[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121517-en":3,"doc-seo-121517-105":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},121517,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning Methods for Hypervelocity Fragment Flyout Characterization - A Dissertation","Hypervelocity fragments generated by breakup events, including collisions and explosions, pose hazards to both terrestrial and on-orbit environments, motivating accurate characterization of fragmentation outcomes. Publicly available two-line element datasets from on-orbit breakups are limited, often omitting pre-detonation parent-body conditions such as orientation and underrepresenting smaller fragments, with dataset uncertainty varying across collections. This work applies machine learning to estimate distribution characteristics of debris clouds by augmenting existing space-debris data with simulated fragmentation events. Gaussian mixture models and k-nearest-neighbor regression infer fragment spatial distribution and counts from two-line element inputs, while neural networks predict individual fragment orbital element locations using simulations initialized from realistic explosion-derived conditions and propagated with J2–J6 gravity harmonics and atmospheric drag.","Doctoral Dissertations and Master's Theses  \nSpring 2025  \nMachine Learning Methods for Hypervelocity Fragment Flyout Characterization  \nKatharine Larsen  \nEmbry-Riddle Aeronautical University, [larsenk2@my.erau.edu](larsenk2@my.erau.edu)  \nFollow this and additional works at: [https://commons.erau.edu/edt](https://commons.erau.edu/edt)  \n Part of the Artificial Intelligence and Robotics Commons, Navigation, Guidance, Control and Dynamics Commons, Numerical Analysis and Scientific Computing Commons, and the Other Aerospace Engineering Commons  \nScholarly Commons Citation  \nLarsen, Katharine, \"Machine Learning Methods for Hypervelocity Fragment Flyout Characterization\"(2025) . Doctoral Dissertations and Master 's Theses. 893.  \n[https://commons.erau.edu/edt/893](https://commons.erau.edu/edt/893)  \nThis Dissertation-Open Access is brought to you for free and open access by Scholarly Commons. It has been accepted for inclusion in Doctoral Dissertations and Master's Theses by an authorized administrator of Scholarly Commons. For more information, please contact [commons@erau.edu](commons@erau.edu).  \nFRAGMENT FLYOUT CHARACTERIZATION  \nMACHINE LEARNING METHODS FOR HYPERVELOCITY  \nBy  \nKatharine Elizabeth Larsen  \nA Dissertation Submitted to the Faculty of Embry-Riddle Aeronautical University In Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy in Aerospace Engineering  \nEmbry-Riddle Aeronautical University Daytona Beach, Florida  \nApril 2025  \n| Chair, Dr. Riccardo Bevilacqua |\n| --- |\n| Member, Dr. Troy Henderson |\n\n\n| Member, Dr. Richard Prazenica |\n| --- |\n| Member, Dr. Eric Coyle |\n\n\n| Graduate Program Coordinator, Dr. Sirish Namilae |\n| --- |\n| Dean of the College of Engineering, Dr. James W. Gregory |\n\nSenior Vice President for Academic Affairs and Provost,  \nDr. Lon Moeller  \nDate  \nTo my dog, Annie, and all my friends who came before her.  \nACKNOWLEDGMENTS  \nFirst and foremost, I thank my advisor, Dr. Riccardo Bevilacqua, for his supervision over this research and my graduate career. Dr. Bevilacqua has provided me with unimaginable opportunities, and without him this dissertation would not have been possible. Secondly, I thank my committee members, Dr. Richard Prazenica, Dr. Troy Henderson, and Dr. Eric Coyle, for their feedback and patience. I also owe a great debt of gratitude to Dr. Jhonathan O. Murcia Pi˜neros, Dr. Tahsinul H. Tasif, and Dr. Omkar Mulekar for their feedback and expertise throughout my research and time as a graduate student.  \nI have also found immense support in the ADvanced Autonomous MUltiple Spacecraft (ADAMUS) lab, led by Dr. Bevilacqua. My fellow researchers have become more than just peers, but I have found friends in all of them. The ADAMUS lab provided a collaborative work environment that allowed each of us to succeed in our own work.  \nFor providing financial support in the pursuit of my degree, I would like to acknowledge the United States Air Force Office of Scientific Research (award number FA9550-20-1-0200), the SMART Scholarship Program, and the Intuitive Machines and Columbia Sportswear Advancing Women in Technology Fellowship.  \nI am forever grateful for my family: my mom, dad, and brother, Erik. I would not be the person I am without you. Finally, I thank my fianc´e, John, and our dog, Annie, for giving me a home to escape to at the end of the day. While Annie’s Frisbee-fixation hasn’t exactly helped, your undying support means the world to me. Thank you for believing in me even when I failed to do so myself.  \nIt would be impossible to name everyone who supported me throughout this process, but to all my friends and family, I thank you for a sense of normality in the crazy world of academic research.  \nABSTRACT  \nResulting from breakup events, such as collisions and explosions, hypervelocity fragments create potential hazards for both terrestrial and on-orbit environments, such as terrestrial weapons explosions and satellite breakup events, respectively. ","cbCaibqpT4PIVHh8","https://ap.wps.com/l/cbCaibqpT4PIVHh8","pdf",14216745,1,131,"English","en",105,"# Abstract\n## Problem and motivation\n## Proposed machine learning approaches\n## Gaussian mixture models and k-nearest neighbors\n## Neural network prediction pipeline","[{\"question\":\"Why is hypervelocity fragment characterization important?\",\"answer\":\"Hypervelocity fragments from collisions and explosions create hazards for terrestrial and on-orbit environments. Accurate characterization helps avoid unnecessary damage.\"},{\"question\":\"What limitations exist in publicly available on-orbit breakup datasets?\",\"answer\":\"Available datasets based on two-line elements are limited and often exclude pre-detonation parent-body conditions and information about smaller fragments, with uncertainties that vary by dataset.\"},{\"question\":\"Which machine learning methods are proposed in the dissertation?\",\"answer\":\"The work proposes Gaussian mixture models and k-nearest neighbors regression to estimate fragment spatial distribution and counts, and neural networks to predict the locations of debris fragments after an explosion.\"}]","Machine Learning Methods for Hypervelocity Fragment Flyout Characterization - A Dissertation | PDF",1785736053,330,{"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},"machine-learning-methods-for-hypervelocity-fragment-flyout-characterization-a-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/machine-learning-methods-for-hypervelocity-fragment-flyout-characterization-a-dissertation/121517/",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 is hypervelocity fragment characterization important?","Question",{"text":75,"@type":76},"Hypervelocity fragments from collisions and explosions create hazards for terrestrial and on-orbit environments. Accurate characterization helps avoid unnecessary damage.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What limitations exist in publicly available on-orbit breakup datasets?",{"text":80,"@type":76},"Available datasets based on two-line elements are limited and often exclude pre-detonation parent-body conditions and information about smaller fragments, with uncertainties that vary by dataset.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning methods are proposed in the dissertation?",{"text":84,"@type":76},"The work proposes Gaussian mixture models and k-nearest neighbors regression to estimate fragment spatial distribution and counts, and neural networks to predict the locations of debris fragments after an explosion.","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"]