Machine learning-based prediction of FeNi nanoparticle magnetization

Autores
Williamson, Federico; Naciff, Nadhir; Catania, Carlos Adrian; Dos Santos Mendez, Gonzalo Joaquín; Amigo, Nicolás; Bringa, Eduardo Marcial
Año de publicación
2024
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
This work proposes a computationally efficient approach for estimating the magnetization of Fe0.7Ni0.3 body-centered cubic (bcc) nanoparticles (NPs) at room temperature using machine-learning algorithms, in terms of the average magnetic moment per atom, ⟨μ⟩. The magnetization data of isolated NPs were generated using atomistic spin dynamics (ASD) simulations for various nanoparticle shapes (cubes, spheres, octahedra, cones, cylinders, ellipsoids, flakes, and pyramids, with or without nanovoids) and FeNi distributions (random, core-shell, onion, sandwich, and Janus with different boundary planes). More than 1600 NPs were created and split into training and testing sets (70%–30% split), with features including the number of Ni/Fe surface and core atoms, potential energy distributions, pair correlation functions, and coordination distributions. Several machine-learning algorithms, including Random Forest (RF), Elastic Net, Support Vector Regression (SVR), and Gradient Boosting Regression (CatBoost), were applied to predict the average magnetic moment per atom of these NPs. The best-performing models, CatBoost and RF, achieved R2 scores of up to 0.86, demonstrating their accuracy in predicting NP magnetization. Feature analysis highlighted the significance of the interface between Fe and Ni clusters, Fe–Fe interactions, and the presence of Fe on the surface as critical contributors to overall magnetization. Random alloy spherical NPs without porosity exhibited the highest ⟨μ⟩ ∼ 1.6μB due to reduced Ni–Ni interactions. Applying machine-learning methods significantly reduces computational time and memory requirements compared to traditional ASD simulations. This allows for rapid prediction of NPs with desired magnetic properties, making them suitable for various technological applications.
Fil: Williamson, Federico. Universidad Nacional de Cuyo; Argentina
Fil: Naciff, Nadhir. Universidad de Mendoza. Facultad de Ingenieria; Argentina
Fil: Catania, Carlos Adrian. Universidad Nacional de Cuyo; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza; Argentina
Fil: Dos Santos Mendez, Gonzalo Joaquín. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza; Argentina. Universidad de Mendoza. Facultad de Ingenieria; Argentina
Fil: Amigo, Nicolás. Universidad Tecnologica Metropolitana (utem);
Fil: Bringa, Eduardo Marcial. Universidad de Mendoza. Facultad de Ingenieria; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza; Argentina
Materia
Magnetization
Nanoparticle
Machine learning
Atomistic spin dynamics
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/247746
Acceder
id CONICETDig_4e208e54a9b989ca2446ee1fade45e89
oai_identifier_str oai:ri.conicet.gov.ar:11336/247746
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Machine learning-based prediction of FeNi nanoparticle magnetizationWilliamson, FedericoNaciff, NadhirCatania, Carlos AdrianDos Santos Mendez, Gonzalo JoaquínAmigo, NicolásBringa, Eduardo MarcialMagnetizationNanoparticleMachine learningAtomistic spin dynamicshttps://purl.org/becyt/ford/1.3https://purl.org/becyt/ford/1This work proposes a computationally efficient approach for estimating the magnetization of Fe0.7Ni0.3 body-centered cubic (bcc) nanoparticles (NPs) at room temperature using machine-learning algorithms, in terms of the average magnetic moment per atom, ⟨μ⟩. The magnetization data of isolated NPs were generated using atomistic spin dynamics (ASD) simulations for various nanoparticle shapes (cubes, spheres, octahedra, cones, cylinders, ellipsoids, flakes, and pyramids, with or without nanovoids) and FeNi distributions (random, core-shell, onion, sandwich, and Janus with different boundary planes). More than 1600 NPs were created and split into training and testing sets (70%–30% split), with features including the number of Ni/Fe surface and core atoms, potential energy distributions, pair correlation functions, and coordination distributions. Several machine-learning algorithms, including Random Forest (RF), Elastic Net, Support Vector Regression (SVR), and Gradient Boosting Regression (CatBoost), were applied to predict the average magnetic moment per atom of these NPs. The best-performing models, CatBoost and RF, achieved R2 scores of up to 0.86, demonstrating their accuracy in predicting NP magnetization. Feature analysis highlighted the significance of the interface between Fe and Ni clusters, Fe–Fe interactions, and the presence of Fe on the surface as critical contributors to overall magnetization. Random alloy spherical NPs without porosity exhibited the highest ⟨μ⟩ ∼ 1.6μB due to reduced Ni–Ni interactions. Applying machine-learning methods significantly reduces computational time and memory requirements compared to traditional ASD simulations. This allows for rapid prediction of NPs with desired magnetic properties, making them suitable for various technological applications.Fil: Williamson, Federico. Universidad Nacional de Cuyo; ArgentinaFil: Naciff, Nadhir. Universidad de Mendoza. Facultad de Ingenieria; ArgentinaFil: Catania, Carlos Adrian. Universidad Nacional de Cuyo; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza; ArgentinaFil: Dos Santos Mendez, Gonzalo Joaquín. