Understanding spatial effects in species distribution models

Iosu Paradinas; Janine Illian; Sophie Smout

doi:10.1371/journal.pone.0285463

Understanding spatial effects in species distribution models

Iosu Paradinas^*, Janine Illian, Sophie Smout

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

Species Distribution Models often include spatial effects which may improve prediction at unsampled locations and reduce Type I errors when identifying environmental drivers. In some cases ecologists try to ecologically interpret the spatial patterns displayed by the spatial effect. However, spatial autocorrelation may be driven by many different unaccounted drivers, which complicates the ecological interpretation of fitted spatial effects. This study aims to provide a practical demonstration that spatial effects are able to smooth the effect of multiple unaccounted drivers. To do so we use a simulation study that fit model-based spatial models using both geostatistics and 2D smoothing splines. Results show that fitted spatial effects resemble the sum of the unaccounted covariate surface(s) in each model.

Original language	English
Article number	e0285463
Number of pages	6
Journal	PLoS ONE
Volume	18
Issue number	5
DOIs	https://doi.org/10.1371/journal.pone.0285463
Publication status	Published - 30 May 2023

Access to Document

10.1371/journal.pone.0285463Licence: CC BY

Paradinas_2023_P-One_Understanding-spatial_CC
Copyright: © 2023 Paradinas et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Final published version, 479 KBLicence: CC BY

Cite this

@article{45643e2cde0342deac60b551c0832d5e,

title = "Understanding spatial effects in species distribution models",

abstract = "Species Distribution Models often include spatial effects which may improve prediction at unsampled locations and reduce Type I errors when identifying environmental drivers. In some cases ecologists try to ecologically interpret the spatial patterns displayed by the spatial effect. However, spatial autocorrelation may be driven by many different unaccounted drivers, which complicates the ecological interpretation of fitted spatial effects. This study aims to provide a practical demonstration that spatial effects are able to smooth the effect of multiple unaccounted drivers. To do so we use a simulation study that fit model-based spatial models using both geostatistics and 2D smoothing splines. Results show that fitted spatial effects resemble the sum of the unaccounted covariate surface(s) in each model.",

author = "Iosu Paradinas and Janine Illian and Sophie Smout",

note = "Funding: IP was funded by a Marie Sk{\l}odowska-Curie Research Fellowship (GAP-847014).",

year = "2023",

month = may,

day = "30",

doi = "10.1371/journal.pone.0285463",

language = "English",

volume = "18",

journal = "PLoS ONE",

issn = "1932-6203",

publisher = "Public Library of Science",

number = "5",

}

TY - JOUR

T1 - Understanding spatial effects in species distribution models

AU - Paradinas, Iosu

AU - Illian, Janine

AU - Smout, Sophie

N1 - Funding: IP was funded by a Marie Skłodowska-Curie Research Fellowship (GAP-847014).

PY - 2023/5/30

Y1 - 2023/5/30

N2 - Species Distribution Models often include spatial effects which may improve prediction at unsampled locations and reduce Type I errors when identifying environmental drivers. In some cases ecologists try to ecologically interpret the spatial patterns displayed by the spatial effect. However, spatial autocorrelation may be driven by many different unaccounted drivers, which complicates the ecological interpretation of fitted spatial effects. This study aims to provide a practical demonstration that spatial effects are able to smooth the effect of multiple unaccounted drivers. To do so we use a simulation study that fit model-based spatial models using both geostatistics and 2D smoothing splines. Results show that fitted spatial effects resemble the sum of the unaccounted covariate surface(s) in each model.

AB - Species Distribution Models often include spatial effects which may improve prediction at unsampled locations and reduce Type I errors when identifying environmental drivers. In some cases ecologists try to ecologically interpret the spatial patterns displayed by the spatial effect. However, spatial autocorrelation may be driven by many different unaccounted drivers, which complicates the ecological interpretation of fitted spatial effects. This study aims to provide a practical demonstration that spatial effects are able to smooth the effect of multiple unaccounted drivers. To do so we use a simulation study that fit model-based spatial models using both geostatistics and 2D smoothing splines. Results show that fitted spatial effects resemble the sum of the unaccounted covariate surface(s) in each model.

U2 - 10.1371/journal.pone.0285463

DO - 10.1371/journal.pone.0285463

M3 - Article

C2 - 37253039

SN - 1932-6203

VL - 18

JO - PLoS ONE

JF - PLoS ONE

IS - 5

M1 - e0285463

ER -

Understanding spatial effects in species distribution models

Abstract

Access to Document

Fingerprint

Cite this