[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125265-en":3,"doc-seo-125265-105":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":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},125265,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Machine Learning Applications for Space Operations - Executive Summary","Machine Learning Applications for Space Operations examines how to improve satellite communications resilience in a contested radio-frequency environment. The study uses digitized RF transmissions to develop and train machine-learning interference detectors in a cloud-enabled workflow, then evaluates model deployment potential to an austere tactical edge such as a ship. Feedforward autoencoders are shown to identify RF interference across varying signal-to-noise ratios and classify corrupted-signal statistics. Additional architectures like LSTM and CNN are assessed for their ability to capture temporal features, supporting autonomous event-driven communication operations and rapid spacecraft reorientation for link recovery.","Calhoun: The NPS Institutional Archive  \nDSpace Repository  \nNPS Scholarship Publications  \n\n| 2024-04-16\u003Cbr>Machine Learning Applications for Space Operations\u003Cbr>Lan, Wenschel; Karpenko, Mark\u003Cbr>Monterey, CA; Naval Postgraduate School |\n| --- |\n| [https://hdl.handle.net/10945/73595](https://hdl.handle.net/10945/73595) |\n\nThis publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.  \nDownloaded from NPS Archive: Calhoun  \nMONTEREY, CALIFORNIA  \nMACHINE LEARNING APPLICATIONS FOR SPACE  \nOPERATIONS  \nEXECUTIVE SUMMARY  \nPrincipal Investigator (PI): Dr. Wenschel Lan, Space Systems Academic Group (SSAG)  \nCo-Principal Investigator (co-PI): Dr. Mark Karpenko, Mechanical and Aerospace Engineering  \nAdditional Researcher(s): Mr. Ron Phelps, SSAG  \nStudent Participation: LT Rorey Garnett, USN, SSAG; Capt Jason Turdo, USMC, SSAG; Maj Paolo Amorim dos Reis Carvalho, Brazilian Air Force, SSAG  \nPrepared for:  \nTopic Sponsor Lead Organization: N2/N6-Information Warfare  \nTopic Sponsor Name(s): LT Blake Wilson USN, N6 CS Current Operations Officer  \nTopic Sponsor Contact Information: 808-474-3451, [blake.l.wilson@navy.mil](blake.l.wilson@navy.mil)  \nProject Summary  \nDue to the increasingly contested radio frequency (RF) environment, new approaches for satellite communications (SATCOM) interference detection and identification are needed. One approach is to apply machine-learning (ML) techniques, which can be applied on both the ground and space segments. This study focuses on exploring applications that can be supported by high-power computing, cloud-enabled services, and embedded ML hardware at the tactical edge. This study uses digitized RF transmissions to support the development of ML concepts for RF interference detection and identification. Due to the memory requirements for RF waveforms, the Cloud environment Azure was chosen to process the digitized waveforms and train the ML interference detectors. Azure shows promise in transitioning ML models to an austere environment (i.e., a ship) for processing large data sets. In this application, it was discovered that feedforward autoencoders can be used to quickly and correctly identify RF interference applied at various signal-to-noise ratios (SNRs). The statistic of corrupted signals may be classified to determine the specific type of interface that has been applied. Other ML architectures, such as long-short-term memory (LSTM) and convolutional neural networks (CNNs) are also applicable as they can process temporal features differently than an autoencoder network. Upon detection of jamming or signal degradation, it may be necessary to steer a SATCOM system to reestablish degraded and/or broken links. This aspect can be handled by performing a rapid spacecraft reorientation maneuver. The current state of practice involves developing appropriate maneuver on the ground for uplink and execution on board the vehicle. To establish autonomy of operation, a concept for on-orbit (edge) command generation using neural networks was demonstrated that can support event-driven and autonomous operations for communication applications that benefit the warfighter.  \nKeywords: machine learning, radio frequency, RF, interference detection, space communications, on-orbit processing, tactical edge processing  \nBackground  \nCurrently, RF interference detection for the space-to-ground link often requires extensive time-consuming site surveying to characterize the RF environment of the ground site, and these methods also require the use of spectrum analyzers on-site to visualize anomalies. Other figures of merit, such as SNR and bit error rate, are also used to assess the quality of the link. Current systems are labor-intensive because human operators are needed to evaluate frequency-use requests and interference reports. This bottleneck reduces command and control capability with respect t","cbCaifZsaj3Onyam","https://ap.wps.com/l/cbCaifZsaj3Onyam","pdf",284543,1,6,"English","en",105,"# Executive Summary\n## Project Summary\n## Background","[{\"question\":\"What problem does the study address in space operations?\",\"answer\":\"The study targets the need for faster, less labor-intensive detection and identification of satellite communications interference in a contested RF environment.\"},{\"question\":\"How is machine learning applied to interference detection?\",\"answer\":\"Digitized RF transmissions are processed to train ML models that detect anomalous signals and classify corrupted-signal statistics, including using feedforward autoencoders trained across multiple SNR levels.\"},{\"question\":\"What deployment and autonomy capabilities does the research explore?\",\"answer\":\"The research evaluates cloud-based training and the promise of transitioning ML models to an austere tactical edge, and it demonstrates an on-orbit (edge) neural-network approach for event-driven autonomous command generation.\"}]","Machine Learning Applications for Space Operations - Executive Summary | PDF",1785897798,15,{"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-applications-for-space-operations-executive-summary","",{"@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-applications-for-space-operations-executive-summary/125265/",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","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address in space operations?","Question",{"text":75,"@type":76},"The study targets the need for faster, less labor-intensive detection and identification of satellite communications interference in a contested RF environment.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is machine learning applied to interference detection?",{"text":80,"@type":76},"Digitized RF transmissions are processed to train ML models that detect anomalous signals and classify corrupted-signal statistics, including using feedforward autoencoders trained across multiple SNR levels.",{"name":82,"@type":73,"acceptedAnswer":83},"What deployment and autonomy capabilities does the research explore?",{"text":84,"@type":76},"The research evaluates cloud-based training and the promise of transitioning ML models to an austere tactical edge, and it demonstrates an on-orbit (edge) neural-network approach for event-driven autonomous command generation.","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},[93,97,101,105,110,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]