Unraveling remagnetization sources using statistical learning

Autores
Gallo, L.C.; Domeier, M.; Antonio, P.Y.; Sapienza, F.; Rapalini, Augusto Ernesto; Font, E.; Adatte, T.; Trindade, R.I.F.; Temporim, F.; Tonti Filippini, J.; Silkoset, P.; Warren, L.
Año de publicación
2025
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
The paleomagnetic archive provides invaluable insights into Earth’s history, but its records are often obscuredby various geological processes. A prime example is remagnetization, which can replace the original naturalremanent magnetization. Although magnetic overprints can be detected by traditional paleomagnetic tests,the mechanisms responsible for them often remain elusive because linking bulk magnetic properties to theirmicroscopic sources is inherently challenging. Here, we bridge this gap by pairing an extensive rock magneticand geochemical dataset with statistical learning techniques for the first time. Using a Random Forest regressortrained on geochemical data, we accurately predict the growth of fine-grained magnetite in an undeformed lateEdiacaran section of remagnetized carbonate rocks from Paraguay. Our modeling results identify the K/Al ratio alongside K and Sr contents—as key predictors of this remagnetization mechanism. Notably, clay mineralogyanalyses further link the K/Al ratio to enhanced clay authigenesis (illitization) driven by K-feldspar dissolutionand albitization—processes that also release iron. Together, these findings indicate that remagnetization occurredvia authigenic magnetite formation under isochemical diagenesis—without the involvement of external fluids.This novel application of statistical learning to uncover the geochemical drivers of chemical remagnetizationsprovides a robust framework to investigate and understand these events. It could also open new avenues for theirdirect dating, thereby significantly enriching the global paleomagnetic record.
Fil: Gallo, L.C.. University Of Oslo. Faculty Of Mathematics And Natural Science; Noruega
Fil: Domeier, M.. University Of Oslo. Faculty Of Mathematics And Natural Science; Noruega
Fil: Antonio, P.Y.. Université Montpellier II; Francia
Fil: Sapienza, F.. University of California at Berkeley; Estados Unidos
Fil: Rapalini, Augusto Ernesto. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Geociencias Básicas, Aplicadas y Ambientales de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Geociencias Básicas, Aplicadas y Ambientales de Buenos Aires; Argentina
Fil: Font, E.. Universidad de Coimbra. Facultad de Ciencias E Tecnología; Portugal
Fil: Adatte, T.. University Of Lausanne; Suiza
Fil: Trindade, R.I.F.. Universidade do Sao Paulo. Instituto de Astronomia, Geofísica e Ciências Atmosféricas; Brasil
Fil: Temporim, F.. Universidade do Sao Paulo. Instituto de Astronomia, Geofísica e Ciências Atmosféricas; Brasil
Fil: Tonti Filippini, J.. University Of Oslo. Faculty Of Mathematics And Natural Science; Noruega
Fil: Silkoset, P.. University Of Oslo. Faculty Of Mathematics And Natural Science; Noruega
Fil: Warren, L.. Instituto de Geociencias Rio Claro; Brasil
Materia
Paleomagnetism
Machine Learning
Remagnetization
Ediacaran
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/281710
Acceder
id CONICETDig_af008d868c14bb0c9323c7584f5d2054
oai_identifier_str oai:ri.conicet.gov.ar:11336/281710
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Unraveling remagnetization sources using statistical learningGallo, L.C.Domeier, M.Antonio, P.Y.Sapienza, F.Rapalini, Augusto ErnestoFont, E.Adatte, T.Trindade, R.I.F.Temporim, F.Tonti Filippini, J.Silkoset, P.Warren, L.PaleomagnetismMachine LearningRemagnetizationEdiacaranhttps://purl.org/becyt/ford/1.5https://purl.org/becyt/ford/1The paleomagnetic archive provides invaluable insights into Earth’s history, but its records are often obscuredby various geological processes. A prime example is remagnetization, which can replace the original naturalremanent magnetization. Although magnetic overprints can be detected by traditional paleomagnetic tests,the mechanisms responsible for them often remain elusive because linking bulk magnetic properties to theirmicroscopic sources is inherently challenging. Here, we bridge this gap by