서브메뉴
검색
Developing Efficient and Accurate Machine-Learning Methods for Understanding and Predicting Molecular and Material Properties.
Developing Efficient and Accurate Machine-Learning Methods for Understanding and Predicting Molecular and Material Properties.
상세정보
- 자료유형
- 학위논문
- Control Number
- 0017163957
- International Standard Book Number
- 9798384098614
- Dewey Decimal Classification Number
- 540
- Main Entry-Personal Name
- Kirkvold, Clara.
- Publication, Distribution, etc. (Imprint
- [S.l.] : University of Minnesota., 2024
- Publication, Distribution, etc. (Imprint
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- Physical Description
- 136 p.
- General Note
- Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
- General Note
- Advisor: Goodpaster, Jason D.
- Dissertation Note
- Thesis (Ph.D.)--University of Minnesota, 2024.
- Summary, Etc.
- 요약Machine learning has been widely applied to accelerate molecular simulations and predict molecular/material properties. Machine learning accomplishes this by leveraging the patterns and relationships between a system's features and the desired property. To further the application of machine learning in chemistry, developing new algorithms and featurization techniques is vital. This dissertation presents innovative machine-learning frameworks and featurization techniques to predict a variety of molecular/material properties and accelerate molecular simulations. In Chapter 2, we investigate training neural networks on features built from information obtained from cheap computational electronic structure (e.g., Hartree-Fock) calculations to predict more expensive ab initio calculations. Chapter 3 presents the development of a machine learning framework that combines neural networks with the many-body expanded Full Configuration Interaction method. In Chapter 4, we apply featurization techniques inspired by natural language processing to leverage nominal categorical data for predicting adsorption energies on metallic surfaces at the Density Functional Theory level. Finally, Chapter 5 introduces a novel hybrid Neural Network Potential/Molecular Mechanics algorithm. Overall, this work provides significant insight into developing more efficient and accurate machine-learning methods for understanding and predicting molecular and material properties.
- Subject Added Entry-Topical Term
- Chemistry.
- Subject Added Entry-Topical Term
- Physical chemistry.
- Subject Added Entry-Topical Term
- Computational chemistry.
- Index Term-Uncontrolled
- Catalysis
- Index Term-Uncontrolled
- Electronic structure
- Index Term-Uncontrolled
- Machine learning
- Index Term-Uncontrolled
- Embedding networks
- Index Term-Uncontrolled
- Natural language processing
- Added Entry-Corporate Name
- University of Minnesota Chemistry
- Host Item Entry
- Dissertations Abstracts International. 86-03B.
- Electronic Location and Access
- 로그인을 한후 보실 수 있는 자료입니다.
- Control Number
- joongbu:656853
MARC
008250224s2024 us ||||||||||||||c||eng d■001000017163957
■00520250211152814
■006m o d
■007cr#unu||||||||
■020 ▼a9798384098614
■035 ▼a(MiAaPQ)AAI31558338
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a540
■1001 ▼aKirkvold, Clara.
■24510▼aDeveloping Efficient and Accurate Machine-Learning Methods for Understanding and Predicting Molecular and Material Properties.
■260 ▼a[S.l.]▼bUniversity of Minnesota. ▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a136 p.
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-03, Section: B.
■500 ▼aAdvisor: Goodpaster, Jason D.
■5021 ▼aThesis (Ph.D.)--University of Minnesota, 2024.
■520 ▼aMachine learning has been widely applied to accelerate molecular simulations and predict molecular/material properties. Machine learning accomplishes this by leveraging the patterns and relationships between a system's features and the desired property. To further the application of machine learning in chemistry, developing new algorithms and featurization techniques is vital. This dissertation presents innovative machine-learning frameworks and featurization techniques to predict a variety of molecular/material properties and accelerate molecular simulations. In Chapter 2, we investigate training neural networks on features built from information obtained from cheap computational electronic structure (e.g., Hartree-Fock) calculations to predict more expensive ab initio calculations. Chapter 3 presents the development of a machine learning framework that combines neural networks with the many-body expanded Full Configuration Interaction method. In Chapter 4, we apply featurization techniques inspired by natural language processing to leverage nominal categorical data for predicting adsorption energies on metallic surfaces at the Density Functional Theory level. Finally, Chapter 5 introduces a novel hybrid Neural Network Potential/Molecular Mechanics algorithm. Overall, this work provides significant insight into developing more efficient and accurate machine-learning methods for understanding and predicting molecular and material properties.
■590 ▼aSchool code: 0130.
■650 4▼aChemistry.
■650 4▼aPhysical chemistry.
■650 4▼aComputational chemistry.
■653 ▼aCatalysis
■653 ▼aElectronic structure
■653 ▼aMachine learning
■653 ▼aEmbedding networks
■653 ▼aNatural language processing
■690 ▼a0485
■690 ▼a0800
■690 ▼a0219
■690 ▼a0494
■71020▼aUniversity of Minnesota▼bChemistry.
■7730 ▼tDissertations Abstracts International▼g86-03B.
■790 ▼a0130
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163957▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
미리보기
내보내기
chatGPT토론
Ai 추천 관련 도서
Buch Status
- Reservierung
- 캠퍼스간 도서대출
- 서가에 없는 책 신고
- Meine Mappe
