Selecting environmental descriptors is critical for modelling the distribution of Antarctic benthic species.

19 pages International audience Species distribution models (SDMs) are increasingly used in ecological and biogeographic studies by Antarctic biologists, including for conservation and management purposes. During the modelling process, model calibration is a critical step to ensure model reliability...

Full description

Bibliographic Details
Published in:Polar Biology
Main Authors: Guillaumot, Charlène, Danis, Bruno, Saucède, Thomas
Other Authors: Laboratoire de Biologie Marine (LBM), Université libre de Bruxelles (ULB), Biogéosciences UMR 6282 (BGS), Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS), Work supported by a “Fonds pour la formation à la Recherche dans l’Industrie et l’Agriculture” (FRIA) and “Bourse Fondation de la mer” grants.
Format: Article in Journal/Newspaper
Language:English
Published: HAL CCSD 2020
Subjects:
Online Access:https://hal.archives-ouvertes.fr/hal-02985328
https://doi.org/10.1007/s00300-020-02714-2
id ftunivnantes:oai:HAL:hal-02985328v1
record_format openpolar
spelling ftunivnantes:oai:HAL:hal-02985328v1 2023-05-15T13:55:54+02:00 Selecting environmental descriptors is critical for modelling the distribution of Antarctic benthic species. Guillaumot, Charlène Danis, Bruno Saucède, Thomas Laboratoire de Biologie Marine (LBM) Université libre de Bruxelles (ULB) Biogéosciences UMR 6282 (BGS) Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS) Work supported by a “Fonds pour la formation à la Recherche dans l’Industrie et l’Agriculture” (FRIA) and “Bourse Fondation de la mer” grants. 2020-09 https://hal.archives-ouvertes.fr/hal-02985328 https://doi.org/10.1007/s00300-020-02714-2 en eng HAL CCSD Springer Verlag info:eu-repo/semantics/altIdentifier/doi/10.1007/s00300-020-02714-2 hal-02985328 https://hal.archives-ouvertes.fr/hal-02985328 doi:10.1007/s00300-020-02714-2 ISSN: 0722-4060 EISSN: 1432-2056 Polar Biology https://hal.archives-ouvertes.fr/hal-02985328 Polar Biology, Springer Verlag, 2020, 43 (9), pp.1363-1381. ⟨10.1007/s00300-020-02714-2⟩ https://link.springer.com/article/10.1007/s00300-020-02714-2 Species distribution models (SDMs) Boosted regression trees (BRT) Southern ocean Collinearity Asteroidea Conservation Environmental descriptors [SDE.BE]Environmental Sciences/Biodiversity and Ecology [SDV.BID]Life Sciences [q-bio]/Biodiversity info:eu-repo/semantics/article Journal articles 2020 ftunivnantes https://doi.org/10.1007/s00300-020-02714-2 2022-11-23T01:18:21Z 19 pages International audience Species distribution models (SDMs) are increasingly used in ecological and biogeographic studies by Antarctic biologists, including for conservation and management purposes. During the modelling process, model calibration is a critical step to ensure model reliability and robustness, especially in the case of SDMs, for which the number of selected environmental descriptors and their collinearity is a recurring issue. Boosted regression trees (BRT) was previously considered as one of the best modelling approach to correct for this type of bias. In the present study, we test the performance of BRT in modelling the distribution of Southern Ocean species using different numbers of environmental descriptors, either collinear or not. Models are generated for six sea star species with contrasting ecological niches and wide distribution ranges over the entire Southern Ocean. For the six studied species, overall modelling performance is not affected by the number of environmental descriptors used to generate models, BRT using the most informative descriptors and minimizing model overfitting. However, removing collinear descriptors also helps reduce model overfitting. Our results confirm that BRTs may perform well and are relevant to deal with complex and redundant environmental information for Antarctic biodiversity distribution studies. Selecting a limited number of non-collinear descriptors before modelling may generate simpler models and facilitate their interpretation. The modelled distributions do not differ noticeably between the different species despite contrasting species ecological niches. This unexpected result stresses important limitations in using SDMs for broad scale spatial studies, based on limited, spatially aggregated data, and low-resolution descriptors. Article in Journal/Newspaper Antarc* Antarctic Polar Biology Southern Ocean Université de Nantes: HAL-UNIV-NANTES Antarctic Southern Ocean Polar Biology 43 9 1363 1381
institution Open Polar
collection Université de Nantes: HAL-UNIV-NANTES
op_collection_id ftunivnantes
language English
topic Species distribution models (SDMs)
Boosted regression trees (BRT)
Southern ocean
Collinearity
Asteroidea
Conservation
