skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • NSF Public Access
  • Search Results
  • Combining Regional Habitat Selection Models for Large-Scale Prediction: Circumpolar Habitat Selection of Southern Ocean Humpback Whales
Title: 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.  more » « less
Award ID(s):
2026045
PAR ID:
10320132
Author(s) / Creator(s):
; ; ; ; ; ; ; ; ; ; ; ; ; ; ;
Date Published:
Journal Name:
Remote Sensing
Volume:
13
Issue:
11
ISSN:
2072-4292
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; (, Frontiers in Ecology and Evolution)
    null (Ed.)
    Predictions from species distribution models (SDMs) are commonly used in support of environmental decision-making to explore potential impacts of climate change on biodiversity. However, because future climates are likely to differ from current climates, there has been ongoing interest in understanding the ability of SDMs to predict species responses under novel conditions (i.e., model transferability). Here, we explore the spatial and environmental limits to extrapolation in SDMs using forest inventory data from 11 model algorithms for 108 tree species across the western United States. Algorithms performed well in predicting occurrence for plots that occurred in the same geographic region in which they were fitted. However, a substantial portion of models performed worse than random when predicting for geographic regions in which algorithms were not fitted. Our results suggest that for transfers in geographic space, no specific algorithm was better than another as there were no significant differences in predictive performance across algorithms. There were significant differences in predictive performance for algorithms transferred in environmental space with GAM performing best. However, the predictive performance of GAM declined steeply with increasing extrapolation in environmental space relative to other algorithms. The results of this study suggest that SDMs may be limited in their ability to predict species ranges beyond the environmental data used for model fitting. When predicting climate-driven range shifts, extrapolation may also not reflect important biotic and abiotic drivers of species ranges, and thus further misrepresent the realized shift in range. Future studies investigating transferability of process based SDMs or relationships between geodiversity and biodiversity may hold promise. 
    more » « less
  2. ; ; ; ; ; ; ; (, Elem Sci Anth)
    The critically endangered North Atlantic right whale (Eubalaena glacialis) faces significant anthropogenic mortality. Recent climatic shifts in traditional habitats have caused abrupt changes in right whale distributions, challenging traditional conservation strategies. Tools that can help anticipate new areas where E. glacialis might forage could inform proactive management. In this study, we trained boosted regression tree algorithms with fine-resolution modeled environmental covariates to build prey copepod (Calanus) species-specific models of historical and future distributions of E. glacialis foraging habitat on the Northwest Atlantic Shelf, from the Mid-Atlantic Bight to the Labrador Shelf. We determined foraging suitability using E. glacialis foraging thresholds for Calanus spp. adjusted by a bathymetry-dependent bioenergetic correction factor based on known foraging behavior constraints. Models were then projected to 2046–2065 and 2066–2085 modeled climatologies for representative concentration pathway scenarios RCP 4.5 and RCP 8.5 with the goal of identifying potential shifts in foraging habitat. The models had generally high performance (area under the receiver operating characteristic curve > 0.9) and indicated ocean bottom conditions and bathymetry as important covariates. Historical (1990–2015) projections aligned with known areas of high foraging habitat suitability as well as potential suitable areas on the Labrador Shelf. Future projections suggested that the suitability of potential foraging habitat would decrease in parts of the Gulf of Maine and southwestern Gulf of Saint Lawrence, while potential habitat would be maintained or improved on the western Scotian Shelf, in the Bay of Fundy, on the Newfoundland and Labrador shelves, and at some locations along the continental shelf breaks. Overall, suitable habitat is projected to decline. Directing some survey efforts toward emerging potential foraging habitats can enable conservation management to anticipate the type of distribution shifts that have led to high mortality in the past. 
