[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125524-en":3,"doc-seo-125524-105":30,"detail-sidebar-cat-0-en-105":95},{"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":4,"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},125524,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Machine learning-based anomaly detection for radio telescopes - Thesis","Machine learning-based anomaly detection for radio telescopes develops methods for identifying abnormal signals in radio astronomy observations, with emphasis on robust monitoring and real-time scientific data processing. The work uses radio astronomy data from the LOFAR telescope and evaluates unsupervised approaches based on representation learning, including variational autoencoders and nearest-neighbour concepts in latent space. Results include quantitative evaluation on simulated data and qualitative assessment using LOFAR measurements, covering both generic anomaly detection and radio-frequency interference detection.","UvA-DARE (Digital Academic Repository)  \nMachine learning-based anomaly detection for radio telescopes  \nMesarcik, M. B.  \nPublication date  \n2024  \nDocument Version  \nFinal published version  \nLink to publication  \nCitation for published version (APA):  \nMesarcik, M. B. (2024) . Machine learning-based anomaly detection for radio telescopes.[Thesis, fully internal, Universiteit van Amsterdam] .  \nGeneral rights  \nIt is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons) .  \nDisclaimer/Complaints regulations  \nIf you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: [https://uba.uva.nl/en/contact](https://uba.uva.nl/en/contact), or a letter to: Library of the University of Amsterdam, Secretariat, P.O. Box 19185, 1000 GD Amsterdam, The Netherlands. You will be contacted as soon as possible.  \nUvA-DARE is a service provided by the library of the University of Amsterdam ( [http](https://dare. uva. nl)[s](https://dare. uva. nl)[://dare. uva. nl](https://dare. uva. nl))  \nDownload date:27 Apr 2026  \nMachine learning-based anomaly detection for radio telescopes  \nMichael Mesarcik  \nMACHINE LEARNING-BASED ANOMALY DETECTION FOR RADIO TELESCOPES  \nmichael mesarcik  \nThis work was carried out in the ASCI graduate school.  \nASCI dissertation series number: 450  \nThis work is part of the “Perspectief” research programme “Efficient Deep Learning”(EDL, [https://efficientdeeplearning.nl](https://efficientdeeplearning.nl)), which is financed by the Dutch Research Council (NWO) domain Applied and Engineering Sciences (TTW) . The research makes use of radio astronomy data from the LOFAR telescope, which is operated by ASTRON (Netherlands Institute for Radio Astronomy), an institute belonging to the Netherlands Foundation for Scientific Research (NWO-I)  \nCopyright © 2024 Michael Mesarcik.  \nCover Design by: Tammy Joubert  \nThesis template: classicthesis by André Miede and Ivo Pletikosi´c. Printed and bound by Ipskamp printing  \nISBN: 978-94-6473-446-1  \nMachine learning-based anomaly detection for radio telescopes  \nACADEMISCH PROEFSCHRIFT  \nter verkrijging van de graad van doctor aan de Universiteit van Amsterdam op gezag van de Rector Magnificus [prof. dr. ir. P.P.C.C. Verbeek](prof. dr. ir. P.P.C.C. Verbeek)  \nten overstaan van een door het College voor Promoties ingestelde commissie, in het openbaar te verdedigen in de Agnietenkapel op woensdag 24 april 2024, te 16.00 uur  \ndoor Michael Benno Mesarcik geboren te ZAF  \nPromotiecommissie  \nPromotores:  \nCopromotores:  \nOverige leden:  \nprof. dr. R.V. van Nieuwpoort [prof. dr. ir. C.T.A.M. de Laat](prof. dr. ir. C.T.A.M. de Laat)  \n[dr. ir. A.J. Boonstra](dr. ir. A.J. Boonstra)[ ](dr. ir. A.J. Boonstra)[dr. E.B. Ranguelova](dr. E.B. Ranguelova)  \n[dr. P. Grosso](dr. P. Grosso)  \nprof. dr. P.T. Groth [prof. dr. ir. H. Corporaal](prof. dr. ir. H. Corporaal)[ ](prof. dr. ir. H. Corporaal)[prof. dr. A.M.M. Scaife](prof. dr. A.M.M. Scaife)[dr. B.A. Rowlinson](dr. B.A. Rowlinson)[ ](dr. B.A. Rowlinson)[prof. dr. ir. S.J. Wijnholds](prof. dr. ir. S.J. Wijnholds)  \nUniversiteit van Amsterdam  \nUniversiteit van Amsterdam  \nASTRON  \nNetherlands eScience Center  \nUniversiteit van Amsterdam  \nUniversiteit van Amsterdam Eindhoven University of Technology University of Manchester Universiteit van Amsterdam ASTRON  \nFaculteit der Natuurwetenschappen, Wiskunde en Informatica  \nTo vertebrae C4, C5 and C7, your support is appreciated.  \nCONTENTS  \n1 introduction 1  \n1.1 System health management in radio telescopes 3  \n1.2 Machine learning-based anomaly detection","cbCaieOLsrgemA80","https://ap.wps.com/l/cbCaieOLsrgemA80","pdf",45700959,1,155,"English","en",105,"# 1 introduction\n## 1.1 System health management in radio telescopes\n## 1.2 Machine learning-based anomaly detection\n## 1.3 Real time scientific data processing\n## 1.4 Thesis structure\n## 1.5 Author publications related to this thesis\n# 2 background\n## 2.1 The Low Frequency Array\n## 2.2 Machine learning in astronomy\n# 3 learning representations of radio astronomy spectrograms\n## 3.1 Introduction\n## 3.2 Data preparation\n## 3.3 Variational autoencoder architecture\n## 3.4 Model evaluation\n## 3.5 Results\n## 3.6 Conclusions and discussion\n# 4 nearest neighbour-based anomaly detection\n## 4.1 Introduction\n## 4.2 NLN: Nearest Latent Neighbours\n## 4.3 Experiments\n## 4.4 Ablation study\n## 4.5 Discussion and conclusions\n# 5 radio frequency interference detection\n## 5.1 Introduction\n## 5.2 Method\n## 5.3 Data selection and preprocessing\n## 5.4 Results","[{\"question\":\"Which telescope data does the thesis use for the anomaly-detection research?\",\"answer\":\"The research uses radio astronomy data from the LOFAR telescope for training and evaluation, with experiments comparing simulated datasets and LOFAR observations.\"},{\"question\":\"What learning approach is used to learn representations of radio astronomy spectrograms?\",\"answer\":\"A variational autoencoder (VAE) is used to learn representations, followed by quantitative evaluation on simulated data and qualitative evaluation using LOFAR data.\"},{\"question\":\"How does the thesis perform anomaly detection using nearest-neighbour concepts?\",\"answer\":\"It introduces a nearest-neighbour-based latent method (NLN: Nearest Latent Neighbours), formulates the problem in latent space, and evaluates performance with efficiency considerations and ablation experiments.\"},{\"question\":\"What additional task is addressed beyond general anomaly detection?\",\"answer\":\"Radio-frequency interference (RFI) detection is treated as a dedicated task, using a nearest-latent-neighbours approach adapted for RFI detection and assessed with tailored results and evaluation methodology.\"}]","Machine learning-based anomaly detection for radio telescopes - Thesis | PDF",1785899617,391,{"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":90,"head_meta":92,"extra_data":94,"updated_unix":28},"machine-learning-based-anomaly-detection-for-radio-telescopes-thesis","",{"@graph":36,"@context":89},[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-based-anomaly-detection-for-radio-telescopes-thesis/125524/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"Which telescope data does the thesis use for the anomaly-detection research?","Question",{"text":75,"@type":76},"The research uses radio astronomy data from the LOFAR telescope for training and evaluation, with experiments comparing simulated datasets and LOFAR observations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What learning approach is used to learn representations of radio astronomy spectrograms?",{"text":80,"@type":76},"A variational autoencoder (VAE) is used to learn representations, followed by quantitative evaluation on simulated data and qualitative evaluation using LOFAR data.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis perform anomaly detection using nearest-neighbour concepts?",{"text":84,"@type":76},"It introduces a nearest-neighbour-based latent method (NLN: Nearest Latent Neighbours), formulates the problem in latent space, and evaluates performance with efficiency considerations and ablation experiments.",{"name":86,"@type":73,"acceptedAnswer":87},"What additional task is addressed beyond general anomaly detection?",{"text":88,"@type":76},"Radio-frequency interference (RFI) detection is treated as a dedicated task, using a nearest-latent-neighbours approach adapted for RFI detection and assessed with tailored results and evaluation methodology.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,139],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":136,"slug":138},10,"Lifestyle","lifestyle",{"id":140,"doc_module":4,"doc_module_name":46,"category_name":141,"show_sort_weight":110,"slug":142},19,"General","general"]