[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119484-en":3,"doc-seo-119484-105":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},119484,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Synthetic satellite telemetry data for machine learning","Labeled data are essential for most machine learning tasks, yet satellite telemetry—often containing thousands of housekeeping parameters—typically lacks holistic, reproducible labels and must be manually annotated by experts, which is costly and time-consuming. Modern satellites generate massive volumes of telemetry-like signals, but anomalies and nominal behavior are difficult to fully characterize for training. A synthetic satellite telemetry data library is implemented to generate diverse telemetry-like data, inject well-defined anomalies, and provide corresponding labels, enabling reproducible training, validation, testing, and model comparison.","CEAS Space Journal  \n[https://doi.org/10.1007/s12567-024-00589-1](https://doi.org/10.1007/s12567-024-00589-1)  \nSynthetic satellite telemetry data for machine learning  \nClemens Schefels1 · Leonard Schlag1 · Kathrin Helmsauer1  \nReceived: 28 March 2024 / Revised: 18 December 2024 / Accepted: 19 December 2024 © The Author(s) 2025  \nAbstract  \nFor many machine learning tasks, labeled data are crucial. Even though there are methods that can be trained with data with only few labels, most of the tasks require many labels. In satellite operations, a huge amount of data are generated by the telemetry parameters of a satellite that keep track of its status. Modern satellites collect telemetry data of thousands of parameters. For example, the GRACE Follow-On satellites, operated by the German Space Operations Center (GSOC) at the German Aerospace Center (DLR), define about 80,000 unique housekeeping parameters each. However, all these telemetry data lack a complete/holistic set of labels. These data are usually unpredictable, hard to reproduce, and very diverse. As a consequence, expert knowledge is necessary to label these data, e.g., with anomalies. Moreover, labeling data by hand can be very time-consuming and, therefore, expensive. To overcome these obstacles, we implemented a synthetic satellite telemetry data library that is able to (a) generate a large variety of telemetry-like data,(b) add a plethora of well-defined anomalies to these data, and (c) deliver the labels for these injected anomalies. With these data, we are now able to train, validate, and test our machine learning models. Furthermore, we can compare different models with reproducible data. Since satellite telemetry data are often strictly confidential, we can share these synthetic data easily with our research partners.  \nKeywords Satellite telemetry · Machine learning · Anomaly detection · Synthetic data · Labeled data · Software development  \n1 Introduction  \nNowadays, the usage of Machine Learning (ML) software tools is routine in many disciplines, also in the space domain. These tools are able to analyze huge amount of data and unburden humans from monotonous tasks. Many of the ML software tools use statistical methods to learn from examples, i.e., from labeled data. In our field of expertise—satellite operations—anomaly detection in satellite telemetry data is a typical use case. Here, ML software tools are scanning through huge amount of telemetry data and check for anomalous behavior, which is traditionally a task of system engineers. However, to implement such ML tools, labeled data is needed. Those labels, which indicate nominal and anomalous data, represent the examples from which the tool learns. With such a data set, the ML model of the tool can be trained, so that it learns how nominal data looks like and is  \n* Clemens Schefels [clemens.schefels@dlr.de](clemens.schefels@dlr.de)  \n1 German Aerospace Center (DLR), German Space Operations Center (GSOC), 82234 Weßling, Bavaria, Germany  \nthen able to distinguish anomalous from nominal behavior. In general, huge amounts of satellite data are already available but, most of the time, they lack labels. And since labeling data by hand is a very time-consuming and therefore expensive task, the need for an automatic solutions is given. As described in Sect. 2, some labeled telemetry data sets can be found online. However, these data sets are the results of former projects and built for a specific use case. They may not completely cover the need of new projects and may need to be adapted; again a time-consuming task. Therefore, amore customizable solution is needed.  \nIn this article, we present our Python library for the generation of synthetic satellite telemetry data. In particular, we focus on its flexible and generic architecture. With this library, we can create data sets for ML training that contain various types of telemetry data. Inspired by the possibility to inject different kinds of anomalies into t","cbCailugMY3t87zw","https://ap.wps.com/l/cbCailugMY3t87zw","pdf",1450664,1,13,"English","en",105,"# Introduction\n## Related work\n## Synthetic telemetry data library\n## Use cases and application\n## Proofs of concept\n## Future work\n# Summary and conclusion","[{\"question\":\"Why are labeled satellite telemetry data needed for machine learning anomaly detection?\",\"answer\":\"Machine learning anomaly detection models require labels that distinguish nominal from anomalous behavior, which serve as training examples. Without labels, ML tools cannot learn what “normal” looks like or detect deviations reliably.\"},{\"question\":\"What problems does the proposed synthetic telemetry library address?\",\"answer\":\"Real satellite telemetry often lacks complete labels, is hard to reproduce, and is diverse, making manual expert labeling expensive and time-consuming. The library aims to overcome unpredictability and reduce labeling effort by generating labeled synthetic datasets.\"},{\"question\":\"How does the library create usable training data and enable model development?\",\"answer\":\"It generates large varieties of telemetry-like data, injects many well-defined anomalies, and delivers labels for each injected anomaly. These datasets support training, validation, and testing of machine learning models, plus reproducible comparisons across different model versions.\"}]","Synthetic satellite telemetry data for machine learning | PDF",1785724563,33,{"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},"synthetic-satellite-telemetry-data-for-machine-learning","",{"@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/synthetic-satellite-telemetry-data-for-machine-learning/119484/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are labeled satellite telemetry data needed for machine learning anomaly detection?","Question",{"text":75,"@type":76},"Machine learning anomaly detection models require labels that distinguish nominal from anomalous behavior, which serve as training examples. Without labels, ML tools cannot learn what “normal” looks like or detect deviations reliably.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What problems does the proposed synthetic telemetry library address?",{"text":80,"@type":76},"Real satellite telemetry often lacks complete labels, is hard to reproduce, and is diverse, making manual expert labeling expensive and time-consuming. The library aims to overcome unpredictability and reduce labeling effort by generating labeled synthetic datasets.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the library create usable training data and enable model development?",{"text":84,"@type":76},"It generates large varieties of telemetry-like data, injects many well-defined anomalies, and delivers labels for each injected anomaly. These datasets support training, validation, and testing of machine learning models, plus reproducible comparisons across different model versions.","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"]