[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81992-en":3,"doc-seo-81992-105":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":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":13,"seo_description":14,"update_tm":28,"read_time":29},81992,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Toward Deployable Satellite Anomaly Detection: A Benchmark Study on Large-Scale ESA-ADB Telemetry","Satellite anomaly detection is vital for ensuring mission reliability and spacecraft health, but it remains difficult because telemetry data are high-dimensional, irregular, and strongly imbalanced. This paper delivers a systematic benchmark on the large-scale ESA-ADB dataset, comparing supervised and unsupervised methods across two mission settings with different temporal scales. It evaluates Multiscale CNN, GCN, and GAT versus ECOD and Elliptic Envelope, and studies runtime and scalability. Results highlight a detection-capability versus operational-efficiency trade-off to guide practical deployment.","Toward Deployable Satellite Anomaly Detection: A Benchmark Study on Large-Scale ESA-ADB  \nTelemetry  \nAndrea Nguyen†, Dafne Rozenberg†, Yeying Zhu‡, and Peng Hu§ *†Faculty of Science, University of Manitoba, Winnipeg, Canada ‡Dept. of Statistics and Actuarial Science, University of Waterloo, Waterloo, Canada  \n§ Dept. of Electrical and Computer Engineering, University of Manitoba, Winnipeg, Canada {nguye75, [rozenbed](rozenbed}@myumanitoba.ca)[}](rozenbed}@myumanitoba.ca)[@myumanitoba.ca](rozenbed}@myumanitoba.ca), [yeying.zhu@uwaterloo.ca](yeying.zhu@uwaterloo.ca), *[peng.hu@umanitoba.ca](peng.hu@umanitoba.ca)  \narXiv :2607 .07335v 1 [ cs .CE] 8 Jul 2026  \nAbstract—Satellite anomaly detection is essential for maintaining mission reliability and spacecraft health, yet remains challenging due to the high-dimensional, irregular, and imbalanced nature of spacecraft telemetry data. This paper presents a systematic benchmark study evaluating supervised and unsupervised anomaly detection approaches on the large-scale ESA-ADB dataset across two mission settings of varying temporal scales. Supervised models, including Multiscale Convolutional Neural Networks (Multiscale CNN), Graph Convolutional Networks (GCN), and Graph Attention Networks (GAT), are compared against unsupervised methods, namely Elliptic Envelope (EE) and Empirical Cumulative Distribution Function-based Outlier Detection (ECOD). Beyond detection performance, we rigorously analyze computational runtime and scalability, which are critical for practical deployment in spacecraft operations. Results show that supervised models achieve stronger overall performance, while unsupervised methods offer competitive precision with significantly lower computational overhead. These findings underscore a fundamental trade-off between detection capacity and operational efficiency, offering practical guidance for mission engineers designing scalable satellite health monitoring systems.  \nI. INTRODUCTION  \nSpacecraft are complex and expensive systems consisting of thousands of telemetry channels that continuously monitor variables such as temperature, radiation levels, power consumption, instrumentation status, and computational activity [1] . As space missions increase in complexity and scale, monitoring and maintaining spacecraft health has become increasingly challenging for spacecraft operations engineers. Detecting anomalies in satellite telemetry time-series data is therefore essential for ensuring the safe, reliable, and continuous operation of scientific, communication, observation, and navigation satellites.  \nThe primary goal of anomaly detection (AD) is to improve automated health monitoring systems by identifying unusual behavior, system faults, and rare events within large-scale multivariate telemetry streams. However, anomaly detection in spacecraft telemetry remains difficult because the data are high-dimensional, noisy, irregular, and highly imbalanced  \nWe acknowledge the support provided by the Natural Sciences and Engineering Research Council of Canada (NSERC), [funding reference number RGPIN-2022-03364] .  \n[2] . In practice, identifying anomalous events can be timeconsuming and dependent on human expertise [3] . As a result, many spacecraft monitoring systems still rely on thresholdbased alarm mechanisms that trigger when telemetry values exceed predefined limits. Failure to detect critical anomalies in time may result in partial or complete spacecraft loss [1] .  \nMachine learning (ML) approaches have shown strong potential for improving anomaly detection in satellite telemetry [2] . In [2], the authors leverage the newly released ESA-ADB benchmark to evaluate supervised and unsupervised anomaly detection approaches on two mission datasets of varying temporal scales: ESA-Mission 1 (84 months) and ESA-Mission 2 (21 months) . For supervised learning, three deep learning (DL) architectures are investigated: Multiscale Convolutional Neural Networks (Multiscale CNN), Gr","cbCaiaPHopK7BXKU","https://ap.wps.com/l/cbCaiaPHopK7BXKU","pdf",250013,5,1,6,"English","en",105,"# Abstract\n# Introduction\n# Related Work","[{\"question\":\"What challenge does the paper address in satellite anomaly detection?\",\"answer\":\"It addresses the difficulty of detecting anomalies in high-dimensional, irregular, and highly imbalanced spacecraft telemetry time series while maintaining reliable mission operation.\"},{\"question\":\"Which models are compared in the benchmark?\",\"answer\":\"Supervised models include Multiscale CNN, GCN, and GAT, while unsupervised methods include Elliptic Envelope (EE) and ECOD.\"},{\"question\":\"How does the paper evaluate practical deployability beyond accuracy?\",\"answer\":\"It analyzes computational runtime and scalability, emphasizing how these factors affect onboard or ground-segment deployment and operational efficiency.\"}]",1784177457,15,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"toward-deployable-satellite-anomaly-detection-a-benchmark-study-on-large-scale-esa-adb-telemetry","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"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/toward-deployable-satellite-anomaly-detection-a-benchmark-study-on-large-scale-esa-adb-telemetry/81992/",4,{"url":52,"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":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-29","2026-07-16",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 challenge does the paper address in satellite anomaly detection?","Question",{"text":76,"@type":77},"It addresses the difficulty of detecting anomalies in high-dimensional, irregular, and highly imbalanced spacecraft telemetry time series while maintaining reliable mission operation.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which models are compared in the benchmark?",{"text":81,"@type":77},"Supervised models include Multiscale CNN, GCN, and GAT, while unsupervised methods include Elliptic Envelope (EE) and ECOD.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the paper evaluate practical deployability beyond accuracy?",{"text":85,"@type":77},"It analyzes computational runtime and scalability, emphasizing how these factors affect onboard or ground-segment deployment and operational efficiency.","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":25},{"code":4,"msg":5,"data":93},[94,98,102,106,110,114,119,122,127,130,134],{"id":21,"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":20,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Comic",60,"comic",{"id":22,"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":20,"slug":137},19,"General","general"]