Adaptive Design of Alloys for CO2 Activation and Methanation via Reinforcement Learning Monte Carlo Tree Search Algorithm

Data-driven machine learning (ML) has earned remarkable achievements in accelerating materials design, while it heavily relies on high-quality data acquisition. In this work, we develop an adaptive design framework for searching for optimal materials starting from zero data and with as few DFT calcu...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:The journal of physical chemistry letters Ročník 14; číslo 14; s. 3594
Hlavní autoři: Song, Zhilong, Zhou, Qionghua, Lu, Shuaihua, Dieb, Sae, Ling, Chongyi, Wang, Jinlan
Médium: Journal Article
Jazyk:angličtina
japonština
Vydáno: 13.04.2023
ISSN:1948-7185, 1948-7185
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Data-driven machine learning (ML) has earned remarkable achievements in accelerating materials design, while it heavily relies on high-quality data acquisition. In this work, we develop an adaptive design framework for searching for optimal materials starting from zero data and with as few DFT calculations as possible. This framework integrates automatic density functional theory (DFT) calculations with an improved Monte Carlo tree search via reinforcement learning algorithm (MCTS-PG). As a successful example, we apply it to rapidly identify the desired alloy catalysts for CO2 activation and methanation within 200 MCTS-PG steps. To this end, seven alloy surfaces with high theoretical activity and selectivity for CO2 methanation are screened out and further validated by comprehensive free energy calculations. Our adaptive design framework enables the fast computational exploration of materials with desired properties via minimal DFT calculations.Data-driven machine learning (ML) has earned remarkable achievements in accelerating materials design, while it heavily relies on high-quality data acquisition. In this work, we develop an adaptive design framework for searching for optimal materials starting from zero data and with as few DFT calculations as possible. This framework integrates automatic density functional theory (DFT) calculations with an improved Monte Carlo tree search via reinforcement learning algorithm (MCTS-PG). As a successful example, we apply it to rapidly identify the desired alloy catalysts for CO2 activation and methanation within 200 MCTS-PG steps. To this end, seven alloy surfaces with high theoretical activity and selectivity for CO2 methanation are screened out and further validated by comprehensive free energy calculations. Our adaptive design framework enables the fast computational exploration of materials with desired properties via minimal DFT calculations.
AbstractList Data-driven machine learning (ML) has earned remarkable achievements in accelerating materials design, while it heavily relies on high-quality data acquisition. In this work, we develop an adaptive design framework for searching for optimal materials starting from zero data and with as few DFT calculations as possible. This framework integrates automatic density functional theory (DFT) calculations with an improved Monte Carlo tree search via reinforcement learning algorithm (MCTS-PG). As a successful example, we apply it to rapidly identify the desired alloy catalysts for CO2 activation and methanation within 200 MCTS-PG steps. To this end, seven alloy surfaces with high theoretical activity and selectivity for CO2 methanation are screened out and further validated by comprehensive free energy calculations. Our adaptive design framework enables the fast computational exploration of materials with desired properties via minimal DFT calculations.Data-driven machine learning (ML) has earned remarkable achievements in accelerating materials design, while it heavily relies on high-quality data acquisition. In this work, we develop an adaptive design framework for searching for optimal materials starting from zero data and with as few DFT calculations as possible. This framework integrates automatic density functional theory (DFT) calculations with an improved Monte Carlo tree search via reinforcement learning algorithm (MCTS-PG). As a successful example, we apply it to rapidly identify the desired alloy catalysts for CO2 activation and methanation within 200 MCTS-PG steps. To this end, seven alloy surfaces with high theoretical activity and selectivity for CO2 methanation are screened out and further validated by comprehensive free energy calculations. Our adaptive design framework enables the fast computational exploration of materials with desired properties via minimal DFT calculations.
