Several methods has been proposed to modeling species distributions, also a few models consider explicitly spatial autocorrelation or spatial neighborhood. We compare a model based on autologistic model with covariates with standard methods frequently used in species distribution models. Accuracy assessment is important in species distribution models. The value of a model depends on the accuracy of its outputs. We evaluated the accuracy in terms of ROC analysis and the F-measure proposed by Li and Gou 2013 for virtual species and for real species data.
(2014). Spatial autocorrelation in species distribution models: autologistic model with covariates vs. BioMod [conference presentation - intervento a convegno]. Retrieved from http://hdl.handle.net/10446/31700
Spatial autocorrelation in species distribution models: autologistic model with covariates vs. BioMod
2014-01-01
Abstract
Several methods has been proposed to modeling species distributions, also a few models consider explicitly spatial autocorrelation or spatial neighborhood. We compare a model based on autologistic model with covariates with standard methods frequently used in species distribution models. Accuracy assessment is important in species distribution models. The value of a model depends on the accuracy of its outputs. We evaluated the accuracy in terms of ROC analysis and the F-measure proposed by Li and Gou 2013 for virtual species and for real species data.File | Dimensione del file | Formato | |
---|---|---|---|
3178-6564-1-PB.pdf
accesso aperto
Descrizione: publisher's version - versione dell'editore
Dimensione del file
119.14 kB
Formato
Adobe PDF
|
119.14 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
Aisberg ©2008 Servizi bibliotecari, Università degli studi di Bergamo | Terms of use/Condizioni di utilizzo