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza; Argentina. Universidad de Mendoza. Facultad de Ingenieria; ArgentinaFil: Amigo, Nicolás. Universidad Tecnologica Metropolitana (utem);Fil: Bringa, Eduardo Marcial. Universidad de Mendoza. Facultad de Ingenieria; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza; ArgentinaElsevier2024-11info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/247746Williamson, Federico; Naciff, Nadhir; Catania, Carlos Adrian; Dos Santos Mendez, Gonzalo Joaquín; Amigo, Nicolás; et al.; Machine learning-based prediction of FeNi nanoparticle magnetization; Elsevier; Journal of Materials Research and Technology; 33; 11-2024; 5263-52762238-7854CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://linkinghub.elsevier.com/retrieve/pii/S2238785424024128info:eu-repo/semantics/altIdentifier/doi/10.1016/j.jmrt.2024.10.142info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-nd/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-10-15T15:35:07Zoai:ri.conicet.gov.ar:11336/247746instacron: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:34982025-10-15 15:35:08.085CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Machine learning-based prediction of FeNi nanoparticle magnetization
title Machine learning-based prediction of FeNi nanoparticle magnetization
spellingShingle Machine learning-based prediction of FeNi nanoparticle magnetization
Williamson, Federico
Magnetization
Nanoparticle
Machine learning
Atomistic spin dynamics
title_short Machine learning-based prediction of FeNi nanoparticle magnetization
title_full Machine learning-based prediction of FeNi nanoparticle magnetization
title_fullStr Machine learning-based prediction of FeNi nanoparticle magnetization
title_full_unstemmed Machine learning-based prediction of FeNi nanoparticle magnetization
title_sort Machine learning-based prediction of FeNi nanoparticle magnetization
dc.creator.none.fl_str_mv Williamson, Federico
Naciff, Nadhir
Catania, Carlos Adrian
Dos Santos Mendez, Gonzalo Joaquín
Amigo, Nicolás
Bringa, Eduardo Marcial
author Williamson, Federico
author_facet Williamson, Federico
Naciff, Nadhir
Catania, Carlos Adrian
Dos Santos Mendez, Gonzalo Joaquín
Amigo, Nicolás
Bringa, Eduardo Marcial
author_role author
author2 Naciff, Nadhir
Catania, Carlos Adrian
Dos Santos Mendez, Gonzalo Joaquín
Amigo, Nicolás
Bringa, Eduardo Marcial
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv Magnetization
Nanoparticle
Machine learning
Atomistic spin dynamics
topic Magnetization
Nanoparticle
Machine learning
Atomistic spin dynamics
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.3
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv This work proposes a computationally efficient approach for estimating the magnetization of Fe0.7Ni0.3 body-centered cubic (bcc) nanoparticles (NPs) at room temperature using machine-learning algorithms, in terms of the average magnetic moment per atom, ⟨μ⟩. The magnetization data of isolated NPs were generated using atomistic spin dynamics (ASD) simulations for various nanoparticle shapes (cubes, spheres, octahedra, cones, cylinders, ellipsoids, flakes, and pyramids, with or without nanovoids) and FeNi distributions (random, core-shell, onion, sandwich, and Janus with different boundary planes). More than 1600 NPs were created and split into training and testing sets (70%–30% split), with features including the number of Ni/Fe surface and core atoms, potential energy distributions, pair correlation functions, and coordination distributions. Several machine-learning algorithms, including Random Forest (RF), Elastic Net, Support Vector Regression (SVR), and Gradient Boosting Regression (CatBoost), were applied to predict the average magnetic moment per atom of these NPs. The best-performing models, CatBoost and RF, achieved R2 scores of up to 0.86, demonstrating their accuracy in predicting NP magnetization. Feature analysis highlighted the significance of the interface between Fe and Ni clusters, Fe–Fe interactions, and the presence of Fe on the surface as critical contributors to overall magnetization. Random alloy spherical NPs without porosity exhibited the highest ⟨μ⟩ ∼ 1.6μB due to reduced Ni–Ni interactions. Applying machine-learning methods significantly reduces computational time and memory requirements compared to traditional ASD simulations. This allows for rapid prediction of NPs with desired magnetic properties, making them suitable for various technological applications.
