Combining Regional Habitat Selection Models for Large-Scale Prediction: Circumpolar Habitat Selection of Southern Ocean Humpback Whales

Type Article
Date 2021-06
Language English
Author(s) Reisinger Ryan R.1, Friedlaender Ari S.2, Zerbini Alexandre N.3, 4, Palacios Daniel M.ORCID5, Andrews-Goff VirginiaORCID6, Dalla Rosa LucianoORCID7, Double Mike6, Findlay Ken8, 9, Garrigue Claire10, How Jason11, Jenner Curt12, Jenner Micheline-Nicole12, Mate Bruce5, Rosenbaum Howard C.13, Seakamela S. MduduziORCID14, Constantine Rochelle15
Affiliation(s) 1 : Institute of Marine Sciences, University of California Santa Cruz, 115 McAllister Way, Santa Cruz, CA 95060, USA
2 : Ecology and Evolutionary Biology, University of California Santa Cruz, 115 McAllister Way, Santa Cruz, CA 95060, USA
3 : Marine Mammal Laboratory, Alaska Fisheries Science Center, NOAA Fisheries, 7600 Sand Point Way NE, Seattle, WA 98115, USA
4 : Marine Ecology and Telemetry Research, 2468 Camp McKenzie Trail NW, Seabeck, WA 98380, USA
5 : Marine Mammal Institute, Oregon State University, 2030 SE Marine Science Dr, Newport, OR 97365, USA
6 : Australian Marine Mammal Centre, Australian Antarctic Division, 203 Channel Highway, Kingston, TAS 7050, Australia
7 : Instituto de Oceanografia, Universidade Federal do Rio Grande—FURG, Av. Itália km 8 s/n, Rio Grande RS 96203-900, Brazil
8 : Cape Peninsula University of Technology, Cape Town 8000, South Africa
9 : Department of Zoology and Entomology, Mammal Research Institute, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa
10 : UMR ENTROPIE, IRD, Université de La Réunion, Université de la Nouvelle-Calédonie, CNRS, IFREMER, Laboratoire d’excellence-CORAIL, BP A5, 98848 Nouméa, New Caledonia
11 : Department of Primary Industries and Regional Development, Perth, WA 6000, Australia
12 : Centre for Whale Research, P.O. Box 1622, Fremantle, WA 6959, Australia
13 : Wildlife Conservation Society, Ocean Giants Program, 2300 Southern Boulevard Bronx, New York, NY 10460, USA
14 : Department of Forestry, Fisheries and the Environment, Branch Oceans and Coasts, P.O. Box 52126, V&A Waterfront, Cape Town 8000, South Africa
15 : School of Biological Sciences & Institute of Marine Science, University of Auckland, Private Bag 92019, Auckland 1142, New Zealand
Source Remote Sensing (2072-4292) (MDPI AG), 2021-06 , Vol. 13 , N. 11 , P. 2074 (23p.)
DOI 10.3390/rs13112074
Note This article belongs to the Special Issue Application of Machine Learning in Marine Ecology
Keyword(s) ensembles, habitat selection, machine learning, prediction, resource selection functions, telemetry, humpback whale, Megaptera novaeangliae

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

Full Text
File Pages Size Access
Publisher's official version 23 4 MB Open access
Supplementary File 1 351 KB Open access
Top of the page

How to cite 

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, 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 (23p.). Publisher's official version : , Open Access version :