Accelerating Materials Development via Automation, Machine Learning, and High-Performance Computing

Successful materials innovations can transform society. However, materials research often involves long timelines and low success probabilities, dissuading investors who have expectations of shorter times from bench to business. A combination of emergent technologies could accelerate the pace of nov...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Joule 2018-08, Vol.2 (8), p.1410-1420
Hauptverfasser: Correa-Baena, Juan-Pablo, Hippalgaonkar, Kedar, van Duren, Jeroen, Jaffer, Shaffiq, Chandrasekhar, Vijay R., Stevanovic, Vladan, Wadia, Cyrus, Guha, Supratik, Buonassisi, Tonio
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1420
container_issue 8
container_start_page 1410
container_title Joule
container_volume 2
creator Correa-Baena, Juan-Pablo
Hippalgaonkar, Kedar
van Duren, Jeroen
Jaffer, Shaffiq
Chandrasekhar, Vijay R.
Stevanovic, Vladan
Wadia, Cyrus
Guha, Supratik
Buonassisi, Tonio
description Successful materials innovations can transform society. However, materials research often involves long timelines and low success probabilities, dissuading investors who have expectations of shorter times from bench to business. A combination of emergent technologies could accelerate the pace of novel materials development by ten times or more, aligning the timelines of stakeholders (investors and researchers), markets, and the environment, while increasing return on investment. First, tool automation enables rapid experimental testing of candidate materials. Second, high-performance computing concentrates experimental bandwidth on promising compounds by predicting and inferring bulk, interface, and defect-related properties. Third, machine learning connects the former two, where experimental outputs automatically refine theory and help define next experiments. We describe state-of-the-art attempts to realize this vision and identify resource gaps. We posit that over the coming decade, this combination of tools will transform the way we perform materials research, with considerable first-mover advantages at stake. [Display omitted] The convergence of high-performance computing, automation, and machine learning promises to accelerate the rate of materials discovery by ≥10 times, better aligning investor and stakeholder timelines. Infrastructure and human-capital investments are discussed, including equipment capabilities, data management, education, and incentives. As our field transitions from thinking “data poor” to thinking “data rich,” we envision a scientific laboratory where the process of materials discovery continues without disruptions, aided by computational power augmenting the human mind, and freeing the latter to perform research closer to the speed of imagination, addressing societal challenges in market-relevant timeframes. A combination of emergent technologies promises to accelerate novel materials development by ten times or more: tool automation, high-performance computing, and machine learning. We describe state-of-the-art attempts to realize this vision and identify resource gaps, including required infrastructure and human-capital investments.
doi_str_mv 10.1016/j.joule.2018.05.009
format Article
fullrecord <record><control><sourceid>elsevier_osti_</sourceid><recordid>TN_cdi_osti_scitechconnect_1618164</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S2542435118302289</els_id><sourcerecordid>S2542435118302289</sourcerecordid><originalsourceid>FETCH-LOGICAL-c441t-63ddfef936053ff4c90ab536f54ee59d279ef3f5e53bf5e5e5ec4f7a4fb477c73</originalsourceid><addsrcrecordid>eNp9kD9PwzAQxS0EEhX0E7BYzE2wYztpBoaq_ClSEQwwW65zbh0lduW4lfj2OJSBCZ10d8N7P909hG4oySmh5V2bt_7QQV4QOs-JyAmpz9CkELzIOBP0_M9-iabD0BJCaF3Mi5JNkF5oDR0EFa3b4lcVIVjVDfgBjtD5fQ8u4qNVeHGIvk8i72ZJpXfWAV6DCi7ZZli5Bq_sdpe9QzA-9MppwEvf7w8j9hpdmMSE6e-8Qp9Pjx_LVbZ-e35ZLtaZ5pzGrGRNY8DUrCSCGcN1TdRGsNIIDiDqpqhqMMwIEGwz9lSam0pxs-FVpSt2hW5PXD9EKwdtI-id9s6BjpKWdE5LnkTsJNLBD0MAI_fB9ip8SUrkmKds5U-ecsxTEiFTnsl1f3JBuv9oIYx4SF82Noz0xtt__d9MwoD8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Accelerating Materials Development via Automation, Machine Learning, and High-Performance Computing</title><source>EZB-FREE-00999 freely available EZB journals</source><source>Alma/SFX Local