[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118713-en":3,"doc-seo-118713-105":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},118713,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Machine Learning in Orbit Estimation: a Survey","Machine Learning in Orbit Estimation: a Survey reviews how data-driven methods improve orbit determination, orbit prediction, and thermospheric density modeling for resident space objects. The paper motivates the need for better tracking and collision-avoidance support due to limitations of physics-based approaches that yield kilometer-scale errors over multi-day forecasts. It explains EKF-based orbit determination, contrasts analytical and numerical orbit prediction limits, and highlights drag-related uncertainty tied to atmospheric density estimation. The survey summarizes current research directions and applications of deep learning.","arXiv :2207 .08993v1 [ astro-ph .EP] 19 Jul 2022  \nMachine Learning in Orbit Estimation: a Survey  \nFrancisco M. Caldas ∗ and Cláudia Soares †  \nNOVA School of Science and Technology, Caparica, Portugal  \nSince the late ’50s, when the first artificial satellite was launched, the number of resident space objects (RSOs) has steadily increased. It is estimated that around 1 Million objects larger than 1 cm are currently orbiting the Earth, with only 30,000, larger than 10 cm, presently being tracked. To avert a chain reaction of collisions, termed Kessler Syndrome [1], it is indispensable to accurately track and predict space debris and satellites’ orbit alike. Current physics-based methods have errors in the order of kilometres for 7 days predictions, which is insufficient when considering space debris that have mostly less than 1 meter. Typically, this failure is due to uncertainty around the state of the space object at the beginning of the trajectory, forecasting errors in environmental conditions such as atmospheric drag, as well as specific unknown characteristics such as mass or geometry of the RSO. Leveraging datadriven techniques, namely machine learning, the orbit prediction accuracy can be enhanced:  \nby deriving unmeasured objects’ characteristics, improving non-conservative forces’ effects, and by the superior abstraction capacity that Deep Learning models have of modelling highly complex non-linear systems. In this survey, we provide an overview of the current work being done in this field.  \nI. Introduction  \nIt is estimated that more than 36,000 objects larger than 10 centimetres, and millions of smaller pieces, exist in Earth’s orbit [2] . To safeguard active spacecraft, it is necessary to accurately determine where each Resident Space Object (RSO) is, and where it will be, at all times. To create such a complex body of knowledge, the larger problem of orbit estimation is divided into smaller problems, each one largely complex but with a specific goal in mind. In this review we observe three main sub-problems: Orbit Determination, Orbit Prediction and Thermospheric Mass Density.  \n• Orbit Determination (OD): the OD is the determination of the orbit of the object based on observations. The Extended Kalman Filter [3](EKF) is the de facto standard for orbit determination in real-world scenarios. The accuracy of this process depends on the amount of sequential observations used to determine the orbit, and the type of observation, e.g., laser ranging and GPS tracking is far more precise than optical observations. The output  \n∗ PhD. Student, NOVA LINCS, [f.caldas@fct.unl.pt](f.caldas@fct.unl.pt)[ ](f.caldas@fct.unl.pt)†Professor, NOVA LINCS, [claudia.soares@fct.unl.pt](claudia.soares@fct.unl.pt)  \nof this method is commonly a Gaussian probability distribution of the orbit of the object, usually represented through a vector consisting of the object’s estimated position and velocity and a covariance matrix reflecting the uncertainty. Currently, this process is limited by the assumptions of the EKF, by lack of knowledge in RSO’s shape and attitude and dynamic model simplifications, which we will further examine in Section III.  \n• Orbit Prediction (OP): Orbit Prediction is the process of predicting the future position and associated uncertainty of any given RSO. Two method families exist for OP: one pursuing analytical solutions, with the other exploiting numerical approximations. Numerical methods are time-consuming but precise, while the analytical methodologies are simpler and faster. To be tractable, these algorithms hold simplifying assumptions that hinder accuracy [4] . Each method is limited by OD in the sense that a orbital state with high uncertainty will necessarily evolve to have an inaccurate orbit prediction. When used in a Collision Avoidance scheme, this process is used to propagate the state of the RSO until the time of closest approach (TCA) to any actively monitored satellite. The current limitations in orbit pre","cbCaikIgjBS0kMTN","https://ap.wps.com/l/cbCaikIgjBS0kMTN","pdf",1279936,1,24,"English","en",105,"# Introduction\n## Orbit Determination (OD)\n## Orbit Prediction (OP)\n## Thermospheric Density Mass\n## Input/Output Summary for Each Task\n## Survey Scope and Review Structure","[{\"question\":\"Why is improved orbit estimation important for space safety?\",\"answer\":\"Accurate tracking and prediction of satellites and space debris helps avoid collision cascades such as Kessler Syndrome. Physics-based methods can leave large prediction errors that are inadequate for objects with sub-meter sizes.\"},{\"question\":\"What are the main sub-problems covered in the survey?\",\"answer\":\"The survey divides orbit estimation into Orbit Determination, Orbit Prediction, and Thermospheric Mass Density modeling, each with its own sources of complexity and uncertainty.\"},{\"question\":\"How do machine learning methods contribute to orbit estimation accuracy?\",\"answer\":\"Machine learning can infer unmeasured object characteristics, better model non-conservative forces, and leverage deep learning’s ability to represent complex nonlinear dynamics, improving prediction quality compared with simplified physics models.\"}]","Machine Learning in Orbit Estimation: a Survey | PDF",1785719859,60,{"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-in-orbit-estimation-a-survey","",{"@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-in-orbit-estimation-a-survey/118713/",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},"Why is improved orbit estimation important for space safety?","Question",{"text":76,"@type":77},"Accurate tracking and prediction of satellites and space debris helps avoid collision cascades such as Kessler Syndrome. Physics-based methods can leave large prediction errors that are inadequate for objects with sub-meter sizes.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What are the main sub-problems covered in the survey?",{"text":81,"@type":77},"The survey divides orbit estimation into Orbit Determination, Orbit Prediction, and Thermospheric Mass Density modeling, each with its own sources of complexity and uncertainty.",{"name":83,"@type":74,"acceptedAnswer":84},"How do machine learning methods contribute to orbit estimation accuracy?",{"text":85,"@type":77},"Machine learning can infer unmeasured object characteristics, better model non-conservative forces, and leverage deep learning’s ability to represent complex nonlinear dynamics, improving prediction quality compared with simplified physics models.","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},[94,98,102,106,110,115,120,123,128,131,135],{"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":29,"slug":109},5,"Comic","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":107,"slug":138},19,"General","general"]