Predicting carbon nanotube forest attributes and mechanical properties using simulated images and deep learning

Abstract Understanding and controlling the self-assembly of vertically oriented carbon nanotube (CNT) forests is essential for realizing their potential in myriad applications. The governing process–structure–property mechanisms are poorly understood, and the processing parameter space is far too va...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Taher Hajilounezhad, Rina Bao, Kannappan Palaniappan, Filiz Bunyak, Prasad Calyam, Matthew R. Maschmann
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
Acceso en línea:https://doaj.org/article/7cbc035ed72342a18a4f677e7c46a9ae
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:7cbc035ed72342a18a4f677e7c46a9ae
record_format dspace
spelling oai:doaj.org-article:7cbc035ed72342a18a4f677e7c46a9ae2021-12-02T17:08:43ZPredicting carbon nanotube forest attributes and mechanical properties using simulated images and deep learning10.1038/s41524-021-00603-82057-3960https://doaj.org/article/7cbc035ed72342a18a4f677e7c46a9ae2021-08-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00603-8https://doaj.org/toc/2057-3960Abstract Understanding and controlling the self-assembly of vertically oriented carbon nanotube (CNT) forests is essential for realizing their potential in myriad applications. The governing process–structure–property mechanisms are poorly understood, and the processing parameter space is far too vast to exhaustively explore experimentally. We overcome these limitations by using a physics-based simulation as a high-throughput virtual laboratory and image-based machine learning to relate CNT forest synthesis attributes to their mechanical performance. Using CNTNet, our image-based deep learning classifier module trained with synthetic imagery, combinations of CNT diameter, density, and population growth rate classes were labeled with an accuracy of >91%. The CNTNet regression module predicted CNT forest stiffness and buckling load properties with a lower root-mean-square error than that of a regression predictor based on CNT physical parameters. These results demonstrate that image-based machine learning trained using only simulated imagery can distinguish subtle CNT forest morphological features to predict physical material properties with high accuracy. CNTNet paves the way to incorporate scanning electron microscope imagery for high-throughput material discovery.Taher HajilounezhadRina BaoKannappan PalaniappanFiliz BunyakPrasad CalyamMatthew R. MaschmannNature 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
Taher Hajilounezhad
Rina Bao
Kannappan Palaniappan
Filiz Bunyak
Prasad Calyam
Matthew R. Maschmann
Predicting carbon nanotube forest attributes and mechanical properties using simulated images and deep learning
description Abstract Understanding and controlling the self-assembly of vertically oriented carbon nanotube (CNT) forests is essential for realizing their potential in myriad applications. The governing process–structure–property mechanisms are poorly understood, and the processing parameter space is far too vast to exhaustively explore experimentally. We overcome these limitations by using a physics-based simulation as a high-throughput virtual laboratory and image-based machine learning to relate CNT forest synthesis attributes to their mechanical performance. Using CNTNet, our image-based deep learning classifier module trained with synthetic imagery, combinations of CNT diameter, density, and population growth rate classes were labeled with an accuracy of >91%. The CNTNet regression module predicted CNT forest stiffness and buckling load properties with a lower root-mean-square error than that of a regression predictor based on CNT physical parameters. These results demonstrate that image-based machine learning trained using only simulated imagery can distinguish subtle CNT forest morphological features to predict physical material properties with high accuracy. CNTNet paves the way to incorporate scanning electron microscope imagery for high-throughput material discovery.
format article
author Taher Hajilounezhad
Rina Bao
Kannappan Palaniappan
Filiz Bunyak
Prasad Calyam
Matthew R. Maschmann
author_facet Taher Hajilounezhad
Rina Bao
Kannappan Palaniappan
Filiz Bunyak
Prasad Calyam
Matthew R. Maschmann
author_sort Taher Hajilounezhad
title Predicting carbon nanotube forest attributes and mechanical properties using simulated images and deep learning
title_short Predicting carbon nanotube forest attributes and mechanical properties using simulated images and deep learning
title_full Predicting carbon nanotube forest attributes and mechanical properties using simulated images and deep learning
title_fullStr Predicting carbon nanotube forest attributes and mechanical properties using simulated images and deep learning
title_full_unstemmed Predicting carbon nanotube forest attributes and mechanical properties using simulated images and deep learning
title_sort predicting carbon nanotube forest attributes and mechanical properties using simulated images and deep learning
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/7cbc035ed72342a18a4f677e7c46a9ae
work_keys_str_mv AT taherhajilounezhad predictingcarbonnanotubeforestattributesandmechanicalpropertiesusingsimulatedimagesanddeeplearning
AT rinabao predictingcarbonnanotubeforestattributesandmechanicalpropertiesusingsimulatedimagesanddeeplearning
AT kannappanpalaniappan predictingcarbonnanotubeforestattributesandmechanicalpropertiesusingsimulatedimagesanddeeplearning
AT filizbunyak predictingcarbonnanotubeforestattributesandmechanicalpropertiesusingsimulatedimagesanddeeplearning
AT prasadcalyam predictingcarbonnanotubeforestattributesandmechanicalpropertiesusingsimulatedimagesanddeeplearning
AT matthewrmaschmann predictingcarbonnanotubeforestattributesandmechanicalpropertiesusingsimulatedimagesanddeeplearning
_version_ 1718381506714402816