Importance of raw material features for the prediction of flux growth of Al 2 O 3 crystals using machine learning
The flux method is an efficient liquid-phase crystal growth technique. Accordingly, it is expected to be one of the key technologies for the development of innovative inorganic materials in future because it enables the production of high-quality crystals. However, owing to the complexity of the mec...
Gespeichert in:
Veröffentlicht in: | CrystEngComm 2022-05, Vol.24 (17), p.3179-3188 |
---|---|
Hauptverfasser: | , , , , , |
Format: | Artikel |
Sprache: | eng |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 3188 |
---|---|
container_issue | 17 |
container_start_page | 3179 |
container_title | CrystEngComm |
container_volume | 24 |
creator | Yamada, Tetsuya Watanabe, Takanori Hatsusaka, Kazuaki Yuan, Jianjun Koyama, Michihisa Teshima, Katsuya |
description | The flux method is an efficient liquid-phase crystal growth technique. Accordingly, it is expected to be one of the key technologies for the development of innovative inorganic materials in future because it enables the production of high-quality crystals. However, owing to the complexity of the mechanism of crystal growth in fluxes, it is difficult to establish guidelines for the experimental recipe to grow crystals. Thus, flux crystal growth still requires the long process of trial and error. Consequently, our goal is to develop a “process informatics” (PI)-assisted flux method, supported by machine learning. To predict flux crystal growth by linking it to the process, essentially, the experimental parameters must be converted into explanatory variables. However, the explanatory power of describing crystal growth is limited using only process conditions, such as raw materials and flux species, their preparation amounts, and heating conditions. In this study, we focused on using information on raw materials (raw material information) as explanatory variables and investigated their influence on the prediction of flux crystal growth. Aluminum oxide (Al
2
O
3
), in which raw materials have abundant lot numbers, was selected as the target material. After performing 185 growth experiments, we created regression models composed of process conditions and wide raw material information as explanatory variables and Al
2
O
3
particle size distribution as the objective variable. The obtained models clarified the effect of the raw material information on the accuracy of the prediction of crystal growth. Our findings provide new insights into the PI-assisted flux method in terms of the importance of raw material information and effective descriptions. This can contribute to the development of highly accurate prediction models for data-driven experimental suggestion and clarification of important factors in flux crystal growth. |
doi_str_mv | 10.1039/D2CE00010E |
format | Article |
fullrecord | <record><control><sourceid>crossref</sourceid><recordid>TN_cdi_crossref_primary_10_1039_D2CE00010E</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1039_D2CE00010E</sourcerecordid><originalsourceid>FETCH-LOGICAL-c76E-4c62400606a7d21ad6e56cb6319e785339d8c40542424efe5522f8ab5fd989793</originalsourceid><addsrcrecordid>eNpNkEFLw0AQhRdRsFYv_oI5C9HZ3WSTHEuNWij00nvYbmbbSJrU2S3Vf2-KgjKHmffm8R2eEPcSHyXq8ulZzStElFhdiIlMjUkK1Pry330tbkJ4HyOplDgRH4v9YeBoe0cweGB7gr2NxK3twJONR6YAfmCIO4IDU9O62A79Oeu74ydseTjF3VnOOlCwAg2Ov0K0XYBjaPvtiHO7tifoyHI_Grfiyo9fuvvdU7F-qdbzt2S5el3MZ8vE5aZKUmdUimjQ2LxR0jaGMuM2RsuS8iLTumwKl2KWqnHIU5Yp5Qu7yXxTFmVe6ql4-ME6HkJg8vWB273lr1pife6q_utKfwNXu1uP</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Importance of raw material features for the prediction of flux growth of Al 2 O 3 crystals using machine learning</title><source>Royal Society Of Chemistry Journals 2008-</source><source>Alma/SFX Local Collection</source><creator>Yamada, Tetsuya ; Watanabe, Takanori ; Hatsusaka, Kazuaki ; Yuan, Jianjun ; Koyama, Michihisa ; Teshima, Katsuya</creator><creatorcontrib>Yamada, Tetsuya ; Watanabe, Takanori ; Hatsusaka, Kazuaki ; Yuan, Jianjun ; Koyama, Michihisa ; Teshima, Katsuya</creatorcontrib><description>The flux method is an efficient liquid-phase crystal growth technique. Accordingly, it is expected to be one of the key technologies for the development of innovative inorganic materials in future because it enables the production of high-quality crystals. However, owing to the complexity of the mechanism of crystal growth in fluxes, it is difficult to establish guidelines for the experimental recipe to grow crystals. Thus, flux crystal growth still requires the long process of trial and error. Consequently, our goal is to develop a “process informatics” (PI)-assisted flux method, supported by machine learning. To predict flux crystal growth by linking it to the process, essentially, the experimental parameters must be converted into explanatory variables. However, the explanatory power of describing crystal growth is limited using only process conditions, such as raw materials and flux species, their preparation amounts, and heating conditions. In this study, we focused on using information on raw materials (raw material information) as explanatory variables and investigated their influence on the prediction of flux crystal growth. Aluminum oxide (Al