Author Song, Zhilong
Lu, Shuaihua
Wang, Jinlan
Dieb, Sae
Zhou, Qionghua
Ling, Chongyi
Author_xml – sequence: 1
  givenname: Zhilong
  surname: Song
  fullname: Song, Zhilong
– sequence: 2
  givenname: Qionghua
  surname: Zhou
  fullname: Zhou, Qionghua
– sequence: 3
  givenname: Shuaihua
  surname: Lu
  fullname: Lu, Shuaihua
– sequence: 4
  givenname: Sae
  surname: Dieb
  fullname: Dieb, Sae
– sequence: 5
  givenname: Chongyi
  surname: Ling
  fullname: Ling, Chongyi
– sequence: 6
  givenname: Jinlan
  surname: Wang
  fullname: Wang, Jinlan
BookMark eNpNjMtuwjAURK2qlQq0X9CNl92E-jomdpZR-pRASC1dI9u5AaNg09gg8feNRBddzYzO6IzJtQ8eCXkANgXG4UnbON0dbIcpTXPLGBf8ioygFCqToGbX__otGce4Y6womZIjcq4afUjuhPQZo9t4GlpadV04R9qGntZLTis7cJ1c8FT7hi4wbbW_7JPT9BOdH64W9-gTnaPuvfMbugg-Ia113wW66hHp10DsdpBvQu_Sdn9HblrdRbz_ywn5fn1Z1e_ZfPn2UVfzTAuQKUMDAIVBMAaUZU1RFiiLdiaxtDBroFCmEUYoyYTNRW7zRioFbdkajgK04RPyePEe-vBzxJjWexctdp32GI5xzWUpQYhSFfwX-ypmEQ
CitedBy_id crossref_primary_10_1021_accountsmr_1c00236
crossref_primary_10_1002_adfm_202515026
crossref_primary_10_1007_s40843_024_2851_9
crossref_primary_10_32604_cmc_2025_060109
crossref_primary_10_1038_s41929_024_01150_3
crossref_primary_10_1088_2632_2153_ad69ff
crossref_primary_10_1002_cctc_202401213
crossref_primary_10_1039_D5CS00324E
ContentType Journal Article
DBID 7X8
DOI 10.1021/acs.jpclett.3c00242
DatabaseName MEDLINE - Academic
DatabaseTitle MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
Database_xml – sequence: 1
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Chemistry
EISSN 1948-7185
GroupedDBID 53G
55A
5VS
7X8
7~N
AABXI
ABBLG
ABJNI
ABLBI
ABMVS
ABQRX
ABUCX
ACGFO
ACGFS
ACS
ADHLV
AEESW
AENEX
AFEFF
AHGAQ
ALMA_UNASSIGNED_HOLDINGS
AQSVZ
BAANH
CUPRZ
DU5
EBS
ED~
GGK
GNL
IH9
JG~
P2P
RNS
ROL
UI2
VF5
VG9
W1F
XKZ
ID FETCH-LOGICAL-a417t-eb1116be1bb18c0d696e76f57e9c15d168bd4b48704c343c3d7881f9fb2e41ab2
IEDL.DBID 7X8
ISICitedReferencesCount 10
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000972204200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1948-7185
IngestDate Fri Jul 11 11:16:30 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 14
Language English
Japanese
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a417t-eb1116be1bb18c0d696e76f57e9c15d168bd4b48704c343c3d7881f9fb2e41ab2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PQID 2797144986
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2797144986
PublicationCentury 2000
PublicationDate 2023-04-13
PublicationDateYYYYMMDD 2023-04-13
PublicationDate_xml – month: 04
  year: 2023
  text: 2023-04-13
  day: 13
PublicationDecade 2020
PublicationTitle The journal of physical chemistry letters
PublicationYear 2023
SSID ssj0069087
Score 2.4507701
Snippet Data-driven machine learning (ML) has earned remarkable achievements in accelerating materials design, while it heavily relies on high-quality data...
SourceID proquest
SourceType Aggregation Database
StartPage 3594
Title Adaptive Design of Alloys for CO2 Activation and Methanation via Reinforcement Learning Monte Carlo Tree Search Algorithm
URI https://www.proquest.com/docview/2797144986
Volume 14
WOSCitedRecordID wos000972204200001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1JS8QwFA7qCHpxF3cieM3YtGnSnGQYFS-jIgpzG7LVhbEdp1Xw3_uSafXgRfAYKCG8Jt_73sL7EDphNHIpV5pomRrCWJKQTLOcGAH-xwrOI6eC2IS4vs6GQ3nbJNyqpq2yxcQA1LY0Pkd-GgspgPzLjJ9N3ohXjfLV1UZCYx51EqAy_mGK4XcVAQK_IJAHcXpGAIPTdupQTE-VqbovE_gzdd1NTPBUv9A4uJjL1f8ebg2tNOQS92a3YR3NuWIDLfVbTbdN9NmzauIBDp-Hzg1c5rg3HpefFQbyivs3Me6ZVvAMq8LigfO59dn641nhOxdGrZqQVcTNdNZHPPBDrnBfTcclvp86h2dtzLD5I5yzfnrdQg-XF_f9K9KILxDFqKgJYDilXDuqNc1MZLnkTvA8FU4amlrKM22ZhnAnYiZhiUmsH0yfy1zHjlGl4220UJSF20EYaIKLmY60SIFMWKptlDqpIPCxTGomdtFxa9UR2MNXLFThyvdq9GPXvT98s4-WvRi8r_XQ5AB1cnjA7hAtmo_6uZoehbvxBYVAxRg
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Adaptive+Design+of+Alloys+for+CO2+Activation+and+Methanation+via+Reinforcement+Learning+Monte+Carlo+Tree+Search+Algorithm&rft.jtitle=The+journal+of+physical+chemistry+letters&rft.au=Song%2C+Zhilong&rft.au=Zhou%2C+Qionghua&rft.au=Lu%2C+Shuaihua&rft.au=Dieb%2C+Sae&rft.date=2023-04-13&rft.issn=1948-7185&rft.eissn=1948-7185&rft.volume=14&rft.issue=14&rft.spage=3594&rft_id=info:doi/10.1021%2Facs.jpclett.3c00242&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1948-7185&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1948-7185&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1948-7185&client=summon