Uncertainty Quantification for a Cramer Generative Adversarial Network based Simulation of the Ring-Imaging Cherenkov particle Detector using Features Densities

Uncertainty Quantification for a Cramer Generative Adversarial Network based Simulation of the Ring-Imaging Cherenkov particle Detector using Features Densities | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Uncertainty Quantification for a Cramer Generative Adversarial Network based Simulation of the Ring-Imaging Cherenkov particle Detector using Features Densities Esteban Villalobos-Gómez, Fernando Ugalde Green, José Arce Morales, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7794298/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract The simulation of particle collisions and of the subsequent detection process is by far the most computationally expensive task for the experiments at the Large Hadron Collider. Generative Machine Learning has been investigated for the last decade to replace the interaction-level computations implemented in the Geant4 libraries with deep neural networks. Using Neural Networks to approximate the outcome of a Geant4 simulation is fast, computationally efficient and ready for hardware acceleration, but introduces an additional approximation error that must be modeled and controlled. In this work, we consider the simulation of the Particle Identification features obtained with the RICH detectors of the LHCb experiment at CERN, which has been extensively studied in the literature as example of parametrization of the detector response with generative models, and in particular with Cramér Generative Adversarial Networks. We propose the usage of the Feature Densities (FD) method to provide a computationally sustainable uncertainty quantification algorithm. This method computes a density estimation of the embeddings obtained from projected training data. In the reported studies, the proposed method is proved to predict uncertainty scores comparable to the previously implemented Monte Carlo Dropout method, with a computational cost reduced by one order of magnitude. And we propose evolutions in the Generative Models that may result in a further reduction of the computational cost. The usage of different embedding layers and the possibility of evaluating the training data as many times as possible, makes the density estimation very flexible to estimate the feature densities. Deep Learning Generative Adversarial Networks Feature Densities Monte Carlo Dropout Uncertainty Quantification Out of Distribution Detection Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 22 Dec, 2025 Reviews received at journal 12 Dec, 2025 Reviewers agreed at journal 14 Nov, 2025 Reviews received at journal 10 Nov, 2025 Reviewers agreed at journal 14 Oct, 2025 Reviewers invited by journal 13 Oct, 2025 Editor assigned by journal 10 Oct, 2025 Submission checks completed at journal 08 Oct, 2025 First submitted to journal 06 Oct, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7794298","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":532167004,"identity":"e13d910d-56ce-47bd-bd53-38d786a0622b","order_by":0,"name":"Esteban Villalobos-Gómez","email":"","orcid":"","institution":"Costa Rica Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Esteban","middleName":"","lastName":"Villalobos-Gómez","suffix":""},{"id":532167006,"identity":"476e1f5a-1d73-4075-b5b3-eba75aa83e2a","order_by":1,"name":"Fernando Ugalde Green","email":"","orcid":"","institution":"Costa Rica Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Fernando","middleName":"Ugalde","lastName":"Green","suffix":""},{"id":532167007,"identity":"1adec98c-398b-4749-9d3a-f3b1c82379fa","order_by":2,"name":"José Arce Morales","email":"","orcid":"","institution":"Costa Rica Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"José","middleName":"Arce","lastName":"Morales","suffix":""},{"id":532167008,"identity":"3c5814d9-315d-439f-9e4c-62b327997c0f","order_by":3,"name":"Jonathan David Pastor Barrientos","email":"","orcid":"","institution":"Costa Rica Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jonathan","middleName":"David Pastor","lastName":"Barrientos","suffix":""},{"id":532167009,"identity":"0459e41e-7c1a-4691-9d22-35429838f3f8","order_by":4,"name":"Lucio Anderlini","email":"","orcid":"","institution":"INFN Sezione di Firenze","correspondingAuthor":false,"prefix":"","firstName":"Lucio","middleName":"","lastName":"Anderlini","suffix":""},{"id":532167010,"identity":"56f00b0b-dad1-4373-82d5-085c83ba1bc2","order_by":5,"name":"Saúl Calderon-Ramirez","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIiWNgGAWjYLCCB2wgkvnAAeK1JIC1sCWQoAeihceAgSgt8u2HH35IKLPJ55fu+Xj4Q809Bv72A4yfK/BoMTiTZiyRcC7NcuacsxsOHDhWzCBxJoFZ8gw+LQw5DBKJbYcNDG7kbjhwsCGBgeEGAxtjAz6H9b9h/pHY9h+oJecBWIs8IS0MN3LYgLYcAGlhAGsxIKTF4MYzM4uEc8kGkjPSDA6cOZbAY3gmsVkSv8OSH9/4UGZnwC+R/PhDRU2CnNzxwwc/4nUYOuBhYMDvk1EwCkbBKBgFRAAAanVQulzRKJIAAAAASUVORK5CYII=","orcid":"","institution":"Costa Rica Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Saúl","middleName":"","lastName":"Calderon-Ramirez","suffix":""},{"id":532167011,"identity":"10832f9a-f2b6-463d-a531-5732582a44cd","order_by":6,"name":"Sergio Arguedas Cuendis","email":"","orcid":"","institution":"Consejo Nacional de Rectores","correspondingAuthor":false,"prefix":"","firstName":"Sergio","middleName":"Arguedas","lastName":"Cuendis","suffix":""}],"badges":[],"createdAt":"2025-10-06 21:08:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7794298/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7794298/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94451034,"identity":"87c8b398-f242-47f3-88ed-9a2abf9334f3","added_by":"auto","created_at":"2025-10-27 14:39:45","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8975,"visible":true,"origin":"","legend":"","description":"","filename":"3af8bf58172744ea8576e72f709075ba.json","url":"https://assets-eu.researchsquare.com/files/rs-7794298/v1/b838f7ae46c3ff2e5702247f.json"},{"id":94467359,"identity":"d85edc50-3139-40b5-8be4-d47c04ff24b5","added_by":"auto","created_at":"2025-10-27 15:22:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":854372,"visible":true,"origin":"","legend":"","description":"","filename":"UncertaintyEstimationforaCramerGANwithRICHparticledetectordata.