Predicting thermoelectric properties from chemical formula with explicitly identifying dopant effects

Abstract Dopants play an important role in synthesizing materials to improve target materials properties or stabilize the materials. In particular, the dopants are essential to improve thermoelectic performances of the materials. However, existing machine learning methods cannot accurately predict t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Gyoung S. Na, Seunghun Jang, Hyunju Chang
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/432bbf5584254aeaa21e56b499ab0a42
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:432bbf5584254aeaa21e56b499ab0a42
record_format	dspace
spelling	oai:doaj.org-article:432bbf5584254aeaa21e56b499ab0a422021-12-02T16:09:44ZPredicting thermoelectric properties from chemical formula with explicitly identifying dopant effects10.1038/s41524-021-00564-y2057-3960https://doaj.org/article/432bbf5584254aeaa21e56b499ab0a422021-07-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00564-yhttps://doaj.org/toc/2057-3960Abstract Dopants play an important role in synthesizing materials to improve target materials properties or stabilize the materials. In particular, the dopants are essential to improve thermoelectic performances of the materials. However, existing machine learning methods cannot accurately predict the materials properties of doped materials due to severely nonlinear relations with their materials properties. Here, we propose a unified architecture of neural networks, called DopNet, to accurately predict the materials properties of the doped materials. DopNet identifies the effects of the dopants by explicitly and independently embedding the host materials and the dopants. In our evaluations, DopNet outperformed existing machine learning methods in predicting experimentally measured thermoelectric properties, and the error of DopNet in predicting a figure of merit (ZT) was 0.06 in mean absolute error. In particular, DopNet was significantly effective in an extrapolation problem that predicts ZTs of unknown materials, which is a key task to discover novel thermoelectric materials.Gyoung S. NaSeunghun JangHyunju ChangNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
spellingShingle	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765 Gyoung S. Na Seunghun Jang Hyunju Chang Predicting thermoelectric properties from chemical formula with explicitly identifying dopant effects
description	Abstract Dopants play an important role in synthesizing materials to improve target materials properties or stabilize the materials. In particular, the dopants are essential to improve thermoelectic performances of the materials. However, existing machine learning methods cannot accurately predict the materials properties of doped materials due to severely nonlinear relations with their materials properties. Here, we propose a unified architecture of neural networks, called DopNet, to accurately predict the materials properties of the doped materials. DopNet identifies the effects of the dopants by explicitly and independently embedding the host materials and the dopants. In our evaluations, DopNet outperformed existing machine learning methods in predicting experimentally measured thermoelectric properties, and the error of DopNet in predicting a figure of merit (ZT) was 0.06 in mean absolute error. In particular, DopNet was significantly effective in an extrapolation problem that predicts ZTs of unknown materials, which is a key task to discover novel thermoelectric materials.
format	article
author	Gyoung S. Na Seunghun Jang Hyunju Chang
author_facet	Gyoung S. Na Seunghun Jang Hyunju Chang
author_sort	Gyoung S. Na
title	Predicting thermoelectric properties from chemical formula with explicitly identifying dopant effects
title_short	Predicting thermoelectric properties from chemical formula with explicitly identifying dopant effects
title_full	Predicting thermoelectric properties from chemical formula with explicitly identifying dopant effects
title_fullStr	Predicting thermoelectric properties from chemical formula with explicitly identifying dopant effects
title_full_unstemmed	Predicting thermoelectric properties from chemical formula with explicitly identifying dopant effects
title_sort	predicting thermoelectric properties from chemical formula with explicitly identifying dopant effects
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/432bbf5584254aeaa21e56b499ab0a42
work_keys_str_mv	AT gyoungsna predictingthermoelectricpropertiesfromchemicalformulawithexplicitlyidentifyingdopanteffects AT seunghunjang predictingthermoelectricpropertiesfromchemicalformulawithexplicitlyidentifyingdopanteffects AT hyunjuchang predictingthermoelectricpropertiesfromchemicalformulawithexplicitlyidentifyingdopanteffects
_version_	1718384405928476672

Predicting thermoelectric properties from chemical formula with explicitly identifying dopant effects

Ejemplares similares