pairing an extensive rock magneticand geochemical dataset with statistical learning techniques for the first time. Using a Random Forest regressortrained on geochemical data, we accurately predict the growth of fine-grained magnetite in an undeformed lateEdiacaran section of remagnetized carbonate rocks from Paraguay. Our modeling results identify the K/Al ratio alongside K and Sr contents—as key predictors of this remagnetization mechanism. Notably, clay mineralogyanalyses further link the K/Al ratio to enhanced clay authigenesis (illitization) driven by K-feldspar dissolutionand albitization—processes that also release iron. Together, these findings indicate that remagnetization occurredvia authigenic magnetite formation under isochemical diagenesis—without the involvement of external fluids.This novel application of statistical learning to uncover the geochemical drivers of chemical remagnetizationsprovides a robust framework to investigate and understand these events. It could also open new avenues for theirdirect dating, thereby significantly enriching the global paleomagnetic record.Fil: Gallo, L.C.. University Of Oslo. Faculty Of Mathematics And Natural Science; NoruegaFil: Domeier, M.. University Of Oslo. Faculty Of Mathematics And Natural Science; NoruegaFil: Antonio, P.Y.. Université Montpellier II; FranciaFil: Sapienza, F.. University of California at Berkeley; Estados UnidosFil: Rapalini, Augusto Ernesto. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Geociencias Básicas, Aplicadas y Ambientales de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Geociencias Básicas, Aplicadas y Ambientales de Buenos Aires; ArgentinaFil: Font, E.. Universidad de Coimbra. Facultad de Ciencias E Tecnología; PortugalFil: Adatte, T.. University Of Lausanne; SuizaFil: Trindade, R.I.F.. Universidade do Sao Paulo. Instituto de Astronomia, Geofísica e Ciências Atmosféricas; BrasilFil: Temporim, F.. Universidade do Sao Paulo. Instituto de Astronomia, Geofísica e Ciências Atmosféricas; BrasilFil: Tonti Filippini, J.. University Of Oslo. Faculty Of Mathematics And Natural Science; NoruegaFil: Silkoset, P.. University Of Oslo. Faculty Of Mathematics And Natural Science; NoruegaFil: Warren, L.. Instituto de Geociencias Rio Claro; BrasilElsevier Science2025-07info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/281710Gallo, L.C.; Domeier, M.; Antonio, P.Y.; Sapienza, F.; Rapalini, Augusto Ernesto; et al.; Unraveling remagnetization sources using statistical learning; Elsevier Science; Earth and Planetary Science Letters; 662; 7-2025; 1-130012-821XCONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://linkinghub.elsevier.com/retrieve/pii/S0012821X2500189Xinfo:eu-repo/semantics/altIdentifier/doi/10.1016/j.epsl.2025.119390info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2026-04-23T14:40:24Zoai:ri.conicet.gov.ar:11336/281710instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982026-04-23 14:40:24.484CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Unraveling remagnetization sources using statistical learning
title Unraveling remagnetization sources using statistical learning
spellingShingle Unraveling remagnetization sources using statistical learning
Gallo, L.C.
Paleomagnetism
Machine Learning
Remagnetization
Ediacaran
title_short Unraveling remagnetization sources using statistical learning
title_full Unraveling remagnetization sources using statistical learning
title_fullStr Unraveling remagnetization sources using statistical learning
title_full_unstemmed Unraveling remagnetization sources using statistical learning
title_sort Unraveling remagnetization sources using statistical learning
dc.creator.none.fl_str_mv Gallo, L.C.
Domeier, M.
Antonio, P.Y.
Sapienza, F.
Rapalini, Augusto Ernesto
Font, E.
Adatte, T.
Trindade, R.I.F.
Temporim, F.
Tonti Filippini, J.
Silkoset, P.
Warren, L.
author Gallo, L.C.
author_facet Gallo, L.C.
Domeier, M.
Antonio, P.Y.
Sapienza, F.
Rapalini, Augusto Ernesto
Font, E.
Adatte, T.
Trindade, R.I.F.
Temporim, F.
Tonti Filippini, J.
Silkoset, P.
Warren, L.
author_role author
author2 Domeier, M.
Antonio, P.Y.
Sapienza, F.
Rapalini, Augusto Ernesto
Font, E.
Adatte, T.
Trindade, R.I.F.
Temporim, F.
Tonti Filippini, J.
Silkoset, P.
