Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials

Abstract Various machine learning models have been used to predict the properties of polycrystalline materials, but none of them directly consider the physical interactions among neighboring grains despite such microscopic interactions critically determining macroscopic material properties. Here, we...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Minyi Dai, Mehmet F. Demirel, Yingyu Liang, Jia-Mian Hu
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/21938143166d47f1b76bb49780e33668
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:21938143166d47f1b76bb49780e33668
record_format	dspace
spelling	oai:doaj.org-article:21938143166d47f1b76bb49780e336682021-12-02T16:14:45ZGraph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials10.1038/s41524-021-00574-w2057-3960https://doaj.org/article/21938143166d47f1b76bb49780e336682021-07-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00574-whttps://doaj.org/toc/2057-3960Abstract Various machine learning models have been used to predict the properties of polycrystalline materials, but none of them directly consider the physical interactions among neighboring grains despite such microscopic interactions critically determining macroscopic material properties. Here, we develop a graph neural network (GNN) model for obtaining an embedding of polycrystalline microstructure which incorporates not only the physical features of individual grains but also their interactions. The embedding is then linked to the target property using a feed-forward neural network. Using the magnetostriction of polycrystalline Tb0.3Dy0.7Fe2 alloys as an example, we show that a single GNN model with fixed network architecture and hyperparameters allows for a low prediction error of ~10% over a group of remarkably different microstructures as well as quantifying the importance of each feature in each grain of a microstructure to its magnetostriction. Such a microstructure-graph-based GNN model, therefore, enables an accurate and interpretable prediction of the properties of polycrystalline materials.Minyi DaiMehmet F. DemirelYingyu LiangJia-Mian HuNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-9 (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 Minyi Dai Mehmet F. Demirel Yingyu Liang Jia-Mian Hu Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials
description	Abstract Various machine learning models have been used to predict the properties of polycrystalline materials, but none of them directly consider the physical interactions among neighboring grains despite such microscopic interactions critically determining macroscopic material properties. Here, we develop a graph neural network (GNN) model for obtaining an embedding of polycrystalline microstructure which incorporates not only the physical features of individual grains but also their interactions. The embedding is then linked to the target property using a feed-forward neural network. Using the magnetostriction of polycrystalline Tb0.3Dy0.7Fe2 alloys as an example, we show that a single GNN model with fixed network architecture and hyperparameters allows for a low prediction error of ~10% over a group of remarkably different microstructures as well as quantifying the importance of each feature in each grain of a microstructure to its magnetostriction. Such a microstructure-graph-based GNN model, therefore, enables an accurate and interpretable prediction of the properties of polycrystalline materials.
format	article
author	Minyi Dai Mehmet F. Demirel Yingyu Liang Jia-Mian Hu
author_facet	Minyi Dai Mehmet F. Demirel Yingyu Liang Jia-Mian Hu
author_sort	Minyi Dai
title	Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials
title_short	Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials
title_full	Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials
title_fullStr	Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials
title_full_unstemmed	Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials
title_sort	graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/21938143166d47f1b76bb49780e33668
work_keys_str_mv	AT minyidai graphneuralnetworksforanaccurateandinterpretablepredictionofthepropertiesofpolycrystallinematerials AT mehmetfdemirel graphneuralnetworksforanaccurateandinterpretablepredictionofthepropertiesofpolycrystallinematerials AT yingyuliang graphneuralnetworksforanaccurateandinterpretablepredictionofthepropertiesofpolycrystallinematerials AT jiamianhu graphneuralnetworksforanaccurateandinterpretablepredictionofthepropertiesofpolycrystallinematerials
_version_	1718384279025614848

Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials

Ejemplares similares