Identifying predictable foraging habitats for a wide-ranging marine predator using ensemble ecological niche models
Aim: Ecological niche modelling can provide valuable insight into species' environmental preferences and aid the identification of key habitats for populations of conservation concern. Here, we integrate biologging, satellite remote-sensing and ensemble ecological niche models (EENMs) to identi...
Published in: | Diversity and Distributions |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Wiley-Blackwell Publishing Ltd.
2016
|
Subjects: | |
Online Access: | https://doi.org/10.1111/ddi.12389 |
id |
ftunivscoast:usc:20906 |
---|---|
record_format |
openpolar |
spelling |
ftunivscoast:usc:20906 2023-05-15T15:44:45+02:00 Identifying predictable foraging habitats for a wide-ranging marine predator using ensemble ecological niche models Scales, Kylie L Miller, P I Ingram, S N Hazen, E L Bograd, S J Phillips, R A 2016 https://doi.org/10.1111/ddi.12389 eng eng Wiley-Blackwell Publishing Ltd. usc:20906 URN:ISSN: 1366-9516 Copyright © 2016 Wiley-Blackwell Publishing Ltd. This is the accepted version of the following article: Scales, Kylie L; Miller, P I; Ingram, S N; Hazen, E L; Bograd, S J; Phillips, R A (2016) Identifying predictable foraging habitats for a wide-ranging marine predator using ensemble ecological niche models, Diversity and Distributions, 22, pp.212-224 , which has been published in final form at http://dx.doi.org/10.1111/ddi.12389 FoR 05 (Environmental Sciences) FoR 06 (Biological Sciences) albatross biologging boosted regression trees front map generalized additive models habitat model random forest satellite remote sensing Journal Article 2016 ftunivscoast https://doi.org/10.1111/ddi.12389 2020-06-01T22:26:22Z Aim: Ecological niche modelling can provide valuable insight into species' environmental preferences and aid the identification of key habitats for populations of conservation concern. Here, we integrate biologging, satellite remote-sensing and ensemble ecological niche models (EENMs) to identify predictable foraging habitats for a globally important population of the grey-headed albatross (GHA) Thalassarche chrysostoma. Location: Bird Island, South Georgia; Southern Atlantic Ocean. Methods: GPS and geolocation-immersion loggers were used to track at-sea movements and activity patterns of GHA over two breeding seasons (n = 55; brood-guard). Immersion frequency (landings per 10-min interval) was used to define foraging events. EENM combining Generalized Additive Models (GAM), MaxEnt, Random Forest (RF) and Boosted Regression Trees (BRT) identified the biophysical conditions characterizing the locations of foraging events, using time-matched oceanographic predictors (Sea Surface Temperature, SST; chlorophyll a, chl-a; thermal front frequency, TFreq; depth). Model performance was assessed through iterative cross-validation and extrapolative performance through cross-validation among years. Results: Predictable foraging habitats identified by EENM spanned neritic (<500 m), shelf break and oceanic waters, coinciding with a set of persistent biophysical conditions characterized by particular thermal ranges (3-8 °C, 12-13 °C), elevated primary productivity (chl-a > 0.5 mg m-3) and frequent manifestation of mesoscale thermal fronts. Our results confirm previous indications that GHA exploit enhanced foraging opportunities associated with frontal systems and objectively identify the APFZ as a region of high foraging habitat suitability. Moreover, at the spatial and temporal scales investigated here, the performance of multi-model ensembles was superior to that of single-algorithm models, and cross-validation among years indicated reasonable extrapolative performance. Main conclusions: EENM techniques are useful for integrating the predictions of several single-algorithm models, reducing potential bias and increasing confidence in predictions. Our analysis highlights the value of EENM for use with movement data in identifying at-sea habitats of wide-ranging marine predators, with clear implications for conservation and management. © 2015 John Wiley & Sons Ltd. Article in Journal/Newspaper Bird Island University of the Sunshine Coast, Queensland, Australia: COAST Research Database Bird Island ENVELOPE(-38.060,-38.060,-54.004,-54.004) Gam ENVELOPE(-57.955,-57.955,-61.923,-61.923) Diversity and Distributions 22 2 212 224 |
institution |
Open Polar |
collection |
University of the Sunshine Coast, Queensland, Australia: COAST Research Database |
op_collection_id |
ftunivscoast |
language |
English |
topic |
FoR 05 (Environmental Sciences) FoR 06 (Biological Sciences) albatross biologging boosted regression trees front map generalized additive models habitat model random forest satellite remote sensing |
spellingShingle |
