The University of Southampton
University of Southampton Institutional Repository

Combining regional habitat selection models for large-scale prediction: Circumpolar habitat selection of southern ocean humpback whales

Combining regional habitat selection models for large-scale prediction: Circumpolar habitat selection of southern ocean humpback whales
Combining regional habitat selection models for large-scale prediction: Circumpolar habitat selection of southern ocean humpback whales

Machine learning algorithms are often used to model and predict animal habitat selection— the relationships between animal occurrences and habitat characteristics. For broadly distributed species, habitat selection often varies among populations and regions; thus, it would seem preferable to fit region-or population-specific models of habitat selection for more accurate inference and prediction, rather than fitting large-scale models using pooled data. However, where the aim is to make range-wide predictions, including areas for which there are no existing data or models of habitat selection, how can regional models best be combined? We propose that ensemble approaches commonly used to combine different algorithms for a single region can be reframed, treating regional habitat selection models as the candidate models. By doing so, we can incorporate regional variation when fitting predictive models of animal habitat selection across large ranges. We test this approach using satellite telemetry data from 168 humpback whales across five geographic regions in the Southern Ocean. Using random forests, we fitted a large-scale model relating humpback whale locations, versus background locations, to 10 environmental covariates, and made a circumpolar prediction of humpback whale habitat selection. We also fitted five regional models, the predictions of which we used as input features for four ensemble approaches: an unweighted ensemble, an ensemble weighted by environmental similarity in each cell, stacked generalization, and a hybrid approach wherein the environmental covariates and regional predictions were used as input features in a new model. We tested the predictive performance of these approaches on an independent validation dataset of humpback whale sightings and whaling catches. These multiregional ensemble approaches resulted in models with higher predictive performance than the circumpolar naive model. These approaches can be used to incorporate regional variation in animal habitat selection when fitting range-wide predictive models using machine learning algorithms. This can yield more accurate predictions across regions or populations of animals that may show variation in habitat selection.

Ensembles, Habitat selection, Humpback whale, Machine learning, Megaptera novaeangliae, Prediction, Resource selection functions, Telemetry
2072-4292
Reisinger, Ryan R.
4eaf9440-48e5-41fa-853f-d46457e5444e
Friedlaender, Ari S.
bceec0b0-26aa-45be-91b9-a9e9c278494b
Zerbini, Alexandre N.
e4fb990c-5088-4847-887b-8f872be42ef7
Palacios, Daniel M.
a24a4c0c-42cb-4c38-9d7a-c9c789289457
Andrews-Goff, Virginia
01a46442-1df5-4636-a3b9-730dae07f597
Dalla Rosa, Luciano
17808466-dc6d-47ce-88a8-f6d0b3bc91a0
Double, Mike
1573dc76-9dcc-49d7-9fad-43712e4fb558
Findlay, Ken
48b0703a-98e8-44b2-af85-0b076aa71eae
Garrigue, Claire
fff30ed3-068b-4373-ad7b-32798bc1c848
How, Jason
854908a1-1056-47a5-b7f2-89e0f16fce2b
Jenner, Curt
57924a82-d15a-4aaf-93e7-67f6ac0688e5
Jenner, Micheline Nicole
843b1466-2994-497a-b45c-e7938ea6fa06
Mate, Bruce
fef4d599-8b69-4c3b-8ae0-673d4743bc28
Rosenbaum, Howard C.
aed13171-5a5c-4597-95cb-8f632ecbc4e7
Seakamela, S. Mduduzi
dc8218fb-bed5-4a27-b8c1-e094c55e16e5
Constantine, Rochelle
2bce1e1c-fc56-4158-ad9d-339624f3899b
Reisinger, Ryan R.
4eaf9440-48e5-41fa-853f-d46457e5444e
Friedlaender, Ari S.
bceec0b0-26aa-45be-91b9-a9e9c278494b
Zerbini, Alexandre N.
e4fb990c-5088-4847-887b-8f872be42ef7
Palacios, Daniel M.
a24a4c0c-42cb-4c38-9d7a-c9c789289457
Andrews-Goff, Virginia
01a46442-1df5-4636-a3b9-730dae07f597
Dalla Rosa, Luciano
17808466-dc6d-47ce-88a8-f6d0b3bc91a0
Double, Mike
1573dc76-9dcc-49d7-9fad-43712e4fb558
Findlay, Ken
48b0703a-98e8-44b2-af85-0b076aa71eae
Garrigue, Claire
fff30ed3-068b-4373-ad7b-32798bc1c848
How, Jason
854908a1-1056-47a5-b7f2-89e0f16fce2b
Jenner, Curt
57924a82-d15a-4aaf-93e7-67f6ac0688e5
Jenner, Micheline Nicole
843b1466-2994-497a-b45c-e7938ea6fa06
Mate, Bruce
fef4d599-8b69-4c3b-8ae0-673d4743bc28
Rosenbaum, Howard C.
aed13171-5a5c-4597-95cb-8f632ecbc4e7
Seakamela, S. Mduduzi
dc8218fb-bed5-4a27-b8c1-e094c55e16e5
Constantine, Rochelle
2bce1e1c-fc56-4158-ad9d-339624f3899b

