Deep learning-based estimation of Flory–Huggins parameter of A–B block copolymers from cross-sectional images of phase-separated structures

Abstract In this study, deep learning (DL)-based estimation of the Flory–Huggins χ parameter of A-B diblock copolymers from two-dimensional cross-sectional images of three-dimensional (3D) phase-separated structures were investigated. 3D structures with random networks of phase-separated domains wer...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Katsumi Hagita, Takeshi Aoyagi, Yuto Abe, Shinya Genda, Takashi Honda
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/23277c4f89ff4663aec541534d1fba24
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:23277c4f89ff4663aec541534d1fba24
record_format	dspace
spelling	oai:doaj.org-article:23277c4f89ff4663aec541534d1fba242021-12-02T17:47:23ZDeep learning-based estimation of Flory–Huggins parameter of A–B block copolymers from cross-sectional images of phase-separated structures10.1038/s41598-021-91761-82045-2322https://doaj.org/article/23277c4f89ff4663aec541534d1fba242021-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-91761-8https://doaj.org/toc/2045-2322Abstract In this study, deep learning (DL)-based estimation of the Flory–Huggins χ parameter of A-B diblock copolymers from two-dimensional cross-sectional images of three-dimensional (3D) phase-separated structures were investigated. 3D structures with random networks of phase-separated domains were generated from real-space self-consistent field simulations in the 25–40 χN range for chain lengths (N) of 20 and 40. To confirm that the prepared data can be discriminated using DL, image classification was performed using the VGG-16 network. We comprehensively investigated the performances of the learned networks in the regression problem. The generalization ability was evaluated from independent images with the unlearned χN. We found that, except for large χN values, the standard deviation values were approximately 0.1 and 0.5 for A-component fractions of 0.2 and 0.35, respectively. The images for larger χN values were more difficult to distinguish. In addition, the learning performances for the 4-class problem were comparable to those for the 8-class problem, except when the χN values were large. This information is useful for the analysis of real experimental image data, where the variation of samples is limited.Katsumi HagitaTakeshi AoyagiYuto AbeShinya GendaTakashi HondaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-16 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Katsumi Hagita Takeshi Aoyagi Yuto Abe Shinya Genda Takashi Honda Deep learning-based estimation of Flory–Huggins parameter of A–B block copolymers from cross-sectional images of phase-separated structures
description	Abstract In this study, deep learning (DL)-based estimation of the Flory–Huggins χ parameter of A-B diblock copolymers from two-dimensional cross-sectional images of three-dimensional (3D) phase-separated structures were investigated. 3D structures with random networks of phase-separated domains were generated from real-space self-consistent field simulations in the 25–40 χN range for chain lengths (N) of 20 and 40. To confirm that the prepared data can be discriminated using DL, image classification was performed using the VGG-16 network. We comprehensively investigated the performances of the learned networks in the regression problem. The generalization ability was evaluated from independent images with the unlearned χN. We found that, except for large χN values, the standard deviation values were approximately 0.1 and 0.5 for A-component fractions of 0.2 and 0.35, respectively. The images for larger χN values were more difficult to distinguish. In addition, the learning performances for the 4-class problem were comparable to those for the 8-class problem, except when the χN values were large. This information is useful for the analysis of real experimental image data, where the variation of samples is limited.
format	article
author	Katsumi Hagita Takeshi Aoyagi Yuto Abe Shinya Genda Takashi Honda
author_facet	Katsumi Hagita Takeshi Aoyagi Yuto Abe Shinya Genda Takashi Honda
author_sort	Katsumi Hagita
title	Deep learning-based estimation of Flory–Huggins parameter of A–B block copolymers from cross-sectional images of phase-separated structures
title_short	Deep learning-based estimation of Flory–Huggins parameter of A–B block copolymers from cross-sectional images of phase-separated structures
title_full	Deep learning-based estimation of Flory–Huggins parameter of A–B block copolymers from cross-sectional images of phase-separated structures
title_fullStr	Deep learning-based estimation of Flory–Huggins parameter of A–B block copolymers from cross-sectional images of phase-separated structures
title_full_unstemmed	Deep learning-based estimation of Flory–Huggins parameter of A–B block copolymers from cross-sectional images of phase-separated structures
title_sort	deep learning-based estimation of flory–huggins parameter of a–b block copolymers from cross-sectional images of phase-separated structures
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/23277c4f89ff4663aec541534d1fba24
work_keys_str_mv	AT katsumihagita deeplearningbasedestimationoffloryhugginsparameterofabblockcopolymersfromcrosssectionalimagesofphaseseparatedstructures AT takeshiaoyagi deeplearningbasedestimationoffloryhugginsparameterofabblockcopolymersfromcrosssectionalimagesofphaseseparatedstructures AT yutoabe deeplearningbasedestimationoffloryhugginsparameterofabblockcopolymersfromcrosssectionalimagesofphaseseparatedstructures AT shinyagenda deeplearningbasedestimationoffloryhugginsparameterofabblockcopolymersfromcrosssectionalimagesofphaseseparatedstructures AT takashihonda deeplearningbasedestimationoffloryhugginsparameterofabblockcopolymersfromcrosssectionalimagesofphaseseparatedstructures
_version_	1718379453447405568

Deep learning-based estimation of Flory–Huggins parameter of A–B block copolymers from cross-sectional images of phase-separated structures

Ejemplares similares