본문

서브메뉴

Development of Intelligent Systems for Organic Materials Engineering
Development of Intelligent Systems for Organic Materials Engineering
Development of Intelligent Systems for Organic Materials Engineering

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202104709
ISBN  
9798291555255
DDC  
620.11
저자명  
Hart, Matthew R.
서명/저자  
Development of Intelligent Systems for Organic Materials Engineering
발행사항  
[Sl] : The University of North Carolina at Chapel Hill, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
146 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-02, Section: B.
주기사항  
Advisor: Tropsha, Alexander.
학위논문주기  
Thesis (Ph.D.)--The University of North Carolina at Chapel Hill, 2025.
초록/해제  
요약The accelerated availability of data to 21st century chemists has created unprecedented opportunities and two fundamental challenges for the chemical discovery process. The first challenge is that the number of potentially synthesizable organic molecules is so large that uncovering complete structure property relationships is infeasible. The second challenge is that, as scientists explore this chemical space, they produce equally large amounts of experimental, computational, and verbal data that is difficult to manage and integrate. While the methods for addressing these challenges have historically remained separated, this thesis presents computational and conceptual frameworks for navigating these challenges simultaneously through a combination of data curation, machine learning, and knowledge representation and reasoning. Here is presented a general purpose data curation pipeline for organic materials informatics and a demonstration of its utility through the production of polymer and dye databases. This foundation is then used to develop machine learning models for chemical use case predictions in a departure from the traditional property based modeling paradigm. Finally, ontology-guided systems and structured knowledge are leveraged to improve reasoning and accuracy in large language models, enabling more interpretable and reliable question answering in chemistry. Taken together, these individual contributions form the basis of intelligent systems that integrate data, knowledge, and reasoning into unified discovery workflows that can accelerate the discovery and production of organic materials.
일반주제명  
Materials science
일반주제명  
Engineering
일반주제명  
Computational chemistry
키워드  
Cheminformatics
키워드  
Data curation
키워드  
Knowledge engineering
키워드  
Machine learning
키워드  
Materials informatics
키워드  
Ontologies
기타저자  
The University of North Carolina at Chapel Hill Materials Science
기본자료저록  
Dissertations Abstracts International. 87-02B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017358491
■00520260202104709
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798291555255
■035    ▼a(MiAaPQ)AAI32118065
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a620.11
■1001  ▼aHart,  Matthew  R.
■24510▼aDevelopment  of  Intelligent  Systems  for  Organic  Materials  Engineering
■260    ▼a[Sl]▼bThe  University  of  North  Carolina  at  Chapel  Hill▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a146  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-02,  Section:  B.
■500    ▼aAdvisor:  Tropsha,  Alexander.
■5021  ▼aThesis  (Ph.D.)--The  University  of  North  Carolina  at  Chapel  Hill,  2025.
■520    ▼aThe  accelerated  availability  of  data  to  21st  century  chemists  has  created  unprecedented  opportunities  and  two  fundamental  challenges  for  the  chemical  discovery  process.  The  first  challenge  is  that  the  number  of  potentially  synthesizable  organic  molecules  is  so  large  that  uncovering  complete  structure  property  relationships  is  infeasible.  The  second  challenge  is  that,  as  scientists  explore  this  chemical  space,  they  produce  equally  large  amounts  of  experimental,  computational,  and  verbal  data  that  is  difficult  to  manage  and  integrate.  While  the  methods  for  addressing  these  challenges  have  historically  remained  separated,  this  thesis  presents  computational  and  conceptual  frameworks  for  navigating  these  challenges  simultaneously  through  a  combination  of  data  curation,  machine  learning,  and  knowledge  representation  and  reasoning.  Here  is  presented  a  general  purpose  data  curation  pipeline  for  organic  materials  informatics  and  a  demonstration  of  its  utility  through  the  production  of  polymer  and  dye  databases.  This  foundation  is  then  used  to  develop  machine  learning  models  for  chemical  use  case  predictions  in  a  departure  from  the  traditional  property  based  modeling  paradigm.  Finally,  ontology-guided  systems  and  structured  knowledge    are  leveraged  to  improve  reasoning  and  accuracy  in  large  language  models,  enabling  more  interpretable  and  reliable  question  answering  in  chemistry.  Taken  together,  these  individual  contributions  form  the  basis  of  intelligent  systems  that  integrate  data,  knowledge,  and  reasoning  into  unified  discovery  workflows  that  can  accelerate  the  discovery  and  production  of  organic  materials.
■590    ▼aSchool  code:  0153.
■650  4▼aMaterials  science
■650  4▼aEngineering
■650  4▼aComputational  chemistry
■653    ▼aCheminformatics
■653    ▼aData  curation
■653    ▼aKnowledge  engineering
■653    ▼aMachine  learning
■653    ▼aMaterials  informatics
■653    ▼aOntologies
■690    ▼a0794
■690    ▼a0800
■690    ▼a0537
■690    ▼a0219
■71020▼aThe  University  of  North  Carolina  at  Chapel  Hill▼bMaterials  Science.
■7730  ▼tDissertations  Abstracts  International▼g87-02B.
■790    ▼a0153
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358491▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    detalle info

    • Reserva
    • No existe
    • Mi carpeta
    • Primera solicitud
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    Material
    número de libro número de llamada Ubicación estado Prestar info
    TF16225 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Las reservas están disponibles en el libro de préstamos. Para hacer reservaciones, haga clic en el botón de reserva

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.