A comparative framework to develop transferable species distribution models for animal telemetry data
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 f...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | Ecosphere |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/ecs2.70136 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832584153131909120 |
|---|---|
| author | Joshua A. Cullen Camila Domit Margaret M. Lamont Christopher D. Marshall Armando J. B. Santos Christopher R. Sasso Mehsin Al Ansi Mariana M. P. B. Fuentes |
| author_facet | Joshua A. Cullen Camila Domit Margaret M. Lamont Christopher D. Marshall Armando J. B. Santos Christopher R. Sasso Mehsin Al Ansi Mariana M. P. B. Fuentes |
| author_sort | Joshua A. Cullen |
| collection | DOAJ |
| description | 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 (CheloniaChelonia 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. |
| format | Article |
| id | doaj-art-07426eeed9cc478396fa708ff9af6abb |
| institution | Kabale University |
| issn | 2150-8925 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | Ecosphere |
| spelling | doaj-art-07426eeed9cc478396fa708ff9af6abb2025-01-27T14:51:33ZengWileyEcosphere2150-89252024-12-011512n/an/a10.1002/ecs2.70136A comparative framework to develop transferable species distribution models for animal telemetry dataJoshua A. Cullen0Camila Domit1Margaret M. Lamont2Christopher D. Marshall3Armando J. B. Santos4Christopher R. Sasso5Mehsin Al Ansi6Mariana M. P. B. Fuentes7Department of Earth, Ocean and Atmospheric Science Florida State University Tallahassee Florida USALaboratório de Ecologia e Conservação – Centro de Estudos Do Mar Universidade Federal Do Paraná Pontal Do Paraná Paraná BrazilU.S. Geological Survey, Wetland and Aquatic Research Center Gainesville Florida USAGulf Center for Sea Turtle Research Texas A&M University College Station Texas USADepartment of Earth, Ocean and Atmospheric Science Florida State University Tallahassee Florida USANational Marine Fisheries Service NOAA Southeast Fisheries Science Center Miami Florida USADepartment of Biological and Environmental Science Qatar University Doha QatarDepartment of Earth, Ocean and Atmospheric Science Florida State University Tallahassee Florida USAAbstract 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 (CheloniaChelonia 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.https://doi.org/10.1002/ecs2.70136correlative modelGaussian processgeneralized linear modelhabitat selectionhybrid modelpredictive modeling |
| spellingShingle | Joshua A. Cullen Camila Domit Margaret M. Lamont Christopher D. Marshall Armando J. B. Santos Christopher R. Sasso Mehsin Al Ansi Mariana M. P. B. Fuentes A comparative framework to develop transferable species distribution models for animal telemetry data Ecosphere correlative model Gaussian process generalized linear model habitat selection hybrid model predictive modeling |
| title | A comparative framework to develop transferable species distribution models for animal telemetry data |
| title_full | A comparative framework to develop transferable species distribution models for animal telemetry data |
| title_fullStr | A comparative framework to develop transferable species distribution models for animal telemetry data |
| title_full_unstemmed | A comparative framework to develop transferable species distribution models for animal telemetry data |
| title_short | A comparative framework to develop transferable species distribution models for animal telemetry data |
| title_sort | comparative framework to develop transferable species distribution models for animal telemetry data |
| topic | correlative model Gaussian process generalized linear model habitat selection hybrid model predictive modeling |
| url | https://doi.org/10.1002/ecs2.70136 |
| work_keys_str_mv | AT joshuaacullen acomparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT camiladomit acomparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT margaretmlamont acomparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT christopherdmarshall acomparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT armandojbsantos acomparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT christopherrsasso acomparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT mehsinalansi acomparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT marianampbfuentes acomparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT joshuaacullen comparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT camiladomit comparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT margaretmlamont comparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT christopherdmarshall comparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT armandojbsantos comparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT christopherrsasso comparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT mehsinalansi comparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata AT marianampbfuentes comparativeframeworktodeveloptransferablespeciesdistributionmodelsforanimaltelemetrydata |