A spatially explicit method for evaluating accuracy of species distribution models
Abstract Aim Models predicting the spatial distribution of animals are increasingly used in wildlife management and conservation planning. There is growing recognition that common methods of evaluating species distribution model (SDM) accuracy, as a global overall value of predictive ability, could...
Published in: | Diversity and Distributions |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Wiley
2010
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1111/j.1472-4642.2010.00707.x https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1111%2Fj.1472-4642.2010.00707.x https://onlinelibrary.wiley.com/doi/pdf/10.1111/j.1472-4642.2010.00707.x |
id |
crwiley:10.1111/j.1472-4642.2010.00707.x |
---|---|
record_format |
openpolar |
spelling |
crwiley:10.1111/j.1472-4642.2010.00707.x 2024-06-23T07:57:22+00:00 A spatially explicit method for evaluating accuracy of species distribution models Smulders, Mary Nelson, Trisalyn A. Jelinski, Dennis E. Nielsen, Scott E. Stenhouse, Gordon B. 2010 http://dx.doi.org/10.1111/j.1472-4642.2010.00707.x https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1111%2Fj.1472-4642.2010.00707.x https://onlinelibrary.wiley.com/doi/pdf/10.1111/j.1472-4642.2010.00707.x en eng Wiley http://onlinelibrary.wiley.com/termsAndConditions#vor Diversity and Distributions volume 16, issue 6, page 996-1008 ISSN 1366-9516 1472-4642 journal-article 2010 crwiley https://doi.org/10.1111/j.1472-4642.2010.00707.x 2024-06-13T04:23:20Z Abstract Aim Models predicting the spatial distribution of animals are increasingly used in wildlife management and conservation planning. There is growing recognition that common methods of evaluating species distribution model (SDM) accuracy, as a global overall value of predictive ability, could be enhanced by spatially evaluating the model thereby identifying local areas of relative predictive strength and weakness. Current methods of spatial SDM model assessment focus on applying local measures of spatial autocorrelation to SDM residuals, which require quantitative model outputs. However, SDM outputs are often probabilistic (relative probability of species occurrence) or categorical (species present or absent). The goal of this paper was to develop a new method, using a conditional randomization technique, which can be applied to directly spatially evaluate probabilistic and categorical SDMs. Location Eastern slopes, Rocky Mountains, Alberta, Canada. Methods We used predictions from seasonal grizzly bear ( Ursus arctos ) resource selection functions (RSF) models to demonstrate our spatial evaluation technique. Local test statistics computed from bear telemetry locations were used to identify areas where bears were located more frequently than predicted. We evaluated the spatial pattern of model inaccuracies using a measure of spatial autocorrelation, local Moran’s I . Results We found the model to have non‐stationary patterns in accuracy, with clusters of inaccuracies located in central habitat areas. Model inaccuracies varied seasonally, with the summer model performing the best and the least error in areas with high RSF values. The landscape characteristics associated with model inaccuracies were examined, and possible factors contributing to RSF error were identified. Main conclusions The presented method complements existing spatial approaches to model error assessment as it can be used with probabilistic and categorical model output, which is typical for SDMs. We recommend that SDM accuracy assessments ... Article in Journal/Newspaper Ursus arctos Wiley Online Library Canada Diversity and Distributions 16 6 996 1008 |
institution |
Open Polar |
collection |
Wiley Online Library |
op_collection_id |
crwiley |
language |
English |
description |
Abstract Aim Models predicting the spatial distribution of animals are increasingly used in wildlife management and conservation planning. There is growing recognition that common methods of evaluating species distribution model (SDM) accuracy, as a global overall value of predictive ability, could be enhanced by spatially evaluating the model thereby identifying local areas of relative predictive strength and weakness. Current methods of spatial SDM model assessment focus on applying local measures of spatial autocorrelation to SDM residuals, which require quantitative model outputs. However, SDM outputs are often probabilistic (relative probability of species occurrence) or categorical (species present or absent). The goal of this paper was to develop a new method, using a conditional randomization technique, which can be applied to directly spatially evaluate probabilistic and categorical SDMs. Location Eastern slopes, Rocky Mountains, Alberta, Canada. Methods We used predictions from seasonal grizzly bear ( Ursus arctos ) resource selection functions (RSF) models to demonstrate our spatial evaluation technique. Local test statistics computed from bear telemetry locations were used to identify areas where bears were located more frequently than predicted. We evaluated the spatial pattern of model inaccuracies using a measure of spatial autocorrelation, local Moran’s I . Results We found the model to have non‐stationary patterns in accuracy, with clusters of inaccuracies located in central habitat areas. Model inaccuracies varied seasonally, with the summer model performing the best and the least error in areas with high RSF values. The landscape characteristics associated with model inaccuracies were examined, and possible factors contributing to RSF error were identified. Main conclusions The presented method complements existing spatial approaches to model error assessment as it can be used with probabilistic and categorical model output, which is typical for SDMs. We recommend that SDM accuracy assessments ... |
format |
Article in Journal/Newspaper |
author |
Smulders, Mary Nelson, Trisalyn A. Jelinski, Dennis E. Nielsen, Scott E. Stenhouse, Gordon B. |
spellingShingle |
Smulders, Mary Nelson, Trisalyn A. Jelinski, Dennis E. Nielsen, Scott E. Stenhouse, Gordon B. A spatially explicit method for evaluating accuracy of species distribution models |
author_facet |
Smulders, Mary Nelson, Trisalyn A. Jelinski, Dennis E. Nielsen, Scott E. Stenhouse, Gordon B. |
author_sort |
Smulders, Mary |
title |
A spatially explicit method for evaluating accuracy of species distribution models |
title_short |
A spatially explicit method for evaluating accuracy of species distribution models |
title_full |
A spatially explicit method for evaluating accuracy of species distribution models |
title_fullStr |
A spatially explicit method for evaluating accuracy of species distribution models |
title_full_unstemmed |
A spatially explicit method for evaluating accuracy of species distribution models |
title_sort |
spatially explicit method for evaluating accuracy of species distribution models |
publisher |
Wiley |
publishDate |
2010 |
url |
http://dx.doi.org/10.1111/j.1472-4642.2010.00707.x https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1111%2Fj.1472-4642.2010.00707.x https://onlinelibrary.wiley.com/doi/pdf/10.1111/j.1472-4642.2010.00707.x |
geographic |
Canada |
geographic_facet |
Canada |
genre |
Ursus arctos |
genre_facet |
Ursus arctos |
op_source |
Diversity and Distributions volume 16, issue 6, page 996-1008 ISSN 1366-9516 1472-4642 |
op_rights |
http://onlinelibrary.wiley.com/termsAndConditions#vor |
op_doi |
https://doi.org/10.1111/j.1472-4642.2010.00707.x |
container_title |
Diversity and Distributions |
container_volume |
16 |
container_issue |
6 |
container_start_page |
996 |
op_container_end_page |
1008 |
_version_ |
1802650976525484032 |