Advanced machine learning decision policies for diameter control of carbon nanotubes

Abstract The diameters of single-walled carbon nanotubes (SWCNTs) are directly related to their electronic properties, making diameter control highly desirable for a number of applications. Here we utilized a machine learning planner based on the Expected Improvement decision policy that mapped regi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Rahul Rao, Jennifer Carpena-Núñez, Pavel Nikolaev, Michael A. Susner, Kristofer G. Reyes, Benji Maruyama
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/405301fc6d5648b1b8d827b52675e7b9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:405301fc6d5648b1b8d827b52675e7b9
record_format	dspace
spelling	oai:doaj.org-article:405301fc6d5648b1b8d827b52675e7b92021-12-02T18:51:13ZAdvanced machine learning decision policies for diameter control of carbon nanotubes10.1038/s41524-021-00629-y2057-3960https://doaj.org/article/405301fc6d5648b1b8d827b52675e7b92021-10-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00629-yhttps://doaj.org/toc/2057-3960Abstract The diameters of single-walled carbon nanotubes (SWCNTs) are directly related to their electronic properties, making diameter control highly desirable for a number of applications. Here we utilized a machine learning planner based on the Expected Improvement decision policy that mapped regions where growth was feasible vs. not feasible and further optimized synthesis conditions to selectively grow SWCNTs within a narrow diameter range. We maximized two ranges corresponding to Raman radial breathing mode frequencies around 265 and 225 cm−1 (SWCNT diameters around 0.92 and 1.06 nm, respectively), and our planner found optimal synthesis conditions within a hundred experiments. Extensive post-growth characterization showed high selectivity in the optimized growth experiments compared to the unoptimized growth experiments. Remarkably, our planner revealed significantly different synthesis conditions for maximizing the two diameter ranges in spite of their relative closeness. Our study shows the promise for machine learning-driven diameter optimization and paves the way towards chirality-controlled SWCNT growth.Rahul RaoJennifer Carpena-NúñezPavel NikolaevMichael A. SusnerKristofer G. ReyesBenji MaruyamaNature 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 Rahul Rao Jennifer Carpena-Núñez Pavel Nikolaev Michael A. Susner Kristofer G. Reyes Benji Maruyama Advanced machine learning decision policies for diameter control of carbon nanotubes
description	Abstract The diameters of single-walled carbon nanotubes (SWCNTs) are directly related to their electronic properties, making diameter control highly desirable for a number of applications. Here we utilized a machine learning planner based on the Expected Improvement decision policy that mapped regions where growth was feasible vs. not feasible and further optimized synthesis conditions to selectively grow SWCNTs within a narrow diameter range. We maximized two ranges corresponding to Raman radial breathing mode frequencies around 265 and 225 cm−1 (SWCNT diameters around 0.92 and 1.06 nm, respectively), and our planner found optimal synthesis conditions within a hundred experiments. Extensive post-growth characterization showed high selectivity in the optimized growth experiments compared to the unoptimized growth experiments. Remarkably, our planner revealed significantly different synthesis conditions for maximizing the two diameter ranges in spite of their relative closeness. Our study shows the promise for machine learning-driven diameter optimization and paves the way towards chirality-controlled SWCNT growth.
format	article
author	Rahul Rao Jennifer Carpena-Núñez Pavel Nikolaev Michael A. Susner Kristofer G. Reyes Benji Maruyama
author_facet	Rahul Rao Jennifer Carpena-Núñez Pavel Nikolaev Michael A. Susner Kristofer G. Reyes Benji Maruyama
author_sort	Rahul Rao
title	Advanced machine learning decision policies for diameter control of carbon nanotubes
title_short	Advanced machine learning decision policies for diameter control of carbon nanotubes
title_full	Advanced machine learning decision policies for diameter control of carbon nanotubes
title_fullStr	Advanced machine learning decision policies for diameter control of carbon nanotubes
title_full_unstemmed	Advanced machine learning decision policies for diameter control of carbon nanotubes
title_sort	advanced machine learning decision policies for diameter control of carbon nanotubes
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/405301fc6d5648b1b8d827b52675e7b9
work_keys_str_mv	AT rahulrao advancedmachinelearningdecisionpoliciesfordiametercontrolofcarbonnanotubes AT jennifercarpenanunez advancedmachinelearningdecisionpoliciesfordiametercontrolofcarbonnanotubes AT pavelnikolaev advancedmachinelearningdecisionpoliciesfordiametercontrolofcarbonnanotubes AT michaelasusner advancedmachinelearningdecisionpoliciesfordiametercontrolofcarbonnanotubes AT kristofergreyes advancedmachinelearningdecisionpoliciesfordiametercontrolofcarbonnanotubes AT benjimaruyama advancedmachinelearningdecisionpoliciesfordiametercontrolofcarbonnanotubes
_version_	1718377442746302464

Advanced machine learning decision policies for diameter control of carbon nanotubes

Ejemplares similares