Deep learning framework for material design space exploration using active transfer learning and data augmentation

Abstract Neural network-based generative models have been actively investigated as an inverse design method for finding novel materials in a vast design space. However, the applicability of conventional generative models is limited because they cannot access data outside the range of training sets....

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yongtae Kim, Youngsoo Kim, Charles Yang, Kundo Park, Grace X. Gu, Seunghwa Ryu
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/3abb3c18732c4ddb864b7c0fbbb2e5e1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3abb3c18732c4ddb864b7c0fbbb2e5e1
record_format	dspace
spelling	oai:doaj.org-article:3abb3c18732c4ddb864b7c0fbbb2e5e12021-12-02T16:38:24ZDeep learning framework for material design space exploration using active transfer learning and data augmentation10.1038/s41524-021-00609-22057-3960https://doaj.org/article/3abb3c18732c4ddb864b7c0fbbb2e5e12021-09-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00609-2https://doaj.org/toc/2057-3960Abstract Neural network-based generative models have been actively investigated as an inverse design method for finding novel materials in a vast design space. However, the applicability of conventional generative models is limited because they cannot access data outside the range of training sets. Advanced generative models that were devised to overcome the limitation also suffer from the weak predictive power on the unseen domain. In this study, we propose a deep neural network-based forward design approach that enables an efficient search for superior materials far beyond the domain of the initial training set. This approach compensates for the weak predictive power of neural networks on an unseen domain through gradual updates of the neural network with active transfer learning and data augmentation methods. We demonstrate the potential of our framework with a grid composite optimization problem that has an astronomical number of possible design configurations. Results show that our proposed framework can provide excellent designs close to the global optima, even with the addition of a very small dataset corresponding to less than 0.5% of the initial training dataset size.Yongtae KimYoungsoo KimCharles YangKundo ParkGrace X. GuSeunghwa RyuNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-7 (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 Yongtae Kim Youngsoo Kim Charles Yang Kundo Park Grace X. Gu Seunghwa Ryu Deep learning framework for material design space exploration using active transfer learning and data augmentation
description	Abstract Neural network-based generative models have been actively investigated as an inverse design method for finding novel materials in a vast design space. However, the applicability of conventional generative models is limited because they cannot access data outside the range of training sets. Advanced generative models that were devised to overcome the limitation also suffer from the weak predictive power on the unseen domain. In this study, we propose a deep neural network-based forward design approach that enables an efficient search for superior materials far beyond the domain of the initial training set. This approach compensates for the weak predictive power of neural networks on an unseen domain through gradual updates of the neural network with active transfer learning and data augmentation methods. We demonstrate the potential of our framework with a grid composite optimization problem that has an astronomical number of possible design configurations. Results show that our proposed framework can provide excellent designs close to the global optima, even with the addition of a very small dataset corresponding to less than 0.5% of the initial training dataset size.
format	article
author	Yongtae Kim Youngsoo Kim Charles Yang Kundo Park Grace X. Gu Seunghwa Ryu
author_facet	Yongtae Kim Youngsoo Kim Charles Yang Kundo Park Grace X. Gu Seunghwa Ryu
author_sort	Yongtae Kim
title	Deep learning framework for material design space exploration using active transfer learning and data augmentation
title_short	Deep learning framework for material design space exploration using active transfer learning and data augmentation
title_full	Deep learning framework for material design space exploration using active transfer learning and data augmentation
title_fullStr	Deep learning framework for material design space exploration using active transfer learning and data augmentation
title_full_unstemmed	Deep learning framework for material design space exploration using active transfer learning and data augmentation
title_sort	deep learning framework for material design space exploration using active transfer learning and data augmentation
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/3abb3c18732c4ddb864b7c0fbbb2e5e1
work_keys_str_mv	AT yongtaekim deeplearningframeworkformaterialdesignspaceexplorationusingactivetransferlearninganddataaugmentation AT youngsookim deeplearningframeworkformaterialdesignspaceexplorationusingactivetransferlearninganddataaugmentation AT charlesyang deeplearningframeworkformaterialdesignspaceexplorationusingactivetransferlearninganddataaugmentation AT kundopark deeplearningframeworkformaterialdesignspaceexplorationusingactivetransferlearninganddataaugmentation AT gracexgu deeplearningframeworkformaterialdesignspaceexplorationusingactivetransferlearninganddataaugmentation AT seunghwaryu deeplearningframeworkformaterialdesignspaceexplorationusingactivetransferlearninganddataaugmentation
_version_	1718383567705210880

Deep learning framework for material design space exploration using active transfer learning and data augmentation

Ejemplares similares