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 서양
- 최종처리일시
- 20250211152814
- ISBN
- 9798384098614
- DDC
- 540
- 저자명
- Kirkvold, Clara.
- 서명/저자
- Developing Efficient and Accurate Machine-Learning Methods for Understanding and Predicting Molecular and Material Properties
- 발행사항
- [Sl] : University of Minnesota, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 136 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
- 주기사항
- Advisor: Goodpaster, Jason D.
- 학위논문주기
- Thesis (Ph.D.)--University of Minnesota, 2024.
- 초록/해제
- 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.
- 일반주제명
- Chemistry
- 일반주제명
- Physical chemistry
- 일반주제명
- Computational chemistry
- 키워드
- Catalysis
- 키워드
- Machine learning
- 기타저자
- University of Minnesota Chemistry
- 기본자료저록
- Dissertations Abstracts International. 86-03B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 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[Sl]▼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.
