[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126462-en":3,"doc-seo-126462-105":31,"detail-sidebar-cat-0-en-105":93},{"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},126462,962084925290,"Ophelia","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Machine-Learning based photon counting for PMT waveforms - energy resolution improvement for large liquid scintillator detectors","Machine-learning photon counting for PMT waveforms is developed to improve energy reconstruction in large liquid scintillator detectors. The work addresses a key limitation: PMT charge smearing, which degrades energy resolution and affects precision in neutrino experiments. Using the JUNO experiment as an example, the method extracts photon-counting information from a machine-learning model to mitigate charge smearing. The energy resolution improves by about 2.0%–2.8% within 1–9 MeV.","Machine-Learning based photon counting for PMT waveforms and its application to the improvement of the energy resolution in large liquid scintillator detectors  \nWei Jianga,c , Guihong Huangb,∗, Zhen Liuc,∗, Wuming Luoc,∗, Liangjian Wenc , Jianyi Luob  \na School of Physical Sciences, University of Chinese Academy of Science, Beijing 100049, China  \nb Wuyi University, Jiangmen 529020, China  \nc Institute of High Energy Physics, Chinese Academy of Sciences, Beijing 100049, China  \nAbstract  \nPhotomultiplier tubes (PMTs) are widely used in particle experiments for photon detection. PMT waveform analysis is crucial for high-precision measurements of the position and energy of incident particles in liquid scintillator (LS) detectors. A key factor contributing to the energy resolution in large liquid scintillator detectors with PMTs is the charge smearing of PMTs. This paper presents a machine-learning-based photon counting method for PMT waveforms and its application to the energy reconstruction, using the JUNO experiment as an example. The results indicate that leveraging the photon counting information from the machine learning model can partially mitigate the impact of PMT charge smearing and lead to a relative 2.0% to 2.8% improvement on the energy resolution in the energy range of [1, 9] MeV.  \nKeywords: JUNO, Liquid scintillator detector, Neutrino experiment, Waveform reconstruction, Energy reconstruction  \n1. Introduction  \nLiquid scintillators (LS) and photomultiplier tubes (PMT) play important roles in neutrino experiments, as evidenced in projects like KamLAND [1, 2], Borexino [3, 4], Daya Bay [5– 8], RENO [9, 10] and Double Chooz [11, 12] . These LS neutrino detectors typically offer low energy thresholds of subMeV and good energy resolutions, which are ideal for studying neutrinos originating from sources including nuclear reactors, supernova, the Earth or the sun. The next generation LS detector, Jiangmen Underground Neutrino Observatory (JUNO) [13– 15], is equipped with 20 kton of LS, 17,612 20-inch PMTs and 25,600 3-inch PMTs within the central detector. Its primary goal is to determine the neutrino mass ordering (NMO), by precisely measuring the energy spectrum of reactor antineutrinos with a target energy resolution of 3% @ 1 MeV. Reactor antineutrinos are detected in LS detectors via the Inverse Beta  \nDecay (IBD) process, in which a positron and a neutron are produced in the final state. The positron will usually deposit its kinetic energy quickly and then annihilate with an electron, yielding the prompt signal. Meanwhile the neutron will dissipate its energy and eventually be captured by either hydrogen or carbon nuclei, yielding the delayed signal roughly 200 µslater. Taking advantage of the correlated prompt-delay signals, IBD events can be selected efficiently. The visible energy of the positron needs to be reconstructed in order to deduce the energy of the incoming antineutrino. Many factors will con-  \nthe light yield of the LS, Cherenkov photons, non-uniform energy response of the detector, photon contamination from the PMT dark noise and more. A comprehensive breakdown of the energy resolution in JUNO can be found in Ref. [16] .  \nAs indicated by Fig. 8 from Ref. [17], the energy resolution is crucial for the NMO sensitivity in JUNO, a relative 3.3% improvement on the targeted 3%@1 MeV energy resolution would roughly result in a 11.4% reduction in the data taking time to reach 3σ significance. To achieve the unprecedented energy resolution in JUNO, the LS recipe has been studied thoroughly [18] to optimize the light yield. Meanwhile PMTs with world-leading Quantum Efficiency [19] have been developed to further increase the number of detected photons. Prior studies have extensively explored vertex [20, 21] and energy reconstructions [22, 23] . A data-driven simultaneous vertex and energy reconstruction method that combines the charge and time information of PMTs has been developed. It is used to predict th","cbCaidnN3AcgZt8O","https://ap.wps.com/l/cbCaidnN3AcgZt8O","pdf",517526,7,1,12,"English","en",105,"# Introduction\n## Liquid scintillator and PMT role in neutrino experiments\n## JUNO detector context and energy resolution requirement\n## Photon detection, charge smearing, and limitations\n## Motivation for machine learning on PMT waveforms","[{\"question\":\"Why is PMT waveform analysis important in liquid scintillator detectors?\",\"answer\":\"PMT waveform analysis is crucial to reconstruct the position and energy of incident particles. It directly impacts the precision of measurements in experiments using liquid scintillator detectors.\"},{\"question\":\"What problem does PMT charge smearing cause for energy resolution?\",\"answer\":\"PMT charge smearing introduces uncertainty in the charge-based estimate of the number of photoelectrons. This uncertainty propagates into degraded energy resolution.\"},{\"question\":\"How does the proposed machine-learning photon counting method improve energy reconstruction in JUNO?\",\"answer\":\"The method predicts the photon-counting information from PMT waveforms using a machine-learning model, which partially mitigates the impact of PMT charge smearing. It yields a relative 2.0%–2.8% improvement in energy resolution over 1–9 MeV.\"}]","Machine-Learning based photon counting for PMT waveforms - energy resolution improvement for large liquid scintillator detectors | PDF",1785905188,30,{"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":88,"head_meta":90,"extra_data":92,"updated_unix":29},"machine-learning-based-photon-counting-for-pmt-waveforms-energy-resolution-improvement-for-large-liquid-scintillator-detectors","",{"@graph":37,"@context":87},[38,55,70],{"@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":54},"https://docshare.wps.com/document/machine-learning-based-photon-counting-for-pmt-waveforms-energy-resolution-improvement-for-large-liquid-scintillator-detectors/126462/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"Why is PMT waveform analysis important in liquid scintillator detectors?","Question",{"text":77,"@type":78},"PMT waveform analysis is crucial to reconstruct the position and energy of incident particles. It directly impacts the precision of measurements in experiments using liquid scintillator detectors.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What problem does PMT charge smearing cause for energy resolution?",{"text":82,"@type":78},"PMT charge smearing introduces uncertainty in the charge-based estimate of the number of photoelectrons. This uncertainty propagates into degraded energy resolution.",{"name":84,"@type":75,"acceptedAnswer":85},"How does the proposed machine-learning photon counting method improve energy reconstruction in JUNO?",{"text":86,"@type":78},"The method predicts the photon-counting information from PMT waveforms using a machine-learning model, which partially mitigates the impact of PMT charge smearing. It yields a relative 2.0%–2.8% improvement in energy resolution over 1–9 MeV.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,117,121,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":30,"slug":122},"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":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":108,"slug":138},19,"General","general"]