[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126043-en":3,"doc-seo-126043-105":31,"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":28,"seo_description":14,"update_tm":29,"read_time":30},126043,962084928904,"Asher","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Energy reconstruction with machine learning techniques in JUNO - 会议摘要","JUNO is a multipurpose liquid scintillator neutrino experiment under construction in China, designed to determine the neutrino mass ordering with 3–4σ significance in about six years and to measure oscillation parameters with sub-percent precision. Reactor antineutrino events are studied using machine learning energy reconstruction, targeting the inverse beta decay signature. The approach compares Boosted Decision Trees and fully connected deep neural networks trained on aggregated charge and first-hit-time features from the JUNO photomultiplier array.","IL NUOVO CIMENTO 47 C (2024) 358 DOI 10.1393/ncc/i2024-24358-6  \nColloquia: MAYORANA 2023  \nEnergy reconstruction with machine learning techniques in JUNO  \nA. Gavrikov ( 1 )(2 ) on behalf of the JUNO Collaboration  \n(1 ) Dipartimento di Fisica e Astronomia dell’Universita` di Padova - Padova, Italia  \n(2 ) INFN Sezione di Padova - Padova, Italia received 6 August 2024  \nSummary.— The Jiangmen Underground Neutrino Observatory (JUNO) is a multipurpose liquid scintillator neutrino experiment under construction located in China. Although the main source of neutrinos in JUNO is two nuclear power plants located about 52.5 km away from the experiment, it will also be able to study solar and atmospheric neutrinos, geoneutrinos and neutrinos coming from supernovae. The determination of the neutrino mass ordering (NMO) with 3-4σ in 6 years is the main goal of the experiment. Moreover, another JUNO’s important aim is to measure neutrino oscillation parameters sin2 θ12 , Δm221, Δm231 with sub-percent precision. The central detector of JUNO is an acrylic sphere filled with 20 kt of liquid-scintillator (LS) surrounded by 17612 20-inch photomultiplier tubes (PMTs) and 25600 3-inch PMTs, providing ∼78% coverage of the detector sphere. Thanks to the almost complete coverage of the sphere by the PMTs array, as well as highlight yield leads to an unprecedented, for LS-based experiments, energy resolution of 3% at 1 MeV. Due to the need to take into account various effects, includingthe non-linearity of the energy response and the detector’s spatial non-uniformity, event energy reconstruction is not a straightforward task. In this study, energy reconstruction for reactor neutrino events with machine learning (ML) techniques is presented. The following two models are used: Boosted Decision Trees and Fully Connected Deep Neural Network. The models are trained on aggregated features extracted from charge and time information on PMTs.  \n1.– Introduction  \nLiquid-scintillator (LS) detectors surrounded by photomultiplier tubes (PMTs) are widely used for studying neutrino nature in many modern neutrino experiments [1] . The goal of the new generation of LS-based experiments is the construction of even larger and more precise apparatuses. One example of such experiments is the Jiangmen Underground Neutrino Observatory (JUNO) . JUNO is a neutrino observatory with abroad physics program located in China about 52.5 km away from two power plants: Taishan and Yangjiang [2], in a laboratory submerged 650 meters deep underground.  \nThe JUNO’s central detector (CD) is an acrylic sphere, 35.4 meters in diameter, filled Creative Commons Attribution 4.0 License ([https://creativecommons.org/licenses/by/4.0](https://creativecommons.org/licenses/by/4.0)) 1  \n2 A. GAVRIKOV on behalf of the JUNO COLLABORATION  \nwith 20 kt of LS. The CD is held by a stainless steel construction immersed in an ultrapure water pool. To collect photons emitted in LS, the CD of JUNO is equipped with two types of PMTs: 17612 large 20-inch PMTs and 25600 small 3-inch PMTs. This PMT array covers almost 78% of the detector sphere, leading to a high photoelectron statistic of ∼ 1600 photoelectron per 1 MeV. Figure 1 shows a schematic view of JUNO.  \nJUNO has a broad physics program and the main goal is to determine the neutrino mass ordering (NMO) within 3-4σ in 6 years of data-taking. Furthermore, JUNO will measure the following oscillation parameters sin2 θ 12 , Δm221, Δm231 with sub-percent precision.  \nThe “golden reaction” for detecting neutrinos – Inverse Beta Decay (IBD)– is used in JUNO to detect reactor antineutrinos: ν  e + p → e+ + n. The positron rapidly deposits its kinetic energy and annihilates into two 0.511 MeV gammas forming a prompt signal. Thereafter, the neutron, after approximately ∼200 μs, is captured on hydrogen (99%) or carbon (1%) emitting a 2.22 MeV or 4.95 MeV gamma, respectively. Such a clear signature of two signals allows an effective selection of IBD events and rejec","cbCaiajx6aOrsaKy","https://ap.wps.com/l/cbCaiajx6aOrsaKy","pdf",194572,7,1,4,"English","en",105,"# Introduction\n## JUNO detector and physics goals\n# Machine learning approach\n## Event representation and feature aggregation\n## ML models: BDT and deep neural network","[{\"question\":\"What main physics goals does JUNO have according to the document?\",\"answer\":\"JUNO aims to determine the neutrino mass ordering with 3–4σ in roughly six years and to measure oscillation parameters with sub-percent precision.\"},{\"question\":\"Which reactor neutrino interaction is used for event selection and energy reconstruction?\",\"answer\":\"Inverse beta decay is used, with a prompt positron signal followed by neutron capture gamma emission, enabling effective background rejection.\"},{\"question\":\"How is the machine learning input for energy reconstruction constructed?\",\"answer\":\"Each event is represented using charge and first hit time values from PMTs; the study then reduces dimensionality by using aggregated features extracted from the charge and time distributions.\"}]","Energy reconstruction with machine learning techniques in JUNO - 会议摘要 | PDF",1785902702,10,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"energy-reconstruction-with-machine-learning-techniques-in-juno-conference-summary","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":22},"https://docshare.wps.com/document/energy-reconstruction-with-machine-learning-techniques-in-juno-conference-summary/126043/",{"url":53,"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":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",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 main physics goals does JUNO have according to the document?","Question",{"text":76,"@type":77},"JUNO aims to determine the neutrino mass ordering with 3–4σ in roughly six years and to measure oscillation parameters with sub-percent precision.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which reactor neutrino interaction is used for event selection and energy reconstruction?",{"text":81,"@type":77},"Inverse beta decay is used, with a prompt positron signal followed by neutron capture gamma emission, enabling effective background rejection.",{"name":83,"@type":74,"acceptedAnswer":84},"How is the machine learning input for energy reconstruction constructed?",{"text":85,"@type":77},"Each event is represented using charge and first hit time values from PMTs; the study then reduces dimensionality by using aggregated features extracted from the charge and time distributions.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,120,123,128,131,134],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":30,"doc_module":4,"doc_module_name":47,"category_name":132,"show_sort_weight":30,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":47,"category_name":136,"show_sort_weight":107,"slug":137},19,"General","general"]