2
O
3
), in which raw materials have abundant lot numbers, was selected as the target material. After performing 185 growth experiments, we created regression models composed of process conditions and wide raw material information as explanatory variables and Al
2
O
3
particle size distribution as the objective variable. The obtained models clarified the effect of the raw material information on the accuracy of the prediction of crystal growth. Our findings provide new insights into the PI-assisted flux method in terms of the importance of raw material information and effective descriptions. This can contribute to the development of highly accurate prediction models for data-driven experimental suggestion and clarification of important factors in flux crystal growth.</description><identifier>ISSN: 1466-8033</identifier><identifier>EISSN: 1466-8033</identifier><identifier>DOI: 10.1039/D2CE00010E</identifier><language>eng</language><ispartof>CrystEngComm, 2022-05, Vol.24 (17), p.3179-3188</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c76E-4c62400606a7d21ad6e56cb6319e785339d8c40542424efe5522f8ab5fd989793</citedby><cites>FETCH-LOGICAL-c76E-4c62400606a7d21ad6e56cb6319e785339d8c40542424efe5522f8ab5fd989793</cites><orcidid>0000-0003-4347-9923 ; 0000-0002-5784-5157 ; 0000-0001-5527-0508</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids></links><search><creatorcontrib>Yamada, Tetsuya</creatorcontrib><creatorcontrib>Watanabe, Takanori</creatorcontrib><creatorcontrib>Hatsusaka, Kazuaki</creatorcontrib><creatorcontrib>Yuan, Jianjun</creatorcontrib><creatorcontrib>Koyama, Michihisa</creatorcontrib><creatorcontrib>Teshima, Katsuya</creatorcontrib><title>Importance of raw material features for the prediction of flux growth of Al 2 O 3 crystals using machine learning</title><title>CrystEngComm</title><description>The flux method is an efficient liquid-phase crystal growth technique. Accordingly, it is expected to be one of the key technologies for the development of innovative inorganic materials in future because it enables the production of high-quality crystals. However, owing to the complexity of the mechanism of crystal growth in fluxes, it is difficult to establish guidelines for the experimental recipe to grow crystals. Thus, flux crystal growth still requires the long process of trial and error. Consequently, our goal is to develop a “process informatics” (PI)-assisted flux method, supported by machine learning. To predict flux crystal growth by linking it to the process, essentially, the experimental parameters must be converted into explanatory variables. However, the explanatory power of describing crystal growth is limited using only process conditions, such as raw materials and flux species, their preparation amounts, and heating conditions. In this study, we focused on using information on raw materials (raw material information) as explanatory variables and investigated their influence on the prediction of flux crystal growth. Aluminum oxide (Al
2
O
3
), in which raw materials have abundant lot numbers, was selected as the target material. After performing 185 growth experiments, we created regression models composed of process conditions and wide raw material information as explanatory variables and Al
2
O
3
particle size distribution as the objective variable. The obtained models clarified the effect of the raw material information on the accuracy of the prediction of crystal growth. Our findings provide new insights into the PI-assisted flux method in terms of the importance of raw material information and effective descriptions. This can contribute to the development of highly accurate prediction models for data-driven experimental suggestion and clarification of important factors in flux crystal growth.