FoR 05 (Environmental Sciences) FoR 06 (Biological Sciences) albatross biologging boosted regression trees front map generalized additive models habitat model random forest satellite remote sensing Scales, Kylie L Miller, P I Ingram, S N Hazen, E L Bograd, S J Phillips, R A Identifying predictable foraging habitats for a wide-ranging marine predator using ensemble ecological niche models |
topic_facet |
FoR 05 (Environmental Sciences) FoR 06 (Biological Sciences) albatross biologging boosted regression trees front map generalized additive models habitat model random forest satellite remote sensing |
description |
Aim: Ecological niche modelling can provide valuable insight into species' environmental preferences and aid the identification of key habitats for populations of conservation concern. Here, we integrate biologging, satellite remote-sensing and ensemble ecological niche models (EENMs) to identify predictable foraging habitats for a globally important population of the grey-headed albatross (GHA) Thalassarche chrysostoma. Location: Bird Island, South Georgia; Southern Atlantic Ocean. Methods: GPS and geolocation-immersion loggers were used to track at-sea movements and activity patterns of GHA over two breeding seasons (n = 55; brood-guard). Immersion frequency (landings per 10-min interval) was used to define foraging events. EENM combining Generalized Additive Models (GAM), MaxEnt, Random Forest (RF) and Boosted Regression Trees (BRT) identified the biophysical conditions characterizing the locations of foraging events, using time-matched oceanographic predictors (Sea Surface Temperature, SST; chlorophyll a, chl-a; thermal front frequency, TFreq; depth). Model performance was assessed through iterative cross-validation and extrapolative performance through cross-validation among years. Results: Predictable foraging habitats identified by EENM spanned neritic (<500 m), shelf break and oceanic waters, coinciding with a set of persistent biophysical conditions characterized by particular thermal ranges (3-8 °C, 12-13 °C), elevated primary productivity (chl-a > 0.5 mg m-3) and frequent manifestation of mesoscale thermal fronts. Our results confirm previous indications that GHA exploit enhanced foraging opportunities associated with frontal systems and objectively identify the APFZ as a region of high foraging habitat suitability. Moreover, at the spatial and temporal scales investigated here, the performance of multi-model ensembles was superior to that of single-algorithm models, and cross-validation among years indicated reasonable extrapolative performance. Main conclusions: EENM techniques are useful for integrating the predictions of several single-algorithm models, reducing potential bias and increasing confidence in predictions. Our analysis highlights the value of EENM for use with movement data in identifying at-sea habitats of wide-ranging marine predators, with clear implications for conservation and management. © 2015 John Wiley & Sons Ltd. |
format |
Article in Journal/Newspaper |
author |
Scales, Kylie L Miller, P I Ingram, S N Hazen, E L Bograd, S J Phillips, R A |
author_facet |
Scales, Kylie L Miller, P I Ingram, S N Hazen, E L Bograd, S J Phillips, R A |
author_sort |
Scales, Kylie L |
title |
Identifying predictable foraging habitats for a wide-ranging marine predator using ensemble ecological niche models |
title_short |
Identifying predictable foraging habitats for a wide-ranging marine predator using ensemble ecological niche models |
title_full |
Identifying predictable foraging habitats for a wide-ranging marine predator using ensemble ecological niche models |
title_fullStr |
Identifying predictable foraging habitats for a wide-ranging marine predator using ensemble ecological niche models |
title_full_unstemmed |
Identifying predictable foraging habitats for a wide-ranging marine predator using ensemble ecological niche models |
title_sort |
identifying predictable foraging habitats for a wide-ranging marine predator using ensemble ecological niche models |
publisher |
Wiley-Blackwell Publishing Ltd. |
publishDate |
2016 |
url |
https://doi.org/10.1111/ddi.12389 |
long_lat |
ENVELOPE(-38.060,-38.060,-54.004,-54.004) ENVELOPE(-57.955,-57.955,-61.923,-61.923) |
geographic |
Bird Island Gam |
geographic_facet |
Bird Island Gam |
genre |
Bird Island |
genre_facet |
Bird Island |
op_relation |
usc:20906 URN:ISSN: 1366-9516 |
op_rights |
Copyright © 2016 Wiley-Blackwell Publishing Ltd. This is the accepted version of the following article: Scales, Kylie L; Miller, P I; Ingram, S N; Hazen, E L; Bograd, S J; Phillips, R A (2016) Identifying predictable foraging habitats for a wide-ranging marine predator using ensemble ecological niche models, Diversity and Distributions, 22, pp.212-224 , which has been published in final form at http://dx.doi.org/10.1111/ddi.12389 |
op_doi |
https://doi.org/10.1111/ddi.12389 |
container_title |
Diversity and Distributions |
container_volume |
22 |
container_issue |
2 |
container_start_page |
212 |
op_container_end_page |
224 |
_version_ |
1766379118426849280 |