Reisinger, Ryan R., Friedlaender, Ari S., Zerbini, Alexandre N., Palacios, Daniel M., Andrews-Goff, Virginia, Dalla Rosa, Luciano, Double, Mike, Findlay, Ken, Garrigue, Claire, How, Jason, Jenner, Curt, Jenner, Micheline Nicole, Mate, Bruce, Rosenbaum, Howard C., Seakamela, S. Mduduzi and Constantine, Rochelle (2021) Combining regional habitat selection models for large-scale prediction: Circumpolar habitat selection of southern ocean humpback whales. Remote Sensing, 13 (11), [2074]. (doi:10.3390/rs13112074).

Record type: Article

Abstract

Machine learning algorithms are often used to model and predict animal habitat selection— the relationships between animal occurrences and habitat characteristics. For broadly distributed species, habitat selection often varies among populations and regions; thus, it would seem preferable to fit region-or population-specific models of habitat selection for more accurate inference and prediction, rather than fitting large-scale models using pooled data. However, where the aim is to make range-wide predictions, including areas for which there are no existing data or models of habitat selection, how can regional models best be combined? We propose that ensemble approaches commonly used to combine different algorithms for a single region can be reframed, treating regional habitat selection models as the candidate models. By doing so, we can incorporate regional variation when fitting predictive models of animal habitat selection across large ranges. We test this approach using satellite telemetry data from 168 humpback whales across five geographic regions in the Southern Ocean. Using random forests, we fitted a large-scale model relating humpback whale locations, versus background locations, to 10 environmental covariates, and made a circumpolar prediction of humpback whale habitat selection. We also fitted five regional models, the predictions of which we used as input features for four ensemble approaches: an unweighted ensemble, an ensemble weighted by environmental similarity in each cell, stacked generalization, and a hybrid approach wherein the environmental covariates and regional predictions were used as input features in a new model. We tested the predictive performance of these approaches on an independent validation dataset of humpback whale sightings and whaling catches. These multiregional ensemble approaches resulted in models with higher predictive performance than the circumpolar naive model. These approaches can be used to incorporate regional variation in animal habitat selection when fitting range-wide predictive models using machine learning algorithms. This can yield more accurate predictions across regions or populations of animals that may show variation in habitat selection.

Text
remotesensing-13-02074 - Version of Record
Available under License Creative Commons Attribution.
Download (5MB)

More information

Accepted/In Press date: 18 May 2021
e-pub ahead of print date: 25 May 2021
Published date: 1 June 2021
Keywords: Ensembles, Habitat selection, Humpback whale, Machine learning, Megaptera novaeangliae, Prediction, Resource selection functions, Telemetry

Identifiers

Local EPrints ID: 455515
URI: http://eprints.soton.ac.uk/id/eprint/455515
ISSN: 2072-4292
PURE UUID: f0c5a2c5-bc61-4bfa-97cf-16e2105e41fd
ORCID for Ryan R. Reisinger: ORCID iD orcid.org/0000-0002-8933-6875

Catalogue record

Date deposited: 24 Mar 2022 17:32
Last modified: 06 Jun 2024 02:11

Export record

Altmetrics

Contributors

Author: Ari S. Friedlaender
Author: Alexandre N. Zerbini
Author: Daniel M. Palacios
Author: Virginia Andrews-Goff
Author: Luciano Dalla Rosa
Author: Mike Double
Author: Ken Findlay
Author: Claire Garrigue
Author: Jason How
Author: Curt Jenner
Author: Micheline Nicole Jenner
Author: Bruce Mate
Author: Howard C. Rosenbaum
Author: S. Mduduzi Seakamela
Author: Rochelle Constantine

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×