A Universal 3D Voxel Descriptor for Solid-State Material Informatics with Deep Convolutional Neural Networks

Abstract Material informatics (MI) is a promising approach to liberate us from the time-consuming Edisonian (trial and error) process for material discoveries, driven by machine-learning algorithms. Several descriptors, which are encoded material features to feed computers, were proposed in the last...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Seiji Kajita, Nobuko Ohba, Ryosuke Jinnouchi, Ryoji Asahi
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2017
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/08e609fd8d164525ba0be3498a88455a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:08e609fd8d164525ba0be3498a88455a
record_format	dspace
spelling	oai:doaj.org-article:08e609fd8d164525ba0be3498a88455a2021-12-02T15:05:25ZA Universal 3D Voxel Descriptor for Solid-State Material Informatics with Deep Convolutional Neural Networks10.1038/s41598-017-17299-w2045-2322https://doaj.org/article/08e609fd8d164525ba0be3498a88455a2017-12-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-17299-whttps://doaj.org/toc/2045-2322Abstract Material informatics (MI) is a promising approach to liberate us from the time-consuming Edisonian (trial and error) process for material discoveries, driven by machine-learning algorithms. Several descriptors, which are encoded material features to feed computers, were proposed in the last few decades. Especially to solid systems, however, their insufficient representations of three dimensionality of field quantities such as electron distributions and local potentials have critically hindered broad and practical successes of the solid-state MI. We develop a simple, generic 3D voxel descriptor that compacts any field quantities, in such a suitable way to implement convolutional neural networks (CNNs). We examine the 3D voxel descriptor encoded from the electron distribution by a regression test with 680 oxides data. The present scheme outperforms other existing descriptors in the prediction of Hartree energies that are significantly relevant to the long-wavelength distribution of the valence electrons. The results indicate that this scheme can forecast any functionals of field quantities just by learning sufficient amount of data, if there is an explicit correlation between the target properties and field quantities. This 3D descriptor opens a way to import prominent CNNs-based algorithms of supervised, semi-supervised and reinforcement learnings into the solid-state MI.Seiji KajitaNobuko OhbaRyosuke JinnouchiRyoji AsahiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-9 (2017)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Seiji Kajita Nobuko Ohba Ryosuke Jinnouchi Ryoji Asahi A Universal 3D Voxel Descriptor for Solid-State Material Informatics with Deep Convolutional Neural Networks
description	Abstract Material informatics (MI) is a promising approach to liberate us from the time-consuming Edisonian (trial and error) process for material discoveries, driven by machine-learning algorithms. Several descriptors, which are encoded material features to feed computers, were proposed in the last few decades. Especially to solid systems, however, their insufficient representations of three dimensionality of field quantities such as electron distributions and local potentials have critically hindered broad and practical successes of the solid-state MI. We develop a simple, generic 3D voxel descriptor that compacts any field quantities, in such a suitable way to implement convolutional neural networks (CNNs). We examine the 3D voxel descriptor encoded from the electron distribution by a regression test with 680 oxides data. The present scheme outperforms other existing descriptors in the prediction of Hartree energies that are significantly relevant to the long-wavelength distribution of the valence electrons. The results indicate that this scheme can forecast any functionals of field quantities just by learning sufficient amount of data, if there is an explicit correlation between the target properties and field quantities. This 3D descriptor opens a way to import prominent CNNs-based algorithms of supervised, semi-supervised and reinforcement learnings into the solid-state MI.
format	article
author	Seiji Kajita Nobuko Ohba Ryosuke Jinnouchi Ryoji Asahi
author_facet	Seiji Kajita Nobuko Ohba Ryosuke Jinnouchi Ryoji Asahi
author_sort	Seiji Kajita
title	A Universal 3D Voxel Descriptor for Solid-State Material Informatics with Deep Convolutional Neural Networks
title_short	A Universal 3D Voxel Descriptor for Solid-State Material Informatics with Deep Convolutional Neural Networks
title_full	A Universal 3D Voxel Descriptor for Solid-State Material Informatics with Deep Convolutional Neural Networks
title_fullStr	A Universal 3D Voxel Descriptor for Solid-State Material Informatics with Deep Convolutional Neural Networks
title_full_unstemmed	A Universal 3D Voxel Descriptor for Solid-State Material Informatics with Deep Convolutional Neural Networks
title_sort	universal 3d voxel descriptor for solid-state material informatics with deep convolutional neural networks
publisher	Nature Portfolio
publishDate	2017
url	https://doaj.org/article/08e609fd8d164525ba0be3498a88455a
work_keys_str_mv	AT seijikajita auniversal3dvoxeldescriptorforsolidstatematerialinformaticswithdeepconvolutionalneuralnetworks AT nobukoohba auniversal3dvoxeldescriptorforsolidstatematerialinformaticswithdeepconvolutionalneuralnetworks AT ryosukejinnouchi auniversal3dvoxeldescriptorforsolidstatematerialinformaticswithdeepconvolutionalneuralnetworks AT ryojiasahi auniversal3dvoxeldescriptorforsolidstatematerialinformaticswithdeepconvolutionalneuralnetworks AT seijikajita universal3dvoxeldescriptorforsolidstatematerialinformaticswithdeepconvolutionalneuralnetworks AT nobukoohba universal3dvoxeldescriptorforsolidstatematerialinformaticswithdeepconvolutionalneuralnetworks AT ryosukejinnouchi universal3dvoxeldescriptorforsolidstatematerialinformaticswithdeepconvolutionalneuralnetworks AT ryojiasahi universal3dvoxeldescriptorforsolidstatematerialinformaticswithdeepconvolutionalneuralnetworks
_version_	1718388811512152064

A Universal 3D Voxel Descriptor for Solid-State Material Informatics with Deep Convolutional Neural Networks

Ejemplares similares