Evaluating the ability of habitat suitability models to predict species presences.

Détails

ID Serval
serval:BIB_24DB4B5866C2
Type
Article: article d'un périodique ou d'un magazine.
Collection
Publications
Titre
Evaluating the ability of habitat suitability models to predict species presences.
Périodique
Ecological Modelling.
Auteur(s)
Hirzel A.H., Le Lay G., Helfer V., Randin C., Guisan A.
ISSN
0304-3800
Statut éditorial
Publié
Date de publication
2006
Peer-reviewed
Oui
Volume
199
Numéro
1
Pages
142-152
Langue
anglais
Notes
2nd Workshop on Advances in Predictive Species Distribution Models Riederalp, SWITZERLAND, 2004
Résumé
Models predicting species spatial distribution are increasingly applied to wildlife management issues, emphasising the need for reliable methods to evaluate the accuracy of their predictions. As many available datasets (e.g. museums, herbariums, atlas) do not provide reliable information about species absences, several presence-only based analyses have been developed. However, methods to evaluate the accuracy of their predictions are few and have never been validated. The aim of this paper is to compare existing and new presenceonly evaluators to usual presence/absence measures.
We use a reliable, diverse, presence/absence dataset of 114 plant species to test how common presence/absence indices (Kappa, MaxKappa, AUC, adjusted D-2) compare to presenceonly measures (AVI, CVI, Boyce index) for evaluating generalised linear models (GLM). Moreover we propose a new, threshold-independent evaluator, which we call "continuous Boyce index". All indices were implemented in the B10MAPPER software.
We show that the presence-only evaluators are fairly correlated (p > 0.7) to the presence/absence ones. The Boyce indices are closer to AUC than to MaxKappa and are fairly insensitive to species prevalence. In addition, the Boyce indices provide predicted-toexpected ratio curves that offer further insights into the model quality: robustness, habitat suitability resolution and deviation from randomness. This information helps reclassifying predicted maps into meaningful habitat suitability classes. The continuous Boyce index is thus both a complement to usual evaluation of presence/absence models and a reliable measure of presence-only based predictions.
Mots-clé
niche-based modelling, model evaluation, cross-validation, generalised linear models (GLM), alpine plants, Swiss Alps
Web of science
Création de la notice
19/11/2007 10:50
Dernière modification de la notice
03/03/2018 15:00
Données d'usage