Evaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage

Abstract We examine how different datasets, including georeferenced hardcopy maps of different extents and georeferenced herbarium specimens (spanning the range from 100 to 85,000 km2) influence ecological niche modeling. We check 13 of the available environmental niche modeling algorithms, using 30...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kamil Konowalik, Agata Nosol
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/e46194d009fe4317b5199ba2526a933d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e46194d009fe4317b5199ba2526a933d
record_format	dspace
spelling	oai:doaj.org-article:e46194d009fe4317b5199ba2526a933d2021-12-02T14:12:42ZEvaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage10.1038/s41598-020-80062-12045-2322https://doaj.org/article/e46194d009fe4317b5199ba2526a933d2021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-80062-1https://doaj.org/toc/2045-2322Abstract We examine how different datasets, including georeferenced hardcopy maps of different extents and georeferenced herbarium specimens (spanning the range from 100 to 85,000 km2) influence ecological niche modeling. We check 13 of the available environmental niche modeling algorithms, using 30 metrics to score their validity and evaluate which are useful for the selection of the best model. The validation is made using an independent dataset comprised of presences and absences collected in a range-wide field survey of Carpathian endemic plant Leucanthemum rotundifolium (Compositae). Our analysis of models’ predictive performances indicates that almost all datasets may be used for the construction of a species distributional range. Both very local and very general datasets can produce useful predictions, which may be more detailed than the original ranges. Results also highlight the possibility of using the data from manually georeferenced archival sources in reconstructions aimed at establishing species’ ecological niches. We discuss possible applications of those data and associated problems. For the evaluation of models, we suggest employing AUC, MAE, and Bias. We show an example of how AUC and MAE may be combined to select the model with the best performance.Kamil KonowalikAgata NosolNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Kamil Konowalik Agata Nosol Evaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage
description	Abstract We examine how different datasets, including georeferenced hardcopy maps of different extents and georeferenced herbarium specimens (spanning the range from 100 to 85,000 km2) influence ecological niche modeling. We check 13 of the available environmental niche modeling algorithms, using 30 metrics to score their validity and evaluate which are useful for the selection of the best model. The validation is made using an independent dataset comprised of presences and absences collected in a range-wide field survey of Carpathian endemic plant Leucanthemum rotundifolium (Compositae). Our analysis of models’ predictive performances indicates that almost all datasets may be used for the construction of a species distributional range. Both very local and very general datasets can produce useful predictions, which may be more detailed than the original ranges. Results also highlight the possibility of using the data from manually georeferenced archival sources in reconstructions aimed at establishing species’ ecological niches. We discuss possible applications of those data and associated problems. For the evaluation of models, we suggest employing AUC, MAE, and Bias. We show an example of how AUC and MAE may be combined to select the model with the best performance.
format	article
author	Kamil Konowalik Agata Nosol
author_facet	Kamil Konowalik Agata Nosol
author_sort	Kamil Konowalik
title	Evaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage
title_short	Evaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage
title_full	Evaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage
title_fullStr	Evaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage
title_full_unstemmed	Evaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage
title_sort	evaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/e46194d009fe4317b5199ba2526a933d
work_keys_str_mv	AT kamilkonowalik evaluationmetricsandvalidationofpresenceonlyspeciesdistributionmodelsbasedondistributionalmapswithvaryingcoverage AT agatanosol evaluationmetricsandvalidationofpresenceonlyspeciesdistributionmodelsbasedondistributionalmapswithvaryingcoverage
_version_	1718391817204924416

Evaluation metrics and validation of presence-only species distribution models based on distributional maps with varying coverage

Ejemplares similares