Collection</source><creator>Correa-Baena, Juan-Pablo ; Hippalgaonkar, Kedar ; van Duren, Jeroen ; Jaffer, Shaffiq ; Chandrasekhar, Vijay R. ; Stevanovic, Vladan ; Wadia, Cyrus ; Guha, Supratik ; Buonassisi, Tonio</creator><creatorcontrib>Correa-Baena, Juan-Pablo ; Hippalgaonkar, Kedar ; van Duren, Jeroen ; Jaffer, Shaffiq ; Chandrasekhar, Vijay R. ; Stevanovic, Vladan ; Wadia, Cyrus ; Guha, Supratik ; Buonassisi, Tonio</creatorcontrib><description>Successful materials innovations can transform society. However, materials research often involves long timelines and low success probabilities, dissuading investors who have expectations of shorter times from bench to business. A combination of emergent technologies could accelerate the pace of novel materials development by ten times or more, aligning the timelines of stakeholders (investors and researchers), markets, and the environment, while increasing return on investment. First, tool automation enables rapid experimental testing of candidate materials. Second, high-performance computing concentrates experimental bandwidth on promising compounds by predicting and inferring bulk, interface, and defect-related properties. Third, machine learning connects the former two, where experimental outputs automatically refine theory and help define next experiments. We describe state-of-the-art attempts to realize this vision and identify resource gaps. We posit that over the coming decade, this combination of tools will transform the way we perform materials research, with considerable first-mover advantages at stake. [Display omitted] The convergence of high-performance computing, automation, and machine learning promises to accelerate the rate of materials discovery by ≥10 times, better aligning investor and stakeholder timelines. Infrastructure and human-capital investments are discussed, including equipment capabilities, data management, education, and incentives. As our field transitions from thinking “data poor” to thinking “data rich,” we envision a scientific laboratory where the process of materials discovery continues without disruptions, aided by computational power augmenting the human mind, and freeing the latter to perform research closer to the speed of imagination, addressing societal challenges in market-relevant timeframes. A combination of emergent technologies promises to accelerate novel materials development by ten times or more: tool automation, high-performance computing, and machine learning. We describe state-of-the-art attempts to realize this vision and identify resource gaps, including required infrastructure and human-capital investments.</description><identifier>ISSN: 2542-4351</identifier><identifier>EISSN: 2542-4351</identifier><identifier>DOI: 10.1016/j.joule.2018.05.009</identifier><language>eng</language><publisher>United States: Elsevier Inc</publisher><subject>accelerated materials development ; artificial intelligence ; energy materials ; machine learning</subject><ispartof>Joule, 2018-08, Vol.2 (8), p.1410-1420</ispartof><rights>2018</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c441t-63ddfef936053ff4c90ab536f54ee59d279ef3f5e53bf5e5e5ec4f7a4fb477c73</citedby><cites>FETCH-LOGICAL-c441t-63ddfef936053ff4c90ab536f54ee59d279ef3f5e53bf5e5e5ec4f7a4fb477c73</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885,27924,27925</link.rule.ids><backlink>$$Uhttps://www.osti.gov/biblio/1618164$$D View this record in Osti.gov$$Hfree_for_read</backlink></links><search><creatorcontrib>Correa-Baena, Juan-Pablo</creatorcontrib><creatorcontrib>Hippalgaonkar, Kedar</creatorcontrib><creatorcontrib>van Duren, Jeroen</creatorcontrib><creatorcontrib>Jaffer, Shaffiq</creatorcontrib><creatorcontrib>Chandrasekhar, Vijay R.