Reisinger R. R. auteur aut IRD Friedlaender A. S. auteur aut IRD Zerbini A. N. auteur aut IRD Palacios D. M. auteur aut IRD Andrews-Goff V. auteur aut IRD Dalla Rosa L. auteur aut IRD Double M. auteur aut IRD Findlay K. auteur aut IRD Garrigue Claire auteur aut IRD How J. auteur aut IRD Jenner C. auteur aut IRD Jenner M. N. auteur aut IRD Mate B. auteur aut IRD Rosenbaum H. C. auteur aut IRD Seakamela S. M. auteur aut IRD Constantine R. auteur aut IRD text journalArticle eng text/pdf reformatted digital access 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. specialized ensembles habitat selection machine learning prediction resource selection functions telemetry humpback whale Megaptera novaeangliae OCEAN AUSTRAL 034 126 13 11 2074 [23 p.] 2021 https://www.documentation.ird.fr/hor/fdi:010082166 10.3390/rs13112074 [F B010082166] https://www.documentation.ird.fr/hor/fdi:010082166 https://horizon.documentation.ird.fr/exl-doc/pleins_textes/2021-08/010082166.pdf IRD - Base Horizon / Pleins textes 2021-08-31 2021-08-31 fdi:010082166 fre