[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119665-en":3,"doc-seo-119665-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},119665,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Machine learning techniques to support the classification of satellite conjunction events - Master Thesis","The ever-increasing number of objects in Earth’s orbit, combining active satellites and space debris, threatens space safety and collision avoidance. Conjunction Data Messages (CDMs) generated by orbit determination and close-approach screening provide key information that operators use to decide whether to implement risk-mitigation actions. This work applies machine learning to classify conjunction events into high-risk versus low-risk categories, including a feature parametric study and new parameter introduction. A structured selection of training parameters combines physical reasoning and ML analysis, then addresses class imbalance via oversampling, undersampling, and SMOTE, together with risk-threshold-specific algorithms and a filtering strategy for unreliable estimates.","Machine learning techniques to support the classification of satellite conjunction events  \nTesi di Laurea Magistrale in  \nSpace Engineering-Ingegneria Spaziale  \nAuthor: Alberto Blasco  \nStudent ID: 969341  \nAdvisor: Juan Luis Gonzalo Gómez  \nCo-advisors: Camilla Colombo  \nAcademic Year: 2021-22  \nCopyright© April 2023 by Alberto Blasco.  \nAll rights reserved.  \nThis content is original, written by the Author, Alberto Blasco. All the non-originals information, taken from previous works, are specified and recorded in the Bibliography.  \nWhen referring to this work, full bibliographic details must be given, i.e.  \nBlasco Alberto,“Machine learning techniques to support the classification of satellite conjunction events”. 2023, Politecnico di Milano, Master Thesis in Space Engineering, Supervisor: Juan Luis Gonzalo Gómez, Co-supervisor: Camilla Colombo.  \ni  \nAbstract  \nThe ever-increasing number of objects in Earth’s orbit, composed by both active satellites and space debris, is becoming a problem for space safety. In recent years, many resources have been gathered to tackle this issue, from active debris removal to international agreements for safety in space. A lot of effort has been put into assisting collision avoidance activities through theoretical studies and space surveillance and tracking system services. Conjunction data messages are created by the orbit determination process, the objects database maintenance and the close approach screening, and contain the main information about conjunctions. They are constantly sent to the satellite owner/operator to decide whether to plan risk mitigation measures. To support this process and increase automation, in 2019 ESA publicly released a collection of CDMs, collected between 2015 and 2019, to propose a challenge consisting in improving their collision risk estimation through machine learning methods. This work focuses on using machine learning models to classify conjunction events as high risk or low risk. A parametric study on the influencing features appearing in CDMs is presented together with the introduction of new parameters. A selection of the parameters to use for machine learning training is then performed, by both a physical analysis and a ML analysis. This process has shown a considerable improvement over the use of raw data. The publicly available data is then treated to account for the imbalance by combining oversampling, undersampling, SMOTE and specific machine learning algorithms. For each one of the most commonly used risk thresholds, a machine learning algorithm is presented. For all the thresholds selected, the solution found seems to improve the current predictions. A filtering of non reliable events in term of risk estimation is also proposed, which allows for a great accuracy improvement, while maintaining a large portion of data.  \nKeywords: satellite conjunction events; collision risk; machine learning; classification; ESA collision avoidance challenge; collision avoidance  \nAbstract in lingua italiana  \nIl numero sempre crescente di oggetti orbitanti la Terra, siano satelliti attivi o detriti spaziali, sta diventando una questione di massima importanza per la sicurezza spaziale. Negli ultimi anni, molte risorse sono state impiegate per contrastare questa problematica crescente, dalle operazioni di rimozione attiva dei detriti ad accordi internazionaliriguardanti la sicurezza nello spazio. Gran parte dello sforzo è stato rivolto all’assistenza delle attività per evitare potenziali collisioni, grazie a studi teoretici e a sistemi per il monitoraggio orbitale. I \"conjunction data messages\" vengono creati attraverso il processo di determinazione delle orbite, il mantenimento di un database degli oggetti orbitanti e lo screening degli incontri ravvicinati, e contengono le più importanti informazioniriguardanti le potenziali collisioni. Questi messaggi vengono costantemente inviati agli operatori dei satelliti in modo da permettere la decisione per l’eventu","cbCaibMQCrEFtRHC","https://ap.wps.com/l/cbCaibMQCrEFtRHC","pdf",1400011,1,100,"English","en",105,"# Contents\n## Introduction\n## Background\n### Space environment\n### Space debris mitigation guidelines\n### Collision avoidance activities\n## State of the Art","[{\"question\":\"What problem does the thesis address in satellite safety?\",\"answer\":\"It targets the growing collision risk in Earth orbit by improving how conjunction events are evaluated and classified for collision avoidance decisions.\"},{\"question\":\"How are conjunction events represented for the machine learning models?\",\"answer\":\"They are represented using Conjunction Data Messages (CDMs), which include the main information produced by orbit determination, object database maintenance, and close-approach screening.\"},{\"question\":\"Which methods are used to handle class imbalance in the training data?\",\"answer\":\"The work treats the publicly available data to account for imbalance using oversampling, undersampling, SMOTE, and specific machine learning algorithms.\"}]","Machine learning techniques to support the classification of satellite conjunction events - Master Thesis | PDF",1785725570,252,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-techniques-to-support-the-classification-of-satellite-conjunction-events-master-thesis","",{"@graph":36,"@context":86},[37,54,69],{"@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-techniques-to-support-the-classification-of-satellite-conjunction-events-master-thesis/119665/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the thesis address in satellite safety?","Question",{"text":76,"@type":77},"It targets the growing collision risk in Earth orbit by improving how conjunction events are evaluated and classified for collision avoidance decisions.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How are conjunction events represented for the machine learning models?",{"text":81,"@type":77},"They are represented using Conjunction Data Messages (CDMs), which include the main information produced by orbit determination, object database maintenance, and close-approach screening.",{"name":83,"@type":74,"acceptedAnswer":84},"Which methods are used to handle class imbalance in the training data?",{"text":85,"@type":77},"The work treats the publicly available data to account for imbalance using oversampling, undersampling, SMOTE, and specific machine learning algorithms.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]