서브메뉴
검색
Development of Intelligent Systems for Organic Materials Engineering
Development of Intelligent Systems for Organic Materials Engineering
상세정보
- 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
- Machine learning
- 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.


