2026-09-18T21:57:54Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1290542026-06-16T18:53:48Zcom_1721.1_7582com_1721.1_7581col_1721.1_131022

Jeffrey Grossman. Xie, Tian,Ph.D.Massachusetts Institute of Technology. Massachusetts Institute of Technology. Department of Materials Science and Engineering. Massachusetts Institute of Technology. Department of Materials Science and Engineering 2021-01-05T23:15:40Z 2021-01-05T23:15:40Z 2020 2020 https://hdl.handle.net/1721.1/129054 1227037031 Thesis: Ph. D., Massachusetts Institute of Technology, Department of Materials Science and Engineering, 2020 Cataloged from student-submitted PDF of thesis. Includes bibliographical references (pages 127-145). The trend of open material data and automation in the past decade offers a unique opportunity for data-driven design of novel materials for various applications as well as fundamental scientific understanding, but it also poses a challenge for conventional machine learning approaches based on structure features. In this thesis, I develop a class of deep learning methods that solve various types of learning problems for solid materials, and demonstrate its application to both accelerate material design and understand scientific knowledge. First, I present a neural network architecture to learn the representations of an arbitrary solid material, which encodes several fundamental symmetries for solid materials as inductive biases. Then, I extend the approach to explore four different learning problems: 1) supervised learning to predict material properties from structures; 2) visualization to understand structure-property relations; 3) unsupervised learning to understand atomic scale dynamics from time series trajectories; 4) active learning to explore an unknown material space. In each learning problem, I demonstrate the performance of the approach compared with previous approaches, and apply it to solve several realistic materials design problems and extract scientific insights from data. by Tian Xie. Ph.D. Ph.D. Massachusetts Institute of Technology, Department of Materials Science and Engineering 145 pages eng Massachusetts Institute of Technology MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided. http://dspace.mit.edu/handle/1721.1/7582 Materials Science and Engineering. Deep learning methods for the design and understanding of solid materials Thesis application/pdf 2021-01-05T23:15:39Z Publication Doctoral MatSci unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="2e3c9f7a-3581-4f09-8c19-6c362ce5cc71"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Deep learning methods for the design and understanding of solid materials</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2020</PublicationDate> <Authors> <Author> <DisplayName>Xie, Tian,Ph.D.Massachusetts Institute of Technology.</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Materials Science and Engineering.</Keyword> <Abstract>The trend of open material data and automation in the past decade offers a unique opportunity for data-driven design of novel materials for various applications as well as fundamental scientific understanding, but it also poses a challenge for conventional machine learning approaches based on structure features. In this thesis, I develop a class of deep learning methods that solve various types of learning problems for solid materials, and demonstrate its application to both accelerate material design and understand scientific knowledge. First, I present a neural network architecture to learn the representations of an arbitrary solid material, which encodes several fundamental symmetries for solid materials as inductive biases. Then, I extend the approach to explore four different learning problems: 1) supervised learning to predict material properties from structures; 2) visualization to understand structure-property relations; 3) unsupervised learning to understand atomic scale dynamics from time series trajectories; 4) active learning to explore an unknown material space. In each learning problem, I demonstrate the performance of the approach compared with previous approaches, and apply it to solve several realistic materials design problems and extract scientific insights from data.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>