetation and associated feedbacks under climate change , 2013 .