</creatorcontrib><creatorcontrib>Stevanovic, Vladan</creatorcontrib><creatorcontrib>Wadia, Cyrus</creatorcontrib><creatorcontrib>Guha, Supratik</creatorcontrib><creatorcontrib>Buonassisi, Tonio</creatorcontrib><title>Accelerating Materials Development via Automation, Machine Learning, and High-Performance Computing</title><title>Joule</title><description>Successful materials innovations can transform society. However, materials research often involves long timelines and low success probabilities, dissuading investors who have expectations of shorter times from bench to business. A combination of emergent technologies could accelerate the pace of novel materials development by ten times or more, aligning the timelines of stakeholders (investors and researchers), markets, and the environment, while increasing return on investment. First, tool automation enables rapid experimental testing of candidate materials. Second, high-performance computing concentrates experimental bandwidth on promising compounds by predicting and inferring bulk, interface, and defect-related properties. Third, machine learning connects the former two, where experimental outputs automatically refine theory and help define next experiments. We describe state-of-the-art attempts to realize this vision and identify resource gaps. We posit that over the coming decade, this combination of tools will transform the way we perform materials research, with considerable first-mover advantages at stake. [Display omitted] The convergence of high-performance computing, automation, and machine learning promises to accelerate the rate of materials discovery by ≥10 times, better aligning investor and stakeholder timelines. Infrastructure and human-capital investments are discussed, including equipment capabilities, data management, education, and incentives. As our field transitions from thinking “data poor” to thinking “data rich,” we envision a scientific laboratory where the process of materials discovery continues without disruptions, aided by computational power augmenting the human mind, and freeing the latter to perform research closer to the speed of imagination, addressing societal challenges in market-relevant timeframes. A combination of emergent technologies promises to accelerate novel materials development by ten times or more: tool automation, high-performance computing, and machine learning. We describe state-of-the-art attempts to realize this vision and identify resource gaps, including required infrastructure and human-capital investments.</description><subject>accelerated materials development</subject><subject>artificial intelligence</subject><subject>energy materials</subject><subject>machine learning</subject><issn>2542-4351</issn><issn>2542-4351</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><recordid>eNp9kD9PwzAQxS0EEhX0E7BYzE2wYztpBoaq_ClSEQwwW65zbh0lduW4lfj2OJSBCZ10d8N7P909hG4oySmh5V2bt_7QQV4QOs-JyAmpz9CkELzIOBP0_M9-iabD0BJCaF3Mi5JNkF5oDR0EFa3b4lcVIVjVDfgBjtD5fQ8u4qNVeHGIvk8i72ZJpXfWAV6DCi7ZZli5Bq_sdpe9QzA-9MppwEvf7w8j9hpdmMSE6e-8Qp9Pjx_LVbZ-e35ZLtaZ5pzGrGRNY8DUrCSCGcN1TdRGsNIIDiDqpqhqMMwIEGwz9lSam0pxs-FVpSt2hW5PXD9EKwdtI-id9s6BjpKWdE5LnkTsJNLBD0MAI_fB9ip8SUrkmKds5U-ecsxTEiFTnsl1f3JBuv9oIYx4SF82Noz0xtt__d9MwoD8</recordid><startdate>20180815</startdate><enddate>20180815</enddate><creator>Correa-Baena, Juan-Pablo</creator><creator>Hippalgaonkar, Kedar</creator><creator>van Duren, Jeroen</creator><creator>Jaffer, Shaffiq</creator><creator>Chandrasekhar, Vijay R.</creator><creator>Stevanovic, Vladan</creator><creator>Wadia, Cyrus</creator><creator>Guha, Supratik</creator><creator>Buonassisi, Tonio</creator><general>Elsevier Inc</general><general>Elsevier</general><scope>6I.</scope><scope>AAFTH</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>OTOTI</scope></search><sort><creationdate>20180815</creationdate><title>Accelerating Materials Development via Automation, Machine Learning, and High-Performance Computing</title><author>Correa-Baena, Juan-Pablo ; Hippalgaonkar, Kedar ; van Duren, Jeroen ; Jaffer, Shaffiq ; Chandrasekhar, Vijay R. ; Stevanovic, Vladan ; Wadia, Cyrus ; Guha, Supratik ; Buonassisi, Tonio</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c441t-63ddfef936053ff4c90ab536f54ee59d279ef3f5e53bf5e5e5ec4f7a4fb477c73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>accelerated materials development</topic><topic>artificial intelligence</topic><topic>energy materials</topic><topic>machine learning</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Correa-Baena, Juan-Pablo</creatorcontrib><creatorcontrib>Hippalgaonkar, Kedar</creatorcontrib><creatorcontrib>van Duren, Jeroen</creatorcontrib><creatorcontrib>Jaffer, Shaffiq</creatorcontrib><creatorcontrib>Chandrasekhar, Vijay R.