[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119274-en":3,"doc-seo-119274-105":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},119274,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Materials Design with Machine Learning - Thesis","Materials Design with Machine Learning presents a thesis that unifies machine learning methods with density functional theory data to accelerate discovery in materials science. The work introduces a splashdown representation to better model long-range interactions overlooked by standard descriptors. It also develops ORGANIZER to build a key database, leading to a new organic solid-state lasing molecule and improved emission performance.","Materials Design with Machine  \nLearning  \nby  \nIan Benlolo  \nThesis submitted to the University of Ottawa in partial fulfillment of the requirements for Master of Science in Physics  \nDepartment of Physics  \nFaculty of Science  \nUniversity of Ottawa  \n© Ian Benlolo, Ottawa, Canada, 2023  \nExamining Committee  \nThe following served on the Examining Committee for this thesis.  \nInternal Member: Adina Luican-Mayer  \nProfessor, Department of Physics  \nUniversity of Ottawa  \nInternal Member: Stefanie Czischek  \nAssistant Professor, Department of Physics  \nUniversity of Ottawa  \nSupervisor(s): Isaac Tamblyn  \nProfessor, School of Electrical Engineering & Computer Science University of Ottawa  \nDeclaration of Authorship  \nI hereby certify that this thesis is entirely my own original work except where otherwise indicated. I am aware of the University of Ottawa regulations concerning plagiarism, including those regarding consequent disciplinary actions. Any use of the works of anyother author, in any form, is properly acknowledged at their point of use.  \nAbstract  \nIn the quest to advance materials design, this thesis integrates Machine Learning (ML) techniques with Density Functional Theory (DFT) data. A novel representation called splashdown is formulated to capture long-range interactions, an aspect often neglected by material representations. A project known as ORGANIZER leads to the creation of a pivotal database, culminating in the discovery of a new organic solid-state lasing molecule that doubled the state-of-the-art emission gain cross-section. Concurrently, a monte-carlo based optimizer, aMC, is tested, demonstrating superior performance to gradient-based methods without the need for expensive gradient computation. Enhanced Graph Neural Networks (GNN)s predict High Entropy Alloy (HEA) catalysts for oxygen reduction reaction, halving necessary DFT computations and unveiling a new HEA catalyst with a 0.27Voverpotential. The splashdown representation compares to state-of-the-art ones like MBTRand SOAP in predicting long-range interactions. Collectively, these efforts highlight the transformative potential of ML and some adjacent fields in materials science.  \nAcknowledgements  \nI would like to express my deepest appreciation to all those who have provided the possibility to complete this thesis. I would like to start by extending my sincere gratitude to my supervisor, Isaac. His enduring support, guidance, and insightful critiques have played a crucial role in my journey. His kind nature coupled with brutal honesty pushed me to elevate my work and broaden my perspective. The opportunity to work in this exhilarating field under his supervision has truly been a privilege.  \nI am deeply indebted to Prof. Stephen Whitelam, who led the aMC project. His teachings about efficient and neat work, coupled with the invaluable lesson of consistently revisiting the fundamental question - \"What am I trying to show?\" - have profoundly shaped my approach to scientific inquiry.  \nI am grateful for my colleagues at the CLEAN lab, who were always ready for constructive and enriching discussions. Their insights and inputs often gave my work fresh anglesand new directions. Their presence significantly enhanced the vibrancy of the academic environment.  \nA big thanks to the National Research Council of Canada, the University of Ottawa, NSERC, and the Vector Institute for funding my studies and compute resources.  \nAnd last but certainly not least, my heartfelt thanks go out to my family, friends and loved ones. Their unflinching support and occasional distractions in the form of laughter and camaraderie helped keep my spirits high during the intensive periods of my studies. The role they played in this academic endeavour is beyond measure and I am forever thankful.  \nThe journey of completing this thesis has been an enlightening one, thanks to all of you. This accomplishment would not have been possible without your unwavering faith and constant en","cbCaih5VmK7y4s4S","https://ap.wps.com/l/cbCaih5VmK7y4s4S","pdf",5955654,1,141,"English","en",105,"# Introduction\n## The Energy Crisis\n# Methods\n## Density Functional Theory\n## Alloys, Crystals\n## High Entropy Alloys\n## Oxygen Reduction Reaction\n## Statistical Learning\n### Representation Learning\n### Graph Neural Networks\n### Optimizers","[{\"question\":\"What is the main goal of the thesis?\",\"answer\":\"To advance materials design by integrating machine learning techniques with density functional theory data to improve prediction and accelerate discovery.\"},{\"question\":\"What new representation is introduced, and why?\",\"answer\":\"Splashdown is formulated to capture long-range interactions that are often neglected by conventional material representations.\"},{\"question\":\"How does the thesis improve computational efficiency for catalysts?\",\"answer\":\"Enhanced graph neural networks predict high entropy alloy catalysts, halving the required DFT computations and enabling identification of a catalyst with a reported 0.27V overpotential.\"}]","Materials Design with Machine Learning - Thesis | PDF",1785723453,355,{"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},"materials-design-with-machine-learning-thesis","",{"@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/materials-design-with-machine-learning-thesis/119274/",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},"What is the main goal of the thesis?","Question",{"text":75,"@type":76},"To advance materials design by integrating machine learning techniques with density functional theory data to improve prediction and accelerate discovery.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What new representation is introduced, and why?",{"text":80,"@type":76},"Splashdown is formulated to capture long-range interactions that are often neglected by conventional material representations.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis improve computational efficiency for catalysts?",{"text":84,"@type":76},"Enhanced graph neural networks predict high entropy alloy catalysts, halving the required DFT computations and enabling identification of a catalyst with a reported 0.27V overpotential.","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"]