Spatial validation reveals poor predictive performance of large-scale ecological mapping models

Mapping ecological variables using machine-learning algorithms based on remote-sensing data has become a widespread practice in ecology. Here, the authors use forest biomass mapping as a study case to show that the most common model validation approach, which ignores data spatial structure, leads to...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Pierre Ploton, Frédéric Mortier, Maxime Réjou-Méchain, Nicolas Barbier, Nicolas Picard, Vivien Rossi, Carsten Dormann, Guillaume Cornu, Gaëlle Viennois, Nicolas Bayol, Alexei Lyapustin, Sylvie Gourlet-Fleury, Raphaël Pélissier
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2020
Materias:
Q
Acceso en línea:https://doaj.org/article/628f13be6ee34becb88ef385ebe283e3
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:628f13be6ee34becb88ef385ebe283e3
record_format dspace
spelling oai:doaj.org-article:628f13be6ee34becb88ef385ebe283e32021-12-02T17:19:41ZSpatial validation reveals poor predictive performance of large-scale ecological mapping models10.1038/s41467-020-18321-y2041-1723https://doaj.org/article/628f13be6ee34becb88ef385ebe283e32020-09-01T00:00:00Zhttps://doi.org/10.1038/s41467-020-18321-yhttps://doaj.org/toc/2041-1723Mapping ecological variables using machine-learning algorithms based on remote-sensing data has become a widespread practice in ecology. Here, the authors use forest biomass mapping as a study case to show that the most common model validation approach, which ignores data spatial structure, leads to overoptimistic assessment of model predictive power.Pierre PlotonFrédéric MortierMaxime Réjou-MéchainNicolas BarbierNicolas PicardVivien RossiCarsten DormannGuillaume CornuGaëlle ViennoisNicolas BayolAlexei LyapustinSylvie Gourlet-FleuryRaphaël PélissierNature PortfolioarticleScienceQENNature Communications, Vol 11, Iss 1, Pp 1-11 (2020)
institution DOAJ
collection DOAJ
language EN
topic Science
Q
spellingShingle Science
Q
Pierre Ploton
Frédéric Mortier
Maxime Réjou-Méchain
Nicolas Barbier
Nicolas Picard
Vivien Rossi
Carsten Dormann
Guillaume Cornu
Gaëlle Viennois
Nicolas Bayol
Alexei Lyapustin
Sylvie Gourlet-Fleury
Raphaël Pélissier
Spatial validation reveals poor predictive performance of large-scale ecological mapping models
description Mapping ecological variables using machine-learning algorithms based on remote-sensing data has become a widespread practice in ecology. Here, the authors use forest biomass mapping as a study case to show that the most common model validation approach, which ignores data spatial structure, leads to overoptimistic assessment of model predictive power.
format article
author Pierre Ploton
Frédéric Mortier
Maxime Réjou-Méchain
Nicolas Barbier
Nicolas Picard
Vivien Rossi
Carsten Dormann
Guillaume Cornu
Gaëlle Viennois
Nicolas Bayol
Alexei Lyapustin
Sylvie Gourlet-Fleury
Raphaël Pélissier
author_facet Pierre Ploton
Frédéric Mortier
Maxime Réjou-Méchain
Nicolas Barbier
Nicolas Picard
Vivien Rossi
Carsten Dormann
Guillaume Cornu
Gaëlle Viennois
Nicolas Bayol
Alexei Lyapustin
Sylvie Gourlet-Fleury
Raphaël Pélissier
author_sort Pierre Ploton
title Spatial validation reveals poor predictive performance of large-scale ecological mapping models
title_short Spatial validation reveals poor predictive performance of large-scale ecological mapping models
title_full Spatial validation reveals poor predictive performance of large-scale ecological mapping models
title_fullStr Spatial validation reveals poor predictive performance of large-scale ecological mapping models
title_full_unstemmed Spatial validation reveals poor predictive performance of large-scale ecological mapping models
title_sort spatial validation reveals poor predictive performance of large-scale ecological mapping models
publisher Nature Portfolio
publishDate 2020
url https://doaj.org/article/628f13be6ee34becb88ef385ebe283e3
work_keys_str_mv AT pierreploton spatialvalidationrevealspoorpredictiveperformanceoflargescaleecologicalmappingmodels
AT fredericmortier spatialvalidationrevealspoorpredictiveperformanceoflargescaleecologicalmappingmodels
AT maximerejoumechain spatialvalidationrevealspoorpredictiveperformanceoflargescaleecologicalmappingmodels
AT nicolasbarbier spatialvalidationrevealspoorpredictiveperformanceoflargescaleecologicalmappingmodels
AT nicolaspicard spatialvalidationrevealspoorpredictiveperformanceoflargescaleecologicalmappingmodels
AT vivienrossi spatialvalidationrevealspoorpredictiveperformanceoflargescaleecologicalmappingmodels
AT carstendormann spatialvalidationrevealspoorpredictiveperformanceoflargescaleecologicalmappingmodels
AT guillaumecornu spatialvalidationrevealspoorpredictiveperformanceoflargescaleecologicalmappingmodels
AT gaelleviennois spatialvalidationrevealspoorpredictiveperformanceoflargescaleecologicalmappingmodels
AT nicolasbayol spatialvalidationrevealspoorpredictiveperformanceoflargescaleecologicalmappingmodels
AT alexeilyapustin spatialvalidationrevealspoorpredictiveperformanceoflargescaleecologicalmappingmodels
AT sylviegourletfleury spatialvalidationrevealspoorpredictiveperformanceoflargescaleecologicalmappingmodels
AT raphaelpelissier spatialvalidationrevealspoorpredictiveperformanceoflargescaleecologicalmappingmodels
_version_ 1718381028510269440