Environmental descriptors
[SDE.BE]Environmental Sciences/Biodiversity and Ecology
[SDV.BID]Life Sciences [q-bio]/Biodiversity
spellingShingle Species distribution models (SDMs)
Boosted regression trees (BRT)
Southern ocean
Collinearity
Asteroidea
Conservation
Environmental descriptors
[SDE.BE]Environmental Sciences/Biodiversity and Ecology
[SDV.BID]Life Sciences [q-bio]/Biodiversity
Guillaumot, Charlène
Danis, Bruno
Saucède, Thomas
Selecting environmental descriptors is critical for modelling the distribution of Antarctic benthic species.
topic_facet Species distribution models (SDMs)
Boosted regression trees (BRT)
Southern ocean
Collinearity
Asteroidea
Conservation
Environmental descriptors
[SDE.BE]Environmental Sciences/Biodiversity and Ecology
[SDV.BID]Life Sciences [q-bio]/Biodiversity
description 19 pages International audience Species distribution models (SDMs) are increasingly used in ecological and biogeographic studies by Antarctic biologists, including for conservation and management purposes. During the modelling process, model calibration is a critical step to ensure model reliability and robustness, especially in the case of SDMs, for which the number of selected environmental descriptors and their collinearity is a recurring issue. Boosted regression trees (BRT) was previously considered as one of the best modelling approach to correct for this type of bias. In the present study, we test the performance of BRT in modelling the distribution of Southern Ocean species using different numbers of environmental descriptors, either collinear or not. Models are generated for six sea star species with contrasting ecological niches and wide distribution ranges over the entire Southern Ocean. For the six studied species, overall modelling performance is not affected by the number of environmental descriptors used to generate models, BRT using the most informative descriptors and minimizing model overfitting. However, removing collinear descriptors also helps reduce model overfitting. Our results confirm that BRTs may perform well and are relevant to deal with complex and redundant environmental information for Antarctic biodiversity distribution studies. Selecting a limited number of non-collinear descriptors before modelling may generate simpler models and facilitate their interpretation. The modelled distributions do not differ noticeably between the different species despite contrasting species ecological niches. This unexpected result stresses important limitations in using SDMs for broad scale spatial studies, based on limited, spatially aggregated data, and low-resolution descriptors.
author2 Laboratoire de Biologie Marine (LBM)
Université libre de Bruxelles (ULB)
Biogéosciences UMR 6282 (BGS)
Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS)
Work supported by a “Fonds pour la formation à la Recherche dans l’Industrie et l’Agriculture” (FRIA) and “Bourse Fondation de la mer” grants.
format Article in Journal/Newspaper
author Guillaumot, Charlène
Danis, Bruno
Saucède, Thomas
author_facet Guillaumot, Charlène
Danis, Bruno
Saucède, Thomas
author_sort Guillaumot, Charlène
title Selecting environmental descriptors is critical for modelling the distribution of Antarctic benthic species.
title_short Selecting environmental descriptors is critical for modelling the distribution of Antarctic benthic species.
title_full Selecting environmental descriptors is critical for modelling the distribution of Antarctic benthic species.
title_fullStr Selecting environmental descriptors is critical for modelling the distribution of Antarctic benthic species.
title_full_unstemmed Selecting environmental descriptors is critical for modelling the distribution of Antarctic benthic species.
title_sort selecting environmental descriptors is critical for modelling the distribution of antarctic benthic species.
publisher HAL CCSD
publishDate 2020
url https://hal.archives-ouvertes.fr/hal-02985328
https://doi.org/10.1007/s00300-020-02714-2
geographic Antarctic
Southern Ocean
geographic_facet Antarctic
Southern Ocean
genre Antarc*
Antarctic
Polar Biology
Southern Ocean
genre_facet Antarc*
Antarctic
Polar Biology
Southern Ocean
op_source ISSN: 0722-4060
EISSN: 1432-2056
Polar Biology
https://hal.archives-ouvertes.fr/hal-02985328
Polar Biology, Springer Verlag, 2020, 43 (9), pp.1363-1381. ⟨10.1007/s00300-020-02714-2⟩
https://link.springer.com/article/10.1007/s00300-020-02714-2
op_relation info:eu-repo/semantics/altIdentifier/doi/10.1007/s00300-020-02714-2
hal-02985328
https://hal.archives-ouvertes.fr/hal-02985328
doi:10.1007/s00300-020-02714-2
op_doi https://doi.org/10.1007/s00300-020-02714-2
container_title Polar Biology
container_volume 43
container_issue 9
container_start_page 1363
op_container_end_page 1381
_version_ 1766262885905858560