Selecting thresholds of occurrence in the prediction of species distributions
TLDR
Twelve approaches to determining thresholds were compared using two species in Europe and artificial neural networks, and the modelling results were assessed using four indices: sensitivity, specificity, overall prediction success and Cohen's kappa statistic.Abstract:
Transforming the results of species distribution modelling from probabilities of or suitabilities for species occurrence to presences/absences needs a specific threshold. Even though there are many approaches to determining thresholds, there is no comparative study. In this paper, twelve approaches were compared using two species in Europe and artificial neural networks, and the modelling results were assessed using four indices: sensitivity, specificity, overall prediction success and Cohen's kappa statistic. The results show that prevalence approach, average predicted probability/suitability approach, and three sensitivity-specificity-combined approaches, including sensitivity-specificity sum maximization approach, sensitivity-specificity equality approach and the approach based on the shortest distance to the top-left corner (0,1) in ROC plot, are the good ones. The commonly used kappa maximization approach is not as good as the afore-mentioned ones, and the fixed threshold approach is the worst one. We also recommend using datasets with prevalence of 50% to build models if possible since most optimization criteria might be satisfied or nearly satisfied at the same time, and therefore it's easier to find optimal thresholds in this situation.read more
Citations
More filters
Journal ArticleDOI
Taxonomy and biogeography of Bunopus spatalurus (Reptilia; Gekkonidae) from the Arabian Peninsula
Philip de Pous,Luis Machado,Luis Machado,Margarita Metallinou,Jan Červenka,Lukáš Kratochvíl,Nefeli Paschou,Tomáš Mazuch,Jiří Šmíd,Marc Simó-Riudalbas,Delfi Sanuy,Salvador Carranza +11 more
TL;DR: This work addresses for the first time the taxonomy and biogeography of Bunopus spatalurus Anderson, 1901, from Arabia using multilocus concatenated and species tree phylogenies, haplotype networks and morphology and resurrects the genus Trachydactylus hajarensis, which is not monophyletic.
Journal ArticleDOI
Modelling potential impacts of climate change on the bioclimatic envelope and conservation of the Maned Wolf (Chrysocyon brachyurus)
TL;DR: The FGOALS model was the best option for projecting species occurrence into the future because it included the three localities known for the Maned Wolf from the late Pleistocene and predicts stable areas that coincide with spatial patterns of genetic diversity.
Journal ArticleDOI
Santa Maria di Leuca province (Mediterranean Sea): Identification of suitable mounds for cold-water coral settlement using geomorphometric proxies and maxent methods
Annaëlle Bargain,Fabrice Marchese,Alessandra Savini,Marco Taviani,Marco Taviani,Marie-Claire Fabri +5 more
TL;DR: In this article, a fine scale index quantifying the landscape elevation (Bathymetric Position Index at 120m resolution) was used to select all the elevated features considered as candidate morphologies for potential coral mounds.
Journal ArticleDOI
Ecological Niche Modelling of Potential West Nile Virus Vector Mosquito Species and Their Geographical Association with Equine Epizootics in Italy
Lapo Mughini-Gras,Paolo Mulatti,Francesco Severini,Daniela Boccolini,Roberto Romi,Gioia Bongiorno,Cristina Khoury,Riccardo Bianchi,Fabrizio Montarsi,T. Patregnani,Lebana Bonfanti,Giovanni Rezza,Gioia Capelli,Luca Busani +13 more
TL;DR: Maxent-based ecological niche models developed using literature records of 13 potential WNV Italian vector mosquito species were developed to predict their habitat suitability range and to investigate possible geographical associations with WNV equine outbreak occurrence, providing circumstantial evidence that the potential distribution of these two species coincides geographically with the observed distribution of the disease in equines.
Journal ArticleDOI
Examining Local Transferability of Predictive Species Distribution Models for Invasive Plants: An Example with Cogongrass (Imperata cylindrica)
TL;DR: Results suggest that, although relatively robust SDMs can be developed for a given area, those models should not be extrapolated to other areas without careful examination of the underlying environmental predictors, and suggest that within an individual area of interest and with proper care, modeling approaches have potential to contribute to efforts at developing scientifically and statistically based weed management programs for invasive species.
References
More filters
Journal ArticleDOI
Predictive habitat distribution models in ecology
TL;DR: A review of predictive habitat distribution modeling is presented, which shows that a wide array of models has been developed to cover aspects as diverse as biogeography, conservation biology, climate change research, and habitat or species management.
Journal ArticleDOI
Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine.
Mark H. Zweig,Gregory Campbell +1 more
TL;DR: Receiver-operating characteristic (ROC) plots provide a pure index of accuracy by demonstrating the limits of a test's ability to discriminate between alternative states of health over the complete spectrum of operating conditions.
Journal ArticleDOI
A review of methods for the assessment of prediction errors in conservation presence/absence models
Alan H. Fielding,John Bell +1 more
TL;DR: Thirteen recommendations are made to enable the objective selection of an error assessment technique for ecological presence/absence models and a new approach to estimating prediction error, which is based on the spatial characteristics of the errors, is proposed.
Journal ArticleDOI
Basic principles of ROC analysis
TL;DR: ROC analysis is shown to be related in a direct and natural way to cost/benefit analysis of diagnostic decision making and the concepts of "average diagnostic cost" and "average net benefit" are developed and used to identify the optimal compromise among various kinds of diagnostic error.
Journal ArticleDOI
Generalized linear and generalized additive models in studies of species distributions: setting the scene
TL;DR: A series of papers prepared within the framework of an international workshop entitled: Advances in GLMs /GAMs modeling: from species distribution to environmental management, held in Riederalp, Switzerland, 6 � /11 August 2001 are introduced.
Related Papers (5)
Novel methods improve prediction of species' distributions from occurrence data
Jane Elith,Catherine H. Graham,Robert P. Anderson,Miroslav Dudík,Simon Ferrier,Antoine Guisan,Robert J. Hijmans,Falk Huettmann,John R. Leathwick,Anthony Lehmann,Jin Li,Lúcia G. Lohmann,Bette A. Loiselle,Glenn Manion,Craig Moritz,Miguel Nakamura,Yoshinori Nakazawa,Jacob C. M. Mc Overton,A. Townsend Peterson,Steven J. Phillips,Karen Richardson,Ricardo Scachetti-Pereira,Robert E. Schapire,Jorge Soberón,Stephen E. Williams,Mary S. Wisz,Niklaus E. Zimmermann +26 more