Cargando…

Integrating machine learning with otolith isoscapes: Reconstructing connectivity of a marine fish over four decades

Stable isotopes are an important tool to uncover animal migration. Geographic natal assignments often require categorizing the spatial domain through a nominal approach, which can introduce bias given the continuous nature of these tracers. Stable isotopes predicted over a spatial gradient (i.e., is...

Descripción completa

Detalles Bibliográficos
Autores principales: Arai, Kohma, Castonguay, Martin, Lyubchich, Vyacheslav, Secor, David H.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10231828/
https://www.ncbi.nlm.nih.gov/pubmed/37256866
http://dx.doi.org/10.1371/journal.pone.0285702
_version_ 1785051822997635072
author Arai, Kohma
Castonguay, Martin
Lyubchich, Vyacheslav
Secor, David H.
author_facet Arai, Kohma
Castonguay, Martin
Lyubchich, Vyacheslav
Secor, David H.
author_sort Arai, Kohma
collection PubMed
description Stable isotopes are an important tool to uncover animal migration. Geographic natal assignments often require categorizing the spatial domain through a nominal approach, which can introduce bias given the continuous nature of these tracers. Stable isotopes predicted over a spatial gradient (i.e., isoscapes) allow a probabilistic and continuous assignment of origin across space, although applications to marine organisms remain limited. We present a new framework that integrates nominal and continuous assignment approaches by (1) developing a machine-learning multi-model ensemble classifier using Bayesian model averaging (nominal); and (2) integrating nominal predictions with continuous isoscapes to estimate the probability of origin across the spatial domain (continuous). We applied this integrated framework to predict the geographic origin of the Northwest Atlantic mackerel (Scomber scombrus), a migratory pelagic fish comprised of northern and southern components that have distinct spawning sites off Canada (northern contingent) and the US (southern contingent), and seasonally overlap in the US fished regions. The nominal approach based on otolith carbon and oxygen stable isotopes (δ(13)C/δ(18)O) yielded high contingent classification accuracy (84.9%). Contingent assignment of unknown-origin samples revealed prevalent, yet highly varied contingent mixing levels (12.5–83.7%) within the US waters over four decades (1975–2019). Nominal predictions were integrated into mackerel-specific otolith oxygen isoscapes developed independently for Canadian and US waters. The combined approach identified geographic nursery hotspots in known spawning sites, but also detected geographic shifts over multi-decadal time scales. This framework can be applied to other marine species to understand migration and connectivity at a high spatial resolution, relevant to management of unit stocks in fisheries and other conservation assessments.
format Online
Article
Text
id pubmed-10231828
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-102318282023-06-01 Integrating machine learning with otolith isoscapes: Reconstructing connectivity of a marine fish over four decades Arai, Kohma Castonguay, Martin Lyubchich, Vyacheslav Secor, David H. PLoS One Research Article Stable isotopes are an important tool to uncover animal migration. Geographic natal assignments often require categorizing the spatial domain through a nominal approach, which can introduce bias given the continuous nature of these tracers. Stable isotopes predicted over a spatial gradient (i.e., isoscapes) allow a probabilistic and continuous assignment of origin across space, although applications to marine organisms remain limited. We present a new framework that integrates nominal and continuous assignment approaches by (1) developing a machine-learning multi-model ensemble classifier using Bayesian model averaging (nominal); and (2) integrating nominal predictions with continuous isoscapes to estimate the probability of origin across the spatial domain (continuous). We applied this integrated framework to predict the geographic origin of the Northwest Atlantic mackerel (Scomber scombrus), a migratory pelagic fish comprised of northern and southern components that have distinct spawning sites off Canada (northern contingent) and the US (southern contingent), and seasonally overlap in the US fished regions. The nominal approach based on otolith carbon and oxygen stable isotopes (δ(13)C/δ(18)O) yielded high contingent classification accuracy (84.9%). Contingent assignment of unknown-origin samples revealed prevalent, yet highly varied contingent mixing levels (12.5–83.7%) within the US waters over four decades (1975–2019). Nominal predictions were integrated into mackerel-specific otolith oxygen isoscapes developed independently for Canadian and US waters. The combined approach identified geographic nursery hotspots in known spawning sites, but also detected geographic shifts over multi-decadal time scales. This framework can be applied to other marine species to understand migration and connectivity at a high spatial resolution, relevant to management of unit stocks in fisheries and other conservation assessments. Public Library of Science 2023-05-31 /pmc/articles/PMC10231828/ /pubmed/37256866 http://dx.doi.org/10.1371/journal.pone.0285702 Text en © 2023 Arai et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Arai, Kohma
Castonguay, Martin
Lyubchich, Vyacheslav
Secor, David H.
Integrating machine learning with otolith isoscapes: Reconstructing connectivity of a marine fish over four decades
title Integrating machine learning with otolith isoscapes: Reconstructing connectivity of a marine fish over four decades
title_full Integrating machine learning with otolith isoscapes: Reconstructing connectivity of a marine fish over four decades
title_fullStr Integrating machine learning with otolith isoscapes: Reconstructing connectivity of a marine fish over four decades
title_full_unstemmed Integrating machine learning with otolith isoscapes: Reconstructing connectivity of a marine fish over four decades
title_short Integrating machine learning with otolith isoscapes: Reconstructing connectivity of a marine fish over four decades
title_sort integrating machine learning with otolith isoscapes: reconstructing connectivity of a marine fish over four decades
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10231828/
https://www.ncbi.nlm.nih.gov/pubmed/37256866
http://dx.doi.org/10.1371/journal.pone.0285702
work_keys_str_mv AT araikohma integratingmachinelearningwithotolithisoscapesreconstructingconnectivityofamarinefishoverfourdecades
AT castonguaymartin integratingmachinelearningwithotolithisoscapesreconstructingconnectivityofamarinefishoverfourdecades
AT lyubchichvyacheslav integratingmachinelearningwithotolithisoscapesreconstructingconnectivityofamarinefishoverfourdecades
AT secordavidh integratingmachinelearningwithotolithisoscapesreconstructingconnectivityofamarinefishoverfourdecades