Using an ensemble approach to predict habitat of Dusky Grouse ( Dendragapus obscurus ) in Montana, USA
Dusky Grouse ( Dendragapus obscurus ) are an under-monitored game species in Montana and elsewhere across their distribution. Without population monitoring it is difficult to establish appropriate harvest regulations or understand the impact of environmental disturbances (e.g., timber harvest, clima...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Resilience Alliance
2024-12-01
|
| Series: | Avian Conservation and Ecology |
| Subjects: | |
| Online Access: | https://www.ace-eco.org/vol19/iss2/art7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846099422196269056 |
|---|---|
| author | Elizabeth A Leipold Claire N Gower Lance McNew |
| author_facet | Elizabeth A Leipold Claire N Gower Lance McNew |
| author_sort | Elizabeth A Leipold |
| collection | DOAJ |
| description | Dusky Grouse ( Dendragapus obscurus ) are an under-monitored game species in Montana and elsewhere across their distribution. Without population monitoring it is difficult to establish appropriate harvest regulations or understand the impact of environmental disturbances (e.g., timber harvest, climate change) on populations. As a first step toward developing methods for unbiased population monitoring, we must identify appropriate sampling sites, which requires knowledge of Dusky Grouse habitat. Our goal was to explore relationships between Dusky Grouse use and habitat characteristics, and then generate a state-wide map predicting Dusky Grouse habitat in Montana using two methods: resource selection functions and random forest classifiers. The Integrated Monitoring in Bird Conservation Regions program provided a multi-year dataset of Dusky Grouse observations, which we reduced to detected (n=132) and pseudo-absent (n=5960) locations, using geospatial datasets to obtain topographic and vegetation characteristics for each location. We evaluated the predictability of the two models using receiver operating characteristics and area under the curve (ROC/AUC) with k-fold cross validation and classification accuracy of an independent dataset of incidental Dusky Grouse locations. We found both models to be highly predictive and multiple habitat characteristics were found to help predict relative probability of use such as proportion of trees with a height of 16–20m and conifer forest vegetation types. We converted both models to binary values and used an ensemble (frequency histogram) approach to combine the models into a final predictive map. Consensus between the resource selection function and random forest models was high (93%) and the ensemble map had higher predictive accuracy when classifying the independent dataset than the other two models. Our results show that our ensembled model approach was able to accurately predict potential Dusky Grouse habitat and therefore can be used to delineate areas for future population monitoring of Dusky Grouse in Montana. |
| format | Article |
| id | doaj-art-a00abc170f8d4a4ebbb0ed757f5be99c |
| institution | Kabale University |
| issn | 1712-6568 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Resilience Alliance |
| record_format | Article |
| series | Avian Conservation and Ecology |
| spelling | doaj-art-a00abc170f8d4a4ebbb0ed757f5be99c2024-12-31T13:26:21ZengResilience AllianceAvian Conservation and Ecology1712-65682024-12-01192710.5751/ACE-02697-1902072697Using an ensemble approach to predict habitat of Dusky Grouse ( Dendragapus obscurus ) in Montana, USAElizabeth A Leipold0Claire N Gower1Lance McNew2Montana State UniversityMontana Fish, Wildlife & Parks, Bozeman MTMontana State UniversityDusky Grouse ( Dendragapus obscurus ) are an under-monitored game species in Montana and elsewhere across their distribution. Without population monitoring it is difficult to establish appropriate harvest regulations or understand the impact of environmental disturbances (e.g., timber harvest, climate change) on populations. As a first step toward developing methods for unbiased population monitoring, we must identify appropriate sampling sites, which requires knowledge of Dusky Grouse habitat. Our goal was to explore relationships between Dusky Grouse use and habitat characteristics, and then generate a state-wide map predicting Dusky Grouse habitat in Montana using two methods: resource selection functions and random forest classifiers. The Integrated Monitoring in Bird Conservation Regions program provided a multi-year dataset of Dusky Grouse observations, which we reduced to detected (n=132) and pseudo-absent (n=5960) locations, using geospatial datasets to obtain topographic and vegetation characteristics for each location. We evaluated the predictability of the two models using receiver operating characteristics and area under the curve (ROC/AUC) with k-fold cross validation and classification accuracy of an independent dataset of incidental Dusky Grouse locations. We found both models to be highly predictive and multiple habitat characteristics were found to help predict relative probability of use such as proportion of trees with a height of 16–20m and conifer forest vegetation types. We converted both models to binary values and used an ensemble (frequency histogram) approach to combine the models into a final predictive map. Consensus between the resource selection function and random forest models was high (93%) and the ensemble map had higher predictive accuracy when classifying the independent dataset than the other two models. Our results show that our ensembled model approach was able to accurately predict potential Dusky Grouse habitat and therefore can be used to delineate areas for future population monitoring of Dusky Grouse in Montana.https://www.ace-eco.org/vol19/iss2/art7habitat modelrandom forestresource selection functionsspecies distribution model |
| spellingShingle | Elizabeth A Leipold Claire N Gower Lance McNew Using an ensemble approach to predict habitat of Dusky Grouse ( Dendragapus obscurus ) in Montana, USA Avian Conservation and Ecology habitat model random forest resource selection functions species distribution model |
| title | Using an ensemble approach to predict habitat of Dusky Grouse ( Dendragapus obscurus ) in Montana, USA |
| title_full | Using an ensemble approach to predict habitat of Dusky Grouse ( Dendragapus obscurus ) in Montana, USA |
| title_fullStr | Using an ensemble approach to predict habitat of Dusky Grouse ( Dendragapus obscurus ) in Montana, USA |
| title_full_unstemmed | Using an ensemble approach to predict habitat of Dusky Grouse ( Dendragapus obscurus ) in Montana, USA |
| title_short | Using an ensemble approach to predict habitat of Dusky Grouse ( Dendragapus obscurus ) in Montana, USA |
| title_sort | using an ensemble approach to predict habitat of dusky grouse dendragapus obscurus in montana usa |
| topic | habitat model random forest resource selection functions species distribution model |
| url | https://www.ace-eco.org/vol19/iss2/art7 |
| work_keys_str_mv | AT elizabethaleipold usinganensembleapproachtopredicthabitatofduskygrousedendragapusobscurusinmontanausa AT clairengower usinganensembleapproachtopredicthabitatofduskygrousedendragapusobscurusinmontanausa AT lancemcnew usinganensembleapproachtopredicthabitatofduskygrousedendragapusobscurusinmontanausa |