[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127673-en":3,"doc-seo-127673-105":31,"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},127673,962084925636,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Improving Thermospheric Density Predictions in Low-Earth Orbit With Machine Learning - Research Article","Thermospheric density is a major uncertainty source for determining satellite position and velocity in low-Earth orbit, affecting space traffic management, collision avoidance, re-entry prediction, orbital lifetime analysis, and space object cataloging. The study evaluates empirical neutral-density models such as NRLMSISE-00 and JB-08 against black-box machine learning models trained on precise orbit determination-derived density data. Using identical inputs, machine learning reduces mean absolute percentage error from about 40–60% to roughly 20% and provides the open-source Karman framework for ML-ready data ingestion, preprocessing, training, and benchmarking across altitudes, locations, times, and solar/geomagnetic conditions.","RESEARCH ARTICLE  \n10.1029/2023SW003652  \nGiacomo Acciarini and Edward Brown contributed equally to this work.  \nKey Points:  \n• Machine learning (ML) models can significantly outperform existing physics-based thermospheric neutral density models on exactly the same inputs  \n• ML models can improve over NRLMSISE-00 and JB-08 empirical density models by 61% and 39% respectively in the mean absolute percentage error  \n• The software allows the creation of ML-ready data for training and benchmarking new models, supporting solar irradiance and geomagnetic data  \nCorrespondence to:  \nG. Acciarini and E. Brown, giacomo.acciarini@gmail.com; [edward.j.e.brown@gmail.com](edward.j.e.brown@gmail.com)  \nCitation:  \nAcciarini, G., Brown, E., Berger, T., Guhathakurta, M., Parr, J., Bridges, C., & Baydin, A. G. (2024). Improving thermospheric density predictions in low-Earth orbit with machine learning. Space Weather, 22, e2023SW003652 .  \n[https://doi.org/10.1029/2023SW003652](https://doi.org/10.1029/2023SW003652)  \nReceived 22 JUL 2023 Accepted 21 JAN 2024  \nAuthor Contributions:  \nConceptualization: Giacomo Acciarini, Edward Brown, Madhulika Guhathakurta, Atılım Güneş Baydin  \nFunding acquisition: Madhulika Guhathakurta, James Parr Investigation: Giacomo Acciarini, Edward Brown  \nMethodology: Giacomo Acciarini, Edward Brown  \nProject Administration: James Parr, Christopher Bridges  \nResources: Madhulika Guhathakurta  \nSoftware: Giacomo Acciarini, Edward Brown, Atılım Güneş Baydin  \n© 2024. The Authors.  \nThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.  \nImproving Thermospheric Density Predictions in Low-Earth Orbit With Machine Learning  \nGiacomo Acciarini1,2 , Edward Brown1,3,4 , Tom Berger5 , Madhulika Guhathakurta6, James Parr1, Christopher Bridges1,2, and Atılım Güneş Baydin1,7,8  \n1Trillium Technologies Inc., London, UK, 2Surrey Space Centre, University of Surrey, Guildford, UK, 3Computer Science Department, University of Cambridge, Cambridge, UK, 4Space Weather and Atmosphere Team, British Antarctic Survey, Cambridge, UK, 5Space Weather Center, CU Boulder, Boulder, CO, USA, 6NASA Headquarters, Washington DC, DC, USA, 7Department of Engineering Science, University of Oxford, Oxford, UK, 8Department of Computer Science, University of Oxford, Oxford, UK  \nAbstract Thermospheric density is one of the main sources of uncertainty in the estimation of satellites'position and velocity in low-Earth orbit. This has negative consequences in several space domains, including space traffic management, collision avoidance, re-entry predictions, orbital lifetime analysis, and space object cataloging. In this paper, we investigate the prediction accuracy of empirical density models (e.g., NRLMSISE-00 and JB-08) against black-box machine learning (ML) models trained on precise orbit determination-derived thermospheric density data (from CHAMP, GOCE, GRACE, SWARM-A/B satellites) . We show that by using the same inputs, the ML models we designed are capable of consistently improving the predictions with respect to state-of-the-art empirical models by reducing the mean absolute percentage error (MAPE) in the thermospheric density estimation from the range of 40%–60% to approximately 20% . Asa result of this work, we introduce Karman: an open-source Python software package developed during this study. Karman provides functionalities to ingest and preprocess thermospheric density, solar irradiance, and geomagnetic input data for ML readiness. Additionally, it facilitates developing and training ML models on the aforementioned data and benchmarking their performance at different altitudes, geographic locations, times, and solar activity conditions. Through this contribution, we offer the scientific community a comprehensive tool for comparing and enhancing thermospheric density models using ML techniques.","cbCaivngffWEqMY9","https://ap.wps.com/l/cbCaivngffWEqMY9","pdf",1986436,4,1,13,"English","en",105,"# Key Points\n# Abstract\n## Plain Language Summary\n# 1. Introduction","[{\"question\":\"How does machine learning improve thermospheric density prediction compared with empirical models?\",\"answer\":\"Machine learning models trained on precise orbit determination-derived density data outperform physics-based empirical models using the same inputs, reducing mean absolute percentage error substantially (e.g., 61% vs NRLMSISE-00 and 39% vs JB-08).\"},{\"question\":\"What inputs and data sources support the ML models in this study?\",\"answer\":\"The approach uses thermospheric density derived from precise orbit determination data from satellites such as CHAMP, GOCE, GRACE, and SWARM-A/B, along with solar irradiance and geomagnetic inputs for model readiness and benchmarking.\"},{\"question\":\"What is Karman and what does it enable for researchers?\",\"answer\":\"Karman is an open-source Python software package that ingests and preprocesses thermospheric density, solar irradiance, and geomagnetic data, then supports training and benchmarking machine learning models across altitudes, geographic locations, times, and solar activity conditions.\"}]","Improving Thermospheric Density Predictions in Low-Earth Orbit With Machine Learning - Research Article | PDF",1785940681,33,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"improving-thermospheric-density-predictions-in-low-earth-orbit-with-machine-learning-research-article","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/improving-thermospheric-density-predictions-in-low-earth-orbit-with-machine-learning-research-article/127673/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",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},"How does machine learning improve thermospheric density prediction compared with empirical models?","Question",{"text":76,"@type":77},"Machine learning models trained on precise orbit determination-derived density data outperform physics-based empirical models using the same inputs, reducing mean absolute percentage error substantially (e.g., 61% vs NRLMSISE-00 and 39% vs JB-08).","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What inputs and data sources support the ML models in this study?",{"text":81,"@type":77},"The approach uses thermospheric density derived from precise orbit determination data from satellites such as CHAMP, GOCE, GRACE, and SWARM-A/B, along with solar irradiance and geomagnetic inputs for model readiness and benchmarking.",{"name":83,"@type":74,"acceptedAnswer":84},"What is Karman and what does it enable for researchers?",{"text":85,"@type":77},"Karman is an open-source Python software package that ingests and preprocesses thermospheric density, solar irradiance, and geomagnetic data, then supports training and benchmarking machine learning models across altitudes, geographic locations, times, and solar activity conditions.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]