    more » « less
  3. ; ; ; ; ; ; ; ; (, Ecosphere)
    Abstract Species distribution models (SDMs) have become increasingly popular for making ecological inferences, as well as predictions to inform conservation and management. In predictive modeling, practitioners often use correlative SDMs that only evaluate a single spatial scale and do not account for differences in life stages. These modeling decisions may limit the performance of SDMs beyond the study region or sampling period. Given the increasing desire to develop transferable SDMs, a robust framework is necessary that can account for known challenges of model transferability. Here, we propose a comparative framework to develop transferable SDMs, which was tested using satellite telemetry data from green turtles (Chelonia mydas). This framework is characterized by a set of steps comparing among different models based on (1) model algorithm (e.g., generalized linear model vs. Gaussian process regression) and formulation (e.g., correlative model vs. hybrid model), (2) spatial scale, and (3) accounting for life stage. SDMs were fitted as resource selection functions and trained on data from the Gulf of Mexico with bathymetric depth, net primary productivity, and sea surface temperature as covariates. Independent validation datasets from Brazil and Qatar were used to assess model transferability. A correlative SDM using a hierarchical Gaussian process regression (HGPR) algorithm exhibited greater transferability than a hybrid SDM using HGPR, as well as correlative and hybrid forms of hierarchical generalized linear models. Additionally, models that evaluated habitat selection at the finest spatial scale and that did not account for life stage proved to be the most transferable in this study. The comparative framework presented here may be applied to a variety of species, ecological datasets (e.g., presence‐only, presence‐absence, mark‐recapture), and modeling frameworks (e.g., resource selection functions, step selection functions, occupancy models) to generate transferable predictions of species–habitat associations. We expect that SDM predictions resulting from this comparative framework will be more informative management tools and may be used to more accurately assess climate change impacts on a wide array of taxa. 
    more » « less
  4. ; ; ; ; ; ; ; ; ; (, Animal Biotelemetry)
    Abstract BackgroundDespite exhibiting one of the longest migrations in the world, half of the humpback whale migratory cycle has remained unexamined. Until now, no study has provided a continuous description of humpback whale migratory behavior from a feeding ground to a calving ground. We present new information on satellite-derived offshore migratory movements of 16 Breeding Stock G humpback whales from Antarctic feeding grounds to South American calving grounds. Satellite locations were used to demonstrate migratory corridors, while the impact of departure date on migration speed was assessed using a linear regression. A Bayesian hierarchical state–space animal movement model (HSSM) was utilized to investigate the presence of Area Restricted Search (ARS) en route. Results35,642 Argos locations from 16 tagged whales from 2012 to 2017 were collected. The 16 whales were tracked for a mean of 38.5 days of migration (range 10–151 days). The length of individually derived tracks ranged from 645 to 6381 km. Humpbacks were widely dispersed geographically during the initial and middle stages of their migration, but convened in two convergence regions near the southernmost point of Chile as well as Peru’s Illescas Peninsula. The state–space model showed almost no instances of ARS along the migratory route. The linear regression assessing whether departure date affected migration speed showed suggestive but inconclusive support for a positive trend between the two variables. Results suggestive of stratification by sex and reproductive status were found for departure date and route choice. ConclusionsThis multi-year study sets a baseline against which the effects of climate change on humpback whales can be studied across years and conditions and provides an excellent starting point for the investigation into humpback whale migration. 
    more » « less
  5. ; ; ; ; ; ; ; (, Marine Ecology Progress Series)
    Understanding how closely related, sympatric species distribute themselves relative to their environment is critical to understanding ecosystem structure and function and predicting effects of environmental variation. The Antarctic Peninsula supports high densities of krill and krill consumers; however, the region is warming rapidly, with unknown consequences. Humpback whales Megaptera novaeangliae and Antarctic minke whales Balaenoptera bonaerensis are the largest krill consumers here, yet key data gaps remain about their distribution, behavior, and interactions and how these will be impacted by changing conditions. Using satellite telemetry and novel spatial point-process modeling techniques, we quantified habitat use of each species relative to dynamic environmental variables and determined overlap in core habitat areas during summer months when sea ice is at a minimum. We found that humpback whales ranged broadly over continental shelf waters, utilizing nearshore bays, while minke whales restricted their movements to sheltered bays and areas where ice is present. This presents a scenario where minke whale core habitat overlaps substantially with the broader home ranges of humpback whales. While there is no indication that prey is limiting in this ecosystem, increased overlap between these species may arise as climate-driven changes that affect the extent, timing, and duration of seasonal sea ice decrease the amount of preferred foraging habitat for minke whales while concurrently increasing it for humpback whales. Our results provide the first quantitative assessment of behaviorally based habitat use and sympatry between these 2 krill consumers and offers insight into the potential effects of a rapidly changing environment on the structure and function of a polar ecosystem. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email