Fil: Williamson, Federico. Universidad Nacional de Cuyo; Argentina
Fil: Naciff, Nadhir. Universidad de Mendoza. Facultad de Ingenieria; Argentina
Fil: Catania, Carlos Adrian. Universidad Nacional de Cuyo; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza; Argentina
Fil: Dos Santos Mendez, Gonzalo Joaquín. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza; Argentina. Universidad de Mendoza. Facultad de Ingenieria; Argentina
Fil: Amigo, Nicolás. Universidad Tecnologica Metropolitana (utem);
Fil: Bringa, Eduardo Marcial. Universidad de Mendoza. Facultad de Ingenieria; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza; Argentina
description This work proposes a computationally efficient approach for estimating the magnetization of Fe0.7Ni0.3 body-centered cubic (bcc) nanoparticles (NPs) at room temperature using machine-learning algorithms, in terms of the average magnetic moment per atom, ⟨μ⟩. The magnetization data of isolated NPs were generated using atomistic spin dynamics (ASD) simulations for various nanoparticle shapes (cubes, spheres, octahedra, cones, cylinders, ellipsoids, flakes, and pyramids, with or without nanovoids) and FeNi distributions (random, core-shell, onion, sandwich, and Janus with different boundary planes). More than 1600 NPs were created and split into training and testing sets (70%–30% split), with features including the number of Ni/Fe surface and core atoms, potential energy distributions, pair correlation functions, and coordination distributions. Several machine-learning algorithms, including Random Forest (RF), Elastic Net, Support Vector Regression (SVR), and Gradient Boosting Regression (CatBoost), were applied to predict the average magnetic moment per atom of these NPs. The best-performing models, CatBoost and RF, achieved R2 scores of up to 0.86, demonstrating their accuracy in predicting NP magnetization. Feature analysis highlighted the significance of the interface between Fe and Ni clusters, Fe–Fe interactions, and the presence of Fe on the surface as critical contributors to overall magnetization. Random alloy spherical NPs without porosity exhibited the highest ⟨μ⟩ ∼ 1.6μB due to reduced Ni–Ni interactions. Applying machine-learning methods significantly reduces computational time and memory requirements compared to traditional ASD simulations. This allows for rapid prediction of NPs with desired magnetic properties, making them suitable for various technological applications.
publishDate 2024
dc.date.none.fl_str_mv 2024-11
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/11336/247746
Williamson, Federico; Naciff, Nadhir; Catania, Carlos Adrian; Dos Santos Mendez, Gonzalo Joaquín; Amigo, Nicolás; et al.; Machine learning-based prediction of FeNi nanoparticle magnetization; Elsevier; Journal of Materials Research and Technology; 33; 11-2024; 5263-5276
2238-7854
CONICET Digital
CONICET
url http://hdl.handle.net/11336/247746
identifier_str_mv Williamson, Federico; Naciff, Nadhir; Catania, Carlos Adrian; Dos Santos Mendez, Gonzalo Joaquín; Amigo, Nicolás; et al.; Machine learning-based prediction of FeNi nanoparticle magnetization; Elsevier; Journal of Materials Research and Technology; 33; 11-2024; 5263-5276
2238-7854
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/S2238785424024128
info:eu-repo/semantics/altIdentifier/doi/10.1016/j.jmrt.2024.10.142
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-nd/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
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_ 1846083478362259456
score 12.891075

Publicaciones similares