[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291000-105":59,"doc-detail-291000-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","machine-learning-powered-insights-into-metamaterial-prediction-and-design-dissertation","MACHINE LEARNING POWERED INSIGHTS INTO METAMATERIAL PREDICTION AND DESIGN - Dissertation","","Machine learning powered insights into metamaterial prediction and design addresses how ML assumptions hold in real mechanics problems and whether ML can design novel metamaterials using limited prior information. The work focuses on out-of-distribution generalization beyond i.i.d. data, where shifts in unknown test environments can cause model failure. It establishes regression-focused benchmark setups covering covariate shift, mechanism shift, and sampling bias, extending Mechanical MNIST datasets to evaluate OOD methods efficiently.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/machine-learning-powered-insights-into-metamaterial-prediction-and-design-dissertation/291000/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/machine-learning-powered-insights-into-metamaterial-prediction-and-design-dissertation/291000.png","ImageObject",300,407,{"name":92,"@type":93},"Seraphina","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What core problems does the thesis aim to address?","Question",{"text":113,"@type":114},"It targets whether ML model assumptions remain valid for real mechanics settings and whether ML can enable design of novel metamaterials with limited prior information.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"Why are standard i.i.d.-based ML approaches problematic in mechanics research?",{"text":118,"@type":114},"Real-world test environments can differ from training distributions, causing data distribution shifts that break the i.i.d. assumption and reduce reliability.",{"name":120,"@type":111,"acceptedAnswer":121},"What does the thesis contribute for out-of-distribution generalization in regression?",{"text":122,"@type":114},"It studies OOD generalization specifically for regression, identifying covariate shift, mechanism shift, and sampling bias, and creating benchmark examples by extending Mechanical MNIST datasets.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},291000,1789643161,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},962075114101,"https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165","Boston University  \nOpenBU [http://open. bu.edu](http://open. bu.edu)  \nTheses & Dissertations Boston University Theses & Dissertations  \n2024  \nMachine learning powered insights into metamaterial prediction and design  \n[https://hdl.handle.net/2144/49244](https://hdl.handle.net/2144/49244)[ ](https://hdl.handle.net/2144/49244)Boston University  \nBOSTON UNIVERSITY  \nCOLLEGE OF ENGINEERING  \nDissertation  \nMACHINE LEARNING POWERED INSIGHTS INTO  \nMETAMATERIAL PREDICTION AND DESIGN  \nby  \nLINGXIAO YUAN  \nB.S., Xi’an Jiaotong University, 2017  \nM.S., Xi’an Jiaotong University, 2019  \nSubmitted in partial fulfillment of the requirements for the degree of  \nDoctor of Philosophy  \n© 2024 by LINGXIAO YUAN All rights reserved  \nApproved by  \nFirst Reader  \nHarold S. Park, PhD  \nProfessor of Mechanical Engineering  \nProfessor of Materials Science and Engineering  \nSecond Reader  \nEmma Lejeune, PhD  \nAssistant Professor of Mechanical Engineering  \nThird Reader  \nDouglas P. Holmes, PhD  \nAssociate Professor of Mechanical Engineering  \nAssociate Professor of Materials Science and Engineering  \nFourth Reader  \nPaul E. Barbone, PhD  \nProfessor of Mechanical Engineering Professor of Materials Science and Engineering  \nWhen you are studying any matter, or considering any philosophy, ask yourself only what are the facts and what is the truth that the facts bear out. Never let yourself be diverted, either by what you wish to believe, or by what you think would have beneficent social effects if it were believed. But look only, and solely, at what are the facts.  \nBertrand Russell  \nAcknowledgments  \nThis thesis was made possible with the assistance and support from many individuals.  \nFirst and foremost, I would like to thank my advisors Prof. Harold Park and Prof. Emma Lejeune for their consistent guidance and support. Prof. Park has been encouraging me to explore topics that resonate with my interests, patiently guiding me to become an independent and self-directed researcher, and providing ample support whenever I sought help during difficult times. Prof. Lejeune’s expertise in Machine Learning, insightful advice, and dedication toward rigorous research have been greatly supporting me along the way in completing this dissertation. I also thank Prof. Lejeune for fostering a collaborative and vibrant research community, which has been invaluable to me.  \nI am thankful to Prof. Douglas Holmes and Prof. Paul Barbone for their willingness to serve on my Committee, and to Prof. Kamil Ekinci for agreeing to chair my defense. I thank my labmates Jeffrey, Hiba, Saeed, Quan, Sara, Erfan, and Jeong-Ho who have made this journey enjoyable and precious. Additionally, I appreciate the support and assistance provided by MechE staff Emery, Anna, and Patty.  \nLastly, I would like to thank my family, especially my parents, my brother, and my grandparents, for always being there for me. I would also like to thank my fiancé for his unwavering support and companionship, without him I would have completed this dissertation ahead of schedule.  \nMACHINE LEARNING POWERED INSIGHTS INTO METAMATERIAL PREDICTION AND DESIGN  \nLINGXIAO YUAN  \nBoston University, College of Engineering, 2024  \nMajor Professors: Harold S. Park, PhD  \nProfessor of Mechanical Engineering  \nProfessor of Materials Science and Engineering  \nEmma Lejeune, PhD  \nAssistant Professor of Mechanical Engineering  \nABSTRACT  \nThere has been significant recent interest in the mechanics community to apply machine learning methods to design and predict the properties of metamaterials. Metamaterials are distinguished by their programmability, enabling the achievement of novel functionalities typically absent in conventional materials. Understanding metamaterials necessitates unraveling the intricate nonlinear relationship between design choices and mechanical properties. Machine learning (ML) stands out from traditional approaches by its capability to accurately approximate nonlinear relationships and rapidly","cbCaikSwcZQD7miD","https://ap.wps.com/l/cbCaikSwcZQD7miD","pdf",24210766,172,"English","# Abstract\n## Background and motivation\n## Research questions\n## Limitations of i.i.d. assumptions\n## Out-of-distribution (OOD) generalization\n## Regression-focused OOD benchmark design\n## Identified OOD scenarios (covariate shift, mechanism shift, sampling bias)","[{\"question\":\"What core problems does the thesis aim to address?\",\"answer\":\"It targets whether ML model assumptions remain valid for real mechanics settings and whether ML can enable design of novel metamaterials with limited prior information.\"},{\"question\":\"Why are standard i.i.d.-based ML approaches problematic in mechanics research?\",\"answer\":\"Real-world test environments can differ from training distributions, causing data distribution shifts that break the i.i.d. assumption and reduce reliability.\"},{\"question\":\"What does the thesis contribute for out-of-distribution generalization in regression?\",\"answer\":\"It studies OOD generalization specifically for regression, identifying covariate shift, mechanism shift, and sampling bias, and creating benchmark examples by extending Mechanical MNIST datasets.\"}]","MACHINE LEARNING POWERED INSIGHTS INTO METAMATERIAL PREDICTION AND DESIGN - Dissertation | PDF",433]