Warren, L.
author2_role author
author
author
author
author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Paleomagnetism
Machine Learning
Remagnetization
Ediacaran
topic Paleomagnetism
Machine Learning
Remagnetization
Ediacaran
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.5
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv The paleomagnetic archive provides invaluable insights into Earth’s history, but its records are often obscuredby various geological processes. A prime example is remagnetization, which can replace the original naturalremanent magnetization. Although magnetic overprints can be detected by traditional paleomagnetic tests,the mechanisms responsible for them often remain elusive because linking bulk magnetic properties to theirmicroscopic sources is inherently challenging. Here, we bridge this gap by pairing an extensive rock magneticand geochemical dataset with statistical learning techniques for the first time. Using a Random Forest regressortrained on geochemical data, we accurately predict the growth of fine-grained magnetite in an undeformed lateEdiacaran section of remagnetized carbonate rocks from Paraguay. Our modeling results identify the K/Al ratio alongside K and Sr contents—as key predictors of this remagnetization mechanism. Notably, clay mineralogyanalyses further link the K/Al ratio to enhanced clay authigenesis (illitization) driven by K-feldspar dissolutionand albitization—processes that also release iron. Together, these findings indicate that remagnetization occurredvia authigenic magnetite formation under isochemical diagenesis—without the involvement of external fluids.This novel application of statistical learning to uncover the geochemical drivers of chemical remagnetizationsprovides a robust framework to investigate and understand these events. It could also open new avenues for theirdirect dating, thereby significantly enriching the global paleomagnetic record.
Fil: Gallo, L.C.. University Of Oslo. Faculty Of Mathematics And Natural Science; Noruega
Fil: Domeier, M.. University Of Oslo. Faculty Of Mathematics And Natural Science; Noruega
Fil: Antonio, P.Y.. Université Montpellier II; Francia
Fil: Sapienza, F.. University of California at Berkeley; Estados Unidos
Fil: Rapalini, Augusto Ernesto. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Geociencias Básicas, Aplicadas y Ambientales de Buenos Aires. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Geociencias Básicas, Aplicadas y Ambientales de Buenos Aires; Argentina
Fil: Font, E.. Universidad de Coimbra. Facultad de Ciencias E Tecnología; Portugal
Fil: Adatte, T.. University Of Lausanne; Suiza
Fil: Trindade, R.I.F.. Universidade do Sao Paulo. Instituto de Astronomia, Geofísica e Ciências Atmosféricas; Brasil
Fil: Temporim, F.. Universidade do Sao Paulo. Instituto de Astronomia, Geofísica e Ciências Atmosféricas; Brasil
Fil: Tonti Filippini, J.. University Of Oslo. Faculty Of Mathematics And Natural Science; Noruega
Fil: Silkoset, P.. University Of Oslo. Faculty Of Mathematics And Natural Science; Noruega
Fil: Warren, L.. Instituto de Geociencias Rio Claro; Brasil
description The paleomagnetic archive provides invaluable insights into Earth’s history, but its records are often obscuredby various geological processes. A prime example is remagnetization, which can replace the original naturalremanent magnetization. Although magnetic overprints can be detected by traditional paleomagnetic tests,the mechanisms responsible for them often remain elusive because linking bulk magnetic properties to theirmicroscopic sources is inherently challenging. Here, we bridge this gap by pairing an extensive rock magneticand geochemical dataset with statistical learning techniques for the first time. Using a Random Forest regressortrained on geochemical data, we accurately predict the growth of fine-grained magnetite in an undeformed lateEdiacaran section of remagnetized carbonate rocks from Paraguay. Our modeling results identify the K/Al ratio alongside K and Sr contents—as key predictors of this remagnetization mechanism. Notably, clay mineralogyanalyses further link the K/Al ratio to enhanced clay authigenesis (illitization) driven by K-feldspar dissolutionand albitization—processes that also release iron. Together, these findings indicate that remagnetization occurredvia authigenic magnetite formation under isochemical diagenesis—without the involvement of external fluids.This novel application of statistical learning to uncover the geochemical drivers of chemical remagnetizationsprovides a robust framework to investigate and understand these events. It could also open new avenues for theirdirect dating, thereby significantly enriching the global paleomagnetic record.
publishDate 2025
dc.date.none.fl_str_mv 2025-07
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/281710
Gallo, L.C.; Domeier, M.; Antonio, P.Y.; Sapienza, F.; Rapalini, Augusto Ernesto; et al.; Unraveling remagnetization sources using statistical learning; Elsevier Science; Earth and Planetary Science Letters; 662; 7-2025; 1-13
0012-821X
CONICET Digital
CONICET
url http://hdl.handle.net/11336/281710
identifier_str_mv Gallo, L.C.; Domeier, M.; Antonio, P.Y.; Sapienza, F.; Rapalini, Augusto Ernesto; et al.; Unraveling remagnetization sources using statistical learning; Elsevier Science; Earth and Planetary Science Letters; 662; 7-2025; 1-13
0012-821X
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://linkinghub.elsevier.com/retrieve/pii/S0012821X2500189X
info:eu-repo/semantics/altIdentifier/doi/10.1016/j.epsl.2025.119390
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier Science
publisher.none.fl_str_mv Elsevier Science
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1863365524387266560
score 13.05261

Publicaciones similares