[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120967-en":3,"doc-seo-120967-105":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},120967,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","What Machine Learning Can Do for Focusing Aerogel Detectors","Particle identification at the Super Charm-Tau factory is enabled by a Focusing Aerogel Ring Imaging Cherenkov detector (FARICH), whose fixed installation complicates cooling and leads to a high rate of ambient background hits. The resulting data flow is reduced and the particle velocity resolution is improved by filtering signal hits and reconstructing events. The work presents machine-learning approaches inspired by computer vision, using simulated photon coordinates and hit times as a two-channel input to a modified ResNet-18 architecture. Performance is evaluated for signal/noise classification with ROC and AUC metrics under realistic background conditions.","arXiv :2312 .02652v2 [hep-ex] 19 May 2026  \nWhat Machine Learning Can Do for Focusing Aerogel Detectors  \nFoma Shipilov 1 , ∗ , Alexander Barnyakov2,3 , Viktor Bobrovnikov2 , Sergey Kononov2,4 , and Fedor Ratnikov1  \n1NRU Higher School of Economics, Moscow, Russia  \n2Budker Institute of Nuclear Physics of Siberian Branch Russian Academy of Sciences, Novosibirsk, Russia  \n3Novosibirsk State Technical University, Novosibirsk, Russia  \n4Novosibirsk State University, Novosibirsk, Russia  \nAbstract. Particle identification at the Super Charm-Tau factory experiment will be provided by a Focusing Aerogel Ring Imaging CHerenkov detector (FARICH) . The specifics of detector location make proper cooling difficult, therefore a significant number of ambient background hits are captured. They must be mitigated to reduce the data flow and improve particle velocity resolution. In this work we present several approaches to filtering signal hits, inspired by machine learning techniques from computer vision.  \n1 Introduction  \nReliable particle identification (PID) is a crucial component of modern physics experiments. Particle identification in the Super c-τ factory (SCTF) experiments will be provided by FARICH detector [1] . The use of a FARICH is under intensive discussion for the Spin Physics Detector (SPD) detector at NICA [2] . FARICH uses multilayer aerogel for Cherenkov ring proximity focusing (Fig. 1) . The detector may use both seedless real-time signal finder to produce fast trigger and mitigate noise background, and seeded off-line reconstruction mode for precise identification, however, SiPM properties and operating temperatures may result in a significant background hit rate f ∼1 MHz/mm2 (signal-to-background ratio ≈ 0.014), which necessitates the development of robust noise filtering techniques.  \nConventional pattern recognition noise rejection methods aim to eliminate background hits directly by calculating carefully crafted empirical statistics derived from the physical properties of the system [4], e.g. DELPHI RICH automates background removal by measuring photon hit times, the number of hits for each detector cell, and other parameters [5] .  \nStatistical approaches to pattern recognition and reconstruction provide excellent precision and enable simple error estimation. However, such methods are only effective in moderate background conditions [5] due to the local nature of the statistics. This does not suit well for the heavy background environment of the FARICH. Additionally, statistical approaches require a particle track prior and may be difficult to incorporate new data sources into.  \n∗ e-mail: [foma@shipilov.ru](foma@shipilov.ru)  \nFigure 1: Left to right: possible integration of FARICH in SPD detector [2], focusing aerogel operation [3] .  \nIn contrast, Machine Learning (ML) techniques can extract high-level features from the input data and use them to efficiently solve various tasks. Many different data sources can be relatively easily incorporated, contributing to the overall robustness of the method.  \nML approaches proved to be useful across a diversity of nuclear physics research topics [6] . Early variants of neural networks had been developed specifically for use in high energy physics [7] . LHCb experiment uses neural networks for fast fake track rejection [8] and is planning to incorporate them in the RICH PID system [9] . ML has been applied to calibration and reconstruction of Cherenkov detectors with promising results [10] . Recently, object detection techniques from computer vision have been utilized in end-to-end data reconstruction pipeline for LArTPC neutrino imaging [4] . Object detection has also been adapted for sparse detector data in the object condensation pipeline [11] .  \nIn this work, we present our ML-based approach to noise filtering and event reconstruction of the FARICH detector.  \n2 Data processing and model architecture  \nThe signal data is generated in a Geant4 [12, 13] simulation (Fig.","cbCaitCfnX1Smfju","https://ap.wps.com/l/cbCaitCfnX1Smfju","pdf",814707,1,5,"English","en",105,"# Introduction\n## Machine learning motivation\n# Data processing and model architecture\n## Simulation inputs (Geant4)\n## ResNet-18 adaptation\n# Noise filtering\n## Binary classification setup\n## Evaluation metrics (ROC, AUC)","[{\"question\":\"Why is noise filtering necessary for FARICH detectors?\",\"answer\":\"FARICH installation makes cooling difficult, creating a significant ambient background hit rate. This overwhelms the data flow and degrades velocity resolution unless background hits are mitigated.\"},{\"question\":\"What data representation does the machine learning model use?\",\"answer\":\"The model uses simulated photon coordinates on a SiPM grid and hit times. These are formed into a two-channel image input: a bilinearly interpolated binary mask from (xc, yc) and a normalized time channel per pixel.\"},{\"question\":\"How is the noise filtering task defined and evaluated?\",\"answer\":\"Noise filtering is formulated as binary classification of events with or without signal, enabling logistic-regression-style training. Efficiency and noise reduction are assessed using ROC curves, with AUC used for model selection during hyperparameter search.\"}]","What Machine Learning Can Do for Focusing Aerogel Detectors | PDF",1785733098,13,{"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},"what-machine-learning-can-do-for-focusing-aerogel-detectors","",{"@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/what-machine-learning-can-do-for-focusing-aerogel-detectors/120967/",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","2026-08-03",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 noise filtering necessary for FARICH detectors?","Question",{"text":75,"@type":76},"FARICH installation makes cooling difficult, creating a significant ambient background hit rate. This overwhelms the data flow and degrades velocity resolution unless background hits are mitigated.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data representation does the machine learning model use?",{"text":80,"@type":76},"The model uses simulated photon coordinates on a SiPM grid and hit times. These are formed into a two-channel image input: a bilinearly interpolated binary mask from (xc, yc) and a normalized time channel per pixel.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the noise filtering task defined and evaluated?",{"text":84,"@type":76},"Noise filtering is formulated as binary classification of events with or without signal, enabling logistic-regression-style training. Efficiency and noise reduction are assessed using ROC curves, with AUC used for model selection during hyperparameter search.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"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":21,"slug":137},19,"General","general"]