Evaluating the importance of wolverine habitat predictors using a machine learning method
In the conterminous United States, wolverines (Gulo gulo) occupy semi-isolated patches of subalpine habitats at naturally low densities. Determining how to model wolverine habitat, particularly across multiple scales, can contribute greatly to wolverine conservation efforts. We used the machine-lear...
Published in: | Journal of Mammalogy |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
American Society of Mammalogists
2022
|
Subjects: | |
Online Access: | https://doi.org/10.1093/jmammal/gyab088 |
id |
ftbioone:10.1093/jmammal/gyab088 |
---|---|
record_format |
openpolar |
spelling |
ftbioone:10.1093/jmammal/gyab088 2024-06-02T08:07:43+00:00 Evaluating the importance of wolverine habitat predictors using a machine learning method Kathleen A. Carroll Andrew J. Hansen Robert M. Inman Rick L. Lawrence Kathleen A. Carroll Andrew J. Hansen Robert M. Inman Rick L. Lawrence world 2022-01-06 text/HTML https://doi.org/10.1093/jmammal/gyab088 en eng American Society of Mammalogists doi:10.1093/jmammal/gyab088 All rights reserved. https://doi.org/10.1093/jmammal/gyab088 habitat predictors Text 2022 ftbioone https://doi.org/10.1093/jmammal/gyab088 2024-05-07T00:55:08Z In the conterminous United States, wolverines (Gulo gulo) occupy semi-isolated patches of subalpine habitats at naturally low densities. Determining how to model wolverine habitat, particularly across multiple scales, can contribute greatly to wolverine conservation efforts. We used the machine-learning algorithm random forest to determine how a novel analysis approach compared to the existing literature for future wolverine conservation efforts. We also determined how well a small suite of variables explained wolverine habitat use patterns at the second- and third-order selection scale by sex. We found that the importance of habitat covariates differed slightly by sex and selection scales. Snow water equivalent, distance to high-elevation talus, and latitude-adjusted elevation were the driving selective forces for wolverines across the Greater Yellowstone Ecosystem at both selection orders but performed better at the second order. Overall, our results indicate that wolverine habitat selection is, in large part, broadly explained by high-elevation structural features, and this confirms existing data. Our results suggest that for third-order analyses, additional fine-scale habitat data are necessary. Text Gulo gulo BioOne Online Journals Journal of Mammalogy 102 6 1466 1472 |
institution |
Open Polar |
collection |
BioOne Online Journals |
op_collection_id |
ftbioone |
language |
English |
topic |
habitat predictors |
spellingShingle |
habitat predictors Kathleen A. Carroll Andrew J. Hansen Robert M. Inman Rick L. Lawrence Evaluating the importance of wolverine habitat predictors using a machine learning method |
topic_facet |
habitat predictors |
description |
In the conterminous United States, wolverines (Gulo gulo) occupy semi-isolated patches of subalpine habitats at naturally low densities. Determining how to model wolverine habitat, particularly across multiple scales, can contribute greatly to wolverine conservation efforts. We used the machine-learning algorithm random forest to determine how a novel analysis approach compared to the existing literature for future wolverine conservation efforts. We also determined how well a small suite of variables explained wolverine habitat use patterns at the second- and third-order selection scale by sex. We found that the importance of habitat covariates differed slightly by sex and selection scales. Snow water equivalent, distance to high-elevation talus, and latitude-adjusted elevation were the driving selective forces for wolverines across the Greater Yellowstone Ecosystem at both selection orders but performed better at the second order. Overall, our results indicate that wolverine habitat selection is, in large part, broadly explained by high-elevation structural features, and this confirms existing data. Our results suggest that for third-order analyses, additional fine-scale habitat data are necessary. |
author2 |
Kathleen A. Carroll Andrew J. Hansen Robert M. Inman Rick L. Lawrence |
format |
Text |
author |
Kathleen A. Carroll Andrew J. Hansen Robert M. Inman Rick L. Lawrence |
author_facet |
Kathleen A. Carroll Andrew J. Hansen Robert M. Inman Rick L. Lawrence |
author_sort |
Kathleen A. Carroll |
title |
Evaluating the importance of wolverine habitat predictors using a machine learning method |
title_short |
Evaluating the importance of wolverine habitat predictors using a machine learning method |
title_full |
Evaluating the importance of wolverine habitat predictors using a machine learning method |
title_fullStr |
Evaluating the importance of wolverine habitat predictors using a machine learning method |
title_full_unstemmed |
Evaluating the importance of wolverine habitat predictors using a machine learning method |
title_sort |
evaluating the importance of wolverine habitat predictors using a machine learning method |
publisher |
American Society of Mammalogists |
publishDate |
2022 |
url |
https://doi.org/10.1093/jmammal/gyab088 |
op_coverage |
world |
genre |
Gulo gulo |
genre_facet |
Gulo gulo |
op_source |
https://doi.org/10.1093/jmammal/gyab088 |
op_relation |
doi:10.1093/jmammal/gyab088 |
op_rights |
All rights reserved. |
op_doi |
https://doi.org/10.1093/jmammal/gyab088 |
container_title |
Journal of Mammalogy |
container_volume |
102 |
container_issue |
6 |
container_start_page |
1466 |
op_container_end_page |
1472 |
_version_ |
1800752832685539328 |