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7794298/v1_covered_c1b0dd18-24ab-4a73-9d5f-3ef624ad438e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Uncertainty Quantification for a Cramer Generative Adversarial Network based Simulation of the Ring-Imaging Cherenkov particle Detector using Features Densities","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"computing-and-software-for-big-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"csbs","sideBox":"Learn more about [Computing and Software for Big Science](http://link.springer.com/journal/41781)","snPcode":"41781","submissionUrl":"https://submission.nature.com/new-submission/41781/3","title":"Computing and Software for Big Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Deep Learning, Generative Adversarial Networks, Feature Densities, Monte Carlo Dropout, Uncertainty Quantification, Out of Distribution Detection","lastPublishedDoi":"10.21203/rs.3.rs-7794298/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7794298/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\nThe simulation of particle collisions and of the subsequent detection process is by far the most computationally expensive task for the experiments at the Large Hadron Collider. Generative Machine Learning has been investigated for the last decade to replace the interaction-level computations implemented in the Geant4 libraries with deep neural networks. Using Neural Networks to approximate the outcome of a Geant4 simulation is fast, computationally efficient and ready for hardware acceleration, but introduces an additional approximation error that must be modeled and controlled. In this work, we consider the simulation of the Particle Identification features obtained with the RICH detectors of the LHCb experiment at CERN, which has been extensively studied in the literature as example of parametrization of the detector response with generative models, and in particular with Cramér Generative Adversarial Networks. We propose the usage of the Feature Densities (FD) method to provide a computationally sustainable uncertainty quantification algorithm. This method computes a density estimation of the embeddings obtained from projected training data. In the reported studies, the proposed method is proved to predict uncertainty scores comparable to the previously implemented Monte Carlo Dropout method, with a computational cost reduced by one order of magnitude. And we propose evolutions in the Generative Models that may result in a further reduction of the computational cost. The usage of different embedding layers and the possibility of evaluating the training data as many times as possible, makes the density estimation very flexible to estimate the feature densities.","manuscriptTitle":"Uncertainty Quantification for a Cramer Generative Adversarial Network based Simulation of the Ring-Imaging Cherenkov particle Detector using Features Densities","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-27 11:31:21","doi":"10.21203/rs.3.rs-7794298/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-22T09:10:09+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-12T08:57:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"150148274034911066622491965354852886600","date":"2025-11-14T11:50:21+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-10T13:31:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"313736591397015827903975614962893985233","date":"2025-10-14T07:35:00+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-13T10:16:13+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-10T11:10:48+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-09T02:32:24+00:00","index":"","fulltext":""},{"type":"submitted","content":"Computing and Software for Big Science","date":"2025-10-06T20:58:25+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"computing-and-software-for-big-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"csbs","sideBox":"Learn more about [Computing and Software for Big Science](http://link.springer.com/journal/41781)","snPcode":"41781","submissionUrl":"https://submission.nature.com/new-submission/41781/3","title":"Computing and Software for Big Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"8186af19-08e8-43aa-a9a3-03896ada9d3d","owner":[],"postedDate":"October 27th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-18T06:10:00+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-27 11:31:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7794298","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7794298","identity":"rs-7794298","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}