</creatorcontrib><creatorcontrib>Stevanovic, Vladan</creatorcontrib><creatorcontrib>Wadia, Cyrus</creatorcontrib><creatorcontrib>Guha, Supratik</creatorcontrib><creatorcontrib>Buonassisi, Tonio</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>CrossRef</collection><collection>OSTI.GOV</collection><jtitle>Joule</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Correa-Baena, Juan-Pablo</au><au>Hippalgaonkar, Kedar</au><au>van Duren, Jeroen</au><au>Jaffer, Shaffiq</au><au>Chandrasekhar, Vijay R.</au><au>Stevanovic, Vladan</au><au>Wadia, Cyrus</au><au>Guha, Supratik</au><au>Buonassisi, Tonio</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Accelerating Materials Development via Automation, Machine Learning, and High-Performance Computing</atitle><jtitle>Joule</jtitle><date>2018-08-15</date><risdate>2018</risdate><volume>2</volume><issue>8</issue><spage>1410</spage><epage>1420</epage><pages>1410-1420</pages><issn>2542-4351</issn><eissn>2542-4351</eissn><abstract>Successful materials innovations can transform society. However, materials research often involves long timelines and low success probabilities, dissuading investors who have expectations of shorter times from bench to business. A combination of emergent technologies could accelerate the pace of novel materials development by ten times or more, aligning the timelines of stakeholders (investors and researchers), markets, and the environment, while increasing return on investment. First, tool automation enables rapid experimental testing of candidate materials. Second, high-performance computing concentrates experimental bandwidth on promising compounds by predicting and inferring bulk, interface, and defect-related properties. Third, machine learning connects the former two, where experimental outputs automatically refine theory and help define next experiments. We describe state-of-the-art attempts to realize this vision and identify resource gaps. We posit that over the coming decade, this combination of tools will transform the way we perform materials research, with considerable first-mover advantages at stake. [Display omitted] The convergence of high-performance computing, automation, and machine learning promises to accelerate the rate of materials discovery by ≥10 times, better aligning investor and stakeholder timelines. Infrastructure and human-capital investments are discussed, including equipment capabilities, data management, education, and incentives. As our field transitions from thinking “data poor” to thinking “data rich,” we envision a scientific laboratory where the process of materials discovery continues without disruptions, aided by computational power augmenting the human mind, and freeing the latter to perform research closer to the speed of imagination, addressing societal challenges in market-relevant timeframes. A combination of emergent technologies promises to accelerate novel materials development by ten times or more: tool automation, high-performance computing, and machine learning. We describe state-of-the-art attempts to realize this vision and identify resource gaps, including required infrastructure and human-capital investments.</abstract><cop>United States</cop><pub>Elsevier Inc</pub><doi>10.1016/j.joule.2018.05.009</doi><tpages>11</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2542-4351
ispartof Joule, 2018-08, Vol.2 (8), p.1410-1420
issn 2542-4351
2542-4351
language eng
recordid cdi_osti_scitechconnect_1618164
source EZB-FREE-00999 freely available EZB journals; Alma/SFX Local Collection
subjects accelerated materials development
artificial intelligence
energy materials
machine learning
title Accelerating Materials Development via Automation, Machine Learning, and High-Performance Computing
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T23%3A59%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-elsevier_osti_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Accelerating%20Materials%20Development%20via%20Automation,%20Machine%20Learning,%20and%20High-Performance%20Computing&rft.jtitle=Joule&rft.au=Correa-Baena,%20Juan-Pablo&rft.date=2018-08-15&rft.volume=2&rft.issue=8&rft.spage=1410&rft.epage=1420&rft.pages=1410-1420&rft.issn=2542-4351&rft.eissn=2542-4351&rft_id=info:doi/10.1016/j.joule.2018.05.009&rft_dat=%3Celsevier_osti_%3ES2542435118302289%3C/elsevier_osti_%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_els_id=S2542435118302289&rfr_iscdi=true