[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119874-en":3,"doc-seo-119874-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119874,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1786009248482753345",8,"Research & Report","Predicting Material Structures and Properties Using Deep Learning And Machine Learning Algorithms - Doctoral Dissertation","Discovering new materials and understanding their crystal structures and chemical properties are critical tasks in material sciences. Computational approaches such as Density Functional Theory (DFT) can support crystal structure search, but they are often too computationally demanding for predicting structures and properties across most material families, particularly those with many atoms. This dissertation develops deep learning and machine learning algorithms for efficient, data-driven prediction of crystal structures and material properties.","University of South Carolina  \nScholar Commons  \nTheses and Dissertations  \nSummer 2023  \nPredicting Material Structures and Properties Using Deep Learning And Machine Learning Algorithms  \nYuqi Song  \nFollow this and additional works at: [https://scholarcommons.sc.edu/etd](https://scholarcommons.sc.edu/etd)  \n Part of the Computer Sciences Commons, and the Engineering Commons  \nRecommended Citation  \nSong, Y. (2023) . Predicting Material Structures and Properties Using Deep Learning And Machine Learning Algorithms. (Doctoral dissertation) . Retrieved from [https://scholarcommons.sc.edu/etd/7481](https://scholarcommons.sc.edu/etd/7481)  \n[This Open Access Dissertation is brought to you by Scholar Commons. It has been accepted for inclusion in](This Open Access Dissertation is brought to you by Scholar Commons. It has been accepted for inclusion in)[ ](This Open Access Dissertation is brought to you by Scholar Commons. It has been accepted for inclusion in)[Theses and Dissertations by an authorized administrator of Scholar Commons. For more information](Theses and Dissertations by an authorized administrator of Scholar Commons. For more information), please [contact digres@mailbox.sc.edu](contact digres@mailbox.sc.edu).  \nPredicting Material Structures and Properties Using Deep Learning  \nand Machine Learning Algorithms  \nby  \nYuqi Song  \nBachelor of Software Engineering  \nChongqing University 2016  \nMaster of Software Engineering  \nChongqing University 2019  \nSubmitted in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy in Computer Science and Engineering College of Engineering and Computing University of South Carolina 2023  \nAccepted by: Jianjun Hu, Major Professor Yan Tong, Committee Member Forest Agostinelli, Committee Member Qi Zhang, Committee Member Ming Hu, Committee Member Ann Vail, Dean of the Graduate School  \n© Copyright by Yuqi Song, 2023 All Rights Reserved.  \nii  \nAcknowledgments  \nI would like to express my deepest appreciation to my supervisor Dr. Jianjun Hu, who constructively guided and generously provided knowledge and expertise throughout my PhD program. His enthusiasm for research, passion for coding, and his invaluable insights deeply impact my research work and career planning. I could not have undertaken this interesting journey without him.  \nI would also like to extend my deepest gratitude to my dissertation committee members: Dr. Yan Tong, Dr. Forest Agostinelli, Dr. Qi Zhang and Dr. Ming Hu. I appreciate their time and useful suggestions on my work which are very important and valuable in the process of completing my dissertation.  \nI am also grateful to all my collaborators and classmates at the University of South Carolina for their help in various aspects of study and life, these are the intangible and valuable treasures of my last four years. Especially, I want to thank Dr. Yong Zhao, and Dr. Steph-Yves Louis for their practical suggestions and helpful contributions to my research and career development, as well as Dr. Edirisuriya M. Dilanga Siriwardane, Rongzhi Dong, Nihang Fu, Lai Wei, Qinyang Li, Sadman Sadeed Omee, and Rui Xin for their helpful discussion and advice to my research.  \nThe completion of my dissertation would not have been possible without the support and nurturing of my parents and my husband Xin Zhang. Their belief in me has kept my spirits and motivation high during these years. I would also like to thank my puppy ’Captain’, for all the entertainment and emotional support.  \nAbstract  \nDiscovering new materials and understanding their crystal structures and chemical properties are critical tasks in the material sciences. Although computational methodologies such as Density Functional Theory (DFT), provide a convenient means for calculating certain properties of materials or predicting crystal structures when combined with search algorithms, DFT is computationally too demanding for structure prediction and property calculation for most material ","cbCaim7g7TVgGUBm","https://ap.wps.com/l/cbCaim7g7TVgGUBm","pdf",15107941,1,137,"English","en",105,"# Abstract\n## Background and Motivation\n## DeltaCrystal: Deep Learning for Crystal Structure Prediction\n## Motif-Based Crystal Structure Prediction\n## Data-Driven Feature Extraction for Property Prediction","[{\"question\":\"Why does the dissertation focus on deep learning and machine learning instead of relying on DFT?\",\"answer\":\"DFT is computationally too demanding for structure prediction and property calculation for most material families, especially when materials contain many atoms. The dissertation targets this limitation with data-driven models.\"},{\"question\":\"What is DeltaCrystal and how does it predict crystal structures?\",\"answer\":\"DeltaCrystal learns the atomic distance matrix from a material composition using a deep residual neural network, then reconstructs the 3D structure with a genetic algorithm. Experiments demonstrate improved effectiveness and reliability.\"},{\"question\":\"How do the motif-based ideas reduce crystal structure search complexity?\",\"answer\":\"The dissertation extracts structural polyhedron motifs observed frequently across crystal materials with high geometric conservation. By leveraging these recurring patterns, it aims to significantly reduce search complexity.\"}]","Predicting Material Structures and Properties Using Deep Learning And Machine Learning Algorithms - Doctoral Dissertation | PDF",1785726765,345,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"predicting-material-structures-and-properties-using-deep-learning-and-machine-learning-algorithms-doctoral-dissertation","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/predicting-material-structures-and-properties-using-deep-learning-and-machine-learning-algorithms-doctoral-dissertation/119874/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why does the dissertation focus on deep learning and machine learning instead of relying on DFT?","Question",{"text":75,"@type":76},"DFT is computationally too demanding for structure prediction and property calculation for most material families, especially when materials contain many atoms. The dissertation targets this limitation with data-driven models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is DeltaCrystal and how does it predict crystal structures?",{"text":80,"@type":76},"DeltaCrystal learns the atomic distance matrix from a material composition using a deep residual neural network, then reconstructs the 3D structure with a genetic algorithm. Experiments demonstrate improved effectiveness and reliability.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the motif-based ideas reduce crystal structure search complexity?",{"text":84,"@type":76},"The dissertation extracts structural polyhedron motifs observed frequently across crystal materials with high geometric conservation. By leveraging these recurring patterns, it aims to significantly reduce search complexity.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]