</description><issn>1466-8033</issn><issn>1466-8033</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNpNkEFLw0AQhRdRsFYv_oI5C9HZ3WSTHEuNWij00nvYbmbbSJrU2S3Vf2-KgjKHmffm8R2eEPcSHyXq8ulZzStElFhdiIlMjUkK1Pry330tbkJ4HyOplDgRH4v9YeBoe0cweGB7gr2NxK3twJONR6YAfmCIO4IDU9O62A79Oeu74ydseTjF3VnOOlCwAg2Ov0K0XYBjaPvtiHO7tifoyHI_Grfiyo9fuvvdU7F-qdbzt2S5el3MZ8vE5aZKUmdUimjQ2LxR0jaGMuM2RsuS8iLTumwKl2KWqnHIU5Yp5Qu7yXxTFmVe6ql4-ME6HkJg8vWB273lr1pife6q_utKfwNXu1uP</recordid><startdate>20220503</startdate><enddate>20220503</enddate><creator>Yamada, Tetsuya</creator><creator>Watanabe, Takanori</creator><creator>Hatsusaka, Kazuaki</creator><creator>Yuan, Jianjun</creator><creator>Koyama, Michihisa</creator><creator>Teshima, Katsuya</creator><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0003-4347-9923</orcidid><orcidid>https://orcid.org/0000-0002-5784-5157</orcidid><orcidid>https://orcid.org/0000-0001-5527-0508</orcidid></search><sort><creationdate>20220503</creationdate><title>Importance of raw material features for the prediction of flux growth of Al 2 O 3 crystals using machine learning</title><author>Yamada, Tetsuya ; Watanabe, Takanori ; Hatsusaka, Kazuaki ; Yuan, Jianjun ; Koyama, Michihisa ; Teshima, Katsuya</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c76E-4c62400606a7d21ad6e56cb6319e785339d8c40542424efe5522f8ab5fd989793</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yamada, Tetsuya</creatorcontrib><creatorcontrib>Watanabe, Takanori</creatorcontrib><creatorcontrib>Hatsusaka, Kazuaki</creatorcontrib><creatorcontrib>Yuan, Jianjun</creatorcontrib><creatorcontrib>Koyama, Michihisa</creatorcontrib><creatorcontrib>Teshima, Katsuya</creatorcontrib><collection>CrossRef</collection><jtitle>CrystEngComm</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yamada, Tetsuya</au><au>Watanabe, Takanori</au><au>Hatsusaka, Kazuaki</au><au>Yuan, Jianjun</au><au>Koyama, Michihisa</au><au>Teshima, Katsuya</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Importance of raw material features for the prediction of flux growth of Al 2 O 3 crystals using machine learning</atitle><jtitle>CrystEngComm</jtitle><date>2022-05-03</date><risdate>2022</risdate><volume>24</volume><issue>17</issue><spage>3179</spage><epage>3188</epage><pages>3179-3188</pages><issn>1466-8033</issn><eissn>1466-8033</eissn><abstract>The flux method is an efficient liquid-phase crystal growth technique. Accordingly, it is expected to be one of the key technologies for the development of innovative inorganic materials in future because it enables the production of high-quality crystals. However, owing to the complexity of the mechanism of crystal growth in fluxes, it is difficult to establish guidelines for the experimental recipe to grow crystals. Thus, flux crystal growth still requires the long process of trial and error. Consequently, our goal is to develop a “process informatics” (PI)-assisted flux method, supported by machine learning. To predict flux crystal growth by linking it to the process, essentially, the experimental parameters must be converted into explanatory variables. However, the explanatory power of describing crystal growth is limited using only process conditions, such as raw materials and flux species, their preparation amounts, and heating conditions. In this study, we focused on using information on raw materials (raw material information) as explanatory variables and investigated their influence on the prediction of flux crystal growth. Aluminum oxide (Al
2
O
3
), in which raw materials have abundant lot numbers, was selected as the target material. After performing 185 growth experiments, we created regression models composed of process conditions and wide raw material information as explanatory variables and Al
2
O
3
particle size distribution as the objective variable. The obtained models clarified the effect of the raw material information on the accuracy of the prediction of crystal growth. Our findings provide new insights into the PI-assisted flux method in terms of the importance of raw material information and effective descriptions. This can contribute to the development of highly accurate prediction models for data-driven experimental suggestion and clarification of important factors in flux crystal growth.</abstract><doi>10.1039/D2CE00010E</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0003-4347-9923</orcidid><orcidid>https://orcid.org/0000-0002-5784-5157</orcidid><orcidid>https://orcid.org/0000-0001-5527-0508</orcidid></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1466-8033 |
ispartof | CrystEngComm, 2022-05, Vol.24 (17), p.3179-3188 |
issn | 1466-8033 1466-8033 |
language | eng |
recordid | cdi_crossref_primary_10_1039_D2CE00010E |
source | Royal Society Of Chemistry Journals 2008-; Alma/SFX Local Collection |
title | Importance of raw material features for the prediction of flux growth of Al 2 O 3 crystals using machine learning |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T11%3A12%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Importance%20of%20raw%20material%20features%20for%20the%20prediction%20of%20flux%20growth%20of%20Al%202%20O%203%20crystals%20using%20machine%20learning&rft.jtitle=CrystEngComm&rft.au=Yamada,%20Tetsuya&rft.date=2022-05-03&rft.volume=24&rft.issue=17&rft.spage=3179&rft.epage=3188&rft.pages=3179-3188&rft.issn=1466-8033&rft.eissn=1466-8033&rft_id=info:doi/10.1039/D2CE00010E&rft_dat=%3Ccrossref%3E10_1039_D2CE00010E%3C/crossref%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |