Used-habitat calibration plots: a new procedure for validating species distribution, resource selection, and step-selection models

John R. Fieberg, James D. Forester, Garrett M. Street, Douglas H. Johnson, Althea A. ArchMiller, Jason Matthiopoulos

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

‘Species distribution modeling’ was recently ranked as one of the top five ‘research fronts’ in ecology and the environmental sciences by ISI's Essential Science Indicators, reflecting the importance of predicting how species distributions will respond to anthropogenic change. Unfortunately, species distribution models (SDMs) often perform poorly when applied to novel environments. Compounding on this problem is the shortage of methods for evaluating SDMs (hence, we may be getting our predictions wrong and not even know it). Traditional methods for validating SDMs quantify a model's ability to classify locations as used or unused. Instead, we propose to focus on how well SDMs can predict the characteristics of used locations. This subtle shift in viewpoint leads to a more natural and informative evaluation and validation of models across the entire spectrum of SDMs. Through a series of examples, we show how simple graphical methods can help with three fundamental challenges of habitat modeling: identifying missing covariates, non-linearity, and multicollinearity. Identifying habitat characteristics that are not well-predicted by the model can provide insights into variables affecting the distribution of species, suggest appropriate model modifications, and ultimately improve the reliability and generality of conservation and management recommendations.

Original languageEnglish (US)
Pages (from-to)737-752
Number of pages16
JournalEcography
Volume41
Issue number5
DOIs
StatePublished - May 2018

Fingerprint

resource selection
calibration
biogeography
habitat
habitats
distribution
graphical method
environmental science
model validation
nonlinearity
modeling
ecology
methodology

Cite this

Used-habitat calibration plots : a new procedure for validating species distribution, resource selection, and step-selection models. / Fieberg, John R.; Forester, James D.; Street, Garrett M.; Johnson, Douglas H.; ArchMiller, Althea A.; Matthiopoulos, Jason.

In: Ecography, Vol. 41, No. 5, 05.2018, p. 737-752.

Research output: Contribution to journalArticle

Fieberg, John R. ; Forester, James D. ; Street, Garrett M. ; Johnson, Douglas H. ; ArchMiller, Althea A. ; Matthiopoulos, Jason. / Used-habitat calibration plots : a new procedure for validating species distribution, resource selection, and step-selection models. In: Ecography. 2018 ; Vol. 41, No. 5. pp. 737-752.
@article{85702b8b9b094dd88374a08024f1316b,
title = "Used-habitat calibration plots: a new procedure for validating species distribution, resource selection, and step-selection models",
abstract = "‘Species distribution modeling’ was recently ranked as one of the top five ‘research fronts’ in ecology and the environmental sciences by ISI's Essential Science Indicators, reflecting the importance of predicting how species distributions will respond to anthropogenic change. Unfortunately, species distribution models (SDMs) often perform poorly when applied to novel environments. Compounding on this problem is the shortage of methods for evaluating SDMs (hence, we may be getting our predictions wrong and not even know it). Traditional methods for validating SDMs quantify a model's ability to classify locations as used or unused. Instead, we propose to focus on how well SDMs can predict the characteristics of used locations. This subtle shift in viewpoint leads to a more natural and informative evaluation and validation of models across the entire spectrum of SDMs. Through a series of examples, we show how simple graphical methods can help with three fundamental challenges of habitat modeling: identifying missing covariates, non-linearity, and multicollinearity. Identifying habitat characteristics that are not well-predicted by the model can provide insights into variables affecting the distribution of species, suggest appropriate model modifications, and ultimately improve the reliability and generality of conservation and management recommendations.",
author = "Fieberg, {John R.} and Forester, {James D.} and Street, {Garrett M.} and Johnson, {Douglas H.} and ArchMiller, {Althea A.} and Jason Matthiopoulos",
year = "2018",
month = "5",
doi = "10.1111/ecog.03123",
language = "English (US)",
volume = "41",
pages = "737--752",
journal = "Ecography",
issn = "0906-7590",
publisher = "Wiley-Blackwell",
number = "5",

}

TY - JOUR

T1 - Used-habitat calibration plots

T2 - a new procedure for validating species distribution, resource selection, and step-selection models

AU - Fieberg, John R.

AU - Forester, James D.

AU - Street, Garrett M.

AU - Johnson, Douglas H.

AU - ArchMiller, Althea A.

AU - Matthiopoulos, Jason

PY - 2018/5

Y1 - 2018/5

N2 - ‘Species distribution modeling’ was recently ranked as one of the top five ‘research fronts’ in ecology and the environmental sciences by ISI's Essential Science Indicators, reflecting the importance of predicting how species distributions will respond to anthropogenic change. Unfortunately, species distribution models (SDMs) often perform poorly when applied to novel environments. Compounding on this problem is the shortage of methods for evaluating SDMs (hence, we may be getting our predictions wrong and not even know it). Traditional methods for validating SDMs quantify a model's ability to classify locations as used or unused. Instead, we propose to focus on how well SDMs can predict the characteristics of used locations. This subtle shift in viewpoint leads to a more natural and informative evaluation and validation of models across the entire spectrum of SDMs. Through a series of examples, we show how simple graphical methods can help with three fundamental challenges of habitat modeling: identifying missing covariates, non-linearity, and multicollinearity. Identifying habitat characteristics that are not well-predicted by the model can provide insights into variables affecting the distribution of species, suggest appropriate model modifications, and ultimately improve the reliability and generality of conservation and management recommendations.

AB - ‘Species distribution modeling’ was recently ranked as one of the top five ‘research fronts’ in ecology and the environmental sciences by ISI's Essential Science Indicators, reflecting the importance of predicting how species distributions will respond to anthropogenic change. Unfortunately, species distribution models (SDMs) often perform poorly when applied to novel environments. Compounding on this problem is the shortage of methods for evaluating SDMs (hence, we may be getting our predictions wrong and not even know it). Traditional methods for validating SDMs quantify a model's ability to classify locations as used or unused. Instead, we propose to focus on how well SDMs can predict the characteristics of used locations. This subtle shift in viewpoint leads to a more natural and informative evaluation and validation of models across the entire spectrum of SDMs. Through a series of examples, we show how simple graphical methods can help with three fundamental challenges of habitat modeling: identifying missing covariates, non-linearity, and multicollinearity. Identifying habitat characteristics that are not well-predicted by the model can provide insights into variables affecting the distribution of species, suggest appropriate model modifications, and ultimately improve the reliability and generality of conservation and management recommendations.

UR - http://www.scopus.com/inward/record.url?scp=85045987048&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045987048&partnerID=8YFLogxK

U2 - 10.1111/ecog.03123

DO - 10.1111/ecog.03123

M3 - Article

AN - SCOPUS:85045987048

VL - 41

SP - 737

EP - 752

JO - Ecography

JF - Ecography

SN - 0906-7590

IS - 5

ER -