[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117803-en":3,"doc-seo-117803-105":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":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},117803,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","Machine Learning for Quantum-Enhanced Gravitational-Wave Observatories","Machine learning supports the processing of large experimental physics data and enables improved operation of quantum-enhanced gravitational-wave detectors using squeezed vacuum states. Maintaining optimal squeezing remains difficult because squeezed-state preparation and injection are sensitive to environmental fluctuations and interferometer conditions. This work trains neural network models to predict squeezing during LIGO’s third observing run (O3) from auxiliary data streams, and interprets model outputs to identify and quantify key contributors to squeezing degradation. The results support future closed-loop optimization of the squeezer subsystem.","Machine Learning for Quantum-Enhanced Gravitational-Wave Observatories  \narXiv :2305 . 13780v1 [ astro-ph .IM] 23 May 2023  \nChris Whittle, 1, 2 Ge Yang,2 Matthew Evans, 1 and Lisa Barsotti 1, 2  \n1 LIGO, Massachusetts Institute of Technology, Cambridge, MA 02139, USA  \n2 Institute of Artificial Intelligence and Fundamental Interaction,  \nMassachusetts Institute of Technology, Cambridge, MA 02139, USA  \n(Dated: May 24, 2023)  \nMachine learning has become an effective tool for processing the extensive data sets produced by large physics experiments. Gravitational-wave detectors are now listening to the universe with quantum-enhanced sensitivity, accomplished with the injection of squeezed vacuum states. Squeezed state preparation and injection is operationally complicated, as well as highly sensitive to environmental fluctuations and variations in the interferometer state. Achieving and maintaining optimal squeezing levels is a challenging problem and will require development of new techniques to reach the lofty targets set by design goals for future observing runs and next-generation detectors. We use machine learning techniques to predict the squeezing level during the third observing run of the Laser Interferometer Gravitational-Wave Observatory (LIGO) based on auxiliary data streams, and offer interpretations of our models to identify and quantify salient sources of squeezing degradation. The development of these techniques lays the groundwork for future efforts to optimize squeezed state injection in gravitational-wave detectors, with the goal of enabling closed-loop control of the squeezer subsystem by an agent based on machine learning.  \nI. INTRODUCTION  \nMachine learning has seen an abundance of applications in experimental physics: active control of high energy particle experiments [1], quantum state tomography [2, 3], Bose-Einstein condensate preparation [4] and adaptive feedback for phase estimation [5], to name some recent uses. Laser interferometric gravitational-wave detectors like LIGO [6], Virgo [7], GEO600 [8] and KAGRA [9] are complex instruments that require hundreds of control loops to operate simultaneously. The incorporation of machine learning into the operation of these detectors is an active area of research, following the successful application of machine learning in gravitationalwave data characterization and analysis, including glitch classification [10–13], noise subtraction [14–16], waveform modeling [17] and signal searches [18] . A first demonstration of neural network-based alignment of the GEO600 optical cavities was recently performed [19] .  \nHere we investigate the application of machine learning to minimize quantum noise in gravitational-wave detectors by optimizing the injection of squeezed states.  \nThe third observing run (O3) of the gravitationalwave detector network saw the first demonstration of quantum-enhanced gravitational-wave detection [20–22] . At high (≳50Hz) frequencies, interferometers are limited by quantum shot noise due to the random arrival times of the uncorrelated photons that make up the electromagnetic field striking the readout photodiodes. Squeezed states can circumvent this limit by inducing correlations between photons, thereby reducing uncertainty in the readout quadrature [23] . Squeezed vacuum states enabled a reduction of quantum noise by up to 3.2dB in LIGO [20] and Virgo [21], and up to 6dB in GEO600 [22] .  \nAlthough already a triumph in quantum metrology and astrophysics, future gravitational-wave detectors with even greater sensitivity require further improvements.  \nInspection of the detector data recorded over the course of O3 reveals that it is difficult to maintain optimal squeezing performance throughout the 1-year run, with an average observed squeezing of 2 .23dB, nearly 1dB less than the maximum observed. Moreover, there is significant variability in the observed squeezing level. For example, the histogram of squeezing levels observed in the Livi","cbCait3x7tTngMLo","https://ap.wps.com/l/cbCait3x7tTngMLo","pdf",3211131,1,13,"English","en",105,"# Introduction\n## Quantum noise and squeezed-state enhancement\n## Challenges maintaining optimal squeezing during O3\n## Machine learning approach and model interpretability","[{\"question\":\"Why is maintaining optimal squeezing difficult in quantum-enhanced gravitational-wave detectors?\",\"answer\":\"Squeezed-state preparation and injection are operationally complicated and highly sensitive to environmental fluctuations and variations in the interferometer state, including squeezer and interferometer parameters.\"},{\"question\":\"How is machine learning used in this study?\",\"answer\":\"Neural network models predict the squeezing level during LIGO’s third observing run (O3) using auxiliary data streams, enabling assessment of squeezing performance over time.\"},{\"question\":\"What does the paper aim to achieve beyond prediction?\",\"answer\":\"The approach is intended to identify and quantify sources of squeezing degradation and to lay the groundwork for future closed-loop control of the squeezer subsystem using machine-learning agents.\"}]","Machine Learning for Quantum-Enhanced Gravitational-Wave Observatories | PDF",1785679655,33,{"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},"machine-learning-for-quantum-enhanced-gravitational-wave-observatories","",{"@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-for-quantum-enhanced-gravitational-wave-observatories/117803/",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","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is maintaining optimal squeezing difficult in quantum-enhanced gravitational-wave detectors?","Question",{"text":75,"@type":76},"Squeezed-state preparation and injection are operationally complicated and highly sensitive to environmental fluctuations and variations in the interferometer state, including squeezer and interferometer parameters.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is machine learning used in this study?",{"text":80,"@type":76},"Neural network models predict the squeezing level during LIGO’s third observing run (O3) using auxiliary data streams, enabling assessment of squeezing performance over time.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the paper aim to achieve beyond prediction?",{"text":84,"@type":76},"The approach is intended to identify and quantify sources of squeezing degradation and to lay the groundwork for future closed-loop control of the squeezer subsystem using machine-learning agents.","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"]