BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:SDSC - AI4Science monthly seminar: modeling of the particle losses
  in the LHC
DTSTART:20230214T160000
DTEND:20230214T170000
DTSTAMP:20260916T230025Z
UID:20c59dbca3bd7442dd83ba26a514da763393af34e118779bebe008ba
CATEGORIES:Conferences - Seminars
DESCRIPTION:Room: talk in GA3 21 (Bernoulli Center)\, followed by an ap
 éro in GA3 31.\n\nSpeaker: Dr. Ekaterina Krymova\, Lead Data Scientist 
 at SDSC.\nTitle: Modeling of the particle losses in the LHC \nAbstract:\
 nIn the Large Hadron Collider\, most of the beam losses occur in the speci
 ally designed collimation system\, where the particles with high oscillati
 on amplitudes or large momentum errors are scraped from the beams. The los
 ses are continuously recorded and monitored for machine protection. The le
 vel of particle loss depends on control parameters\, which are optimized m
 anually by operators. The presence of various (non-linear) effects in the 
 system\, such as electron cloud\, resonance effects\, etc\, makes it hard 
 to model and predict losses based on the available input data. At the same
  time\, a better understanding of the influence of control parameters on t
 he losses is required in order to improve the operation and performance\, 
 and future design of accelerators. Prior evidence suggests that modeling t
 he losses as an instantaneous function of the control parameter based on t
 he data from one year does not generalize well to the data from a differen
 t year. Given that this is most likely due to lagged effects\, we propose 
 to model the losses as a function of not only instantaneous but also previ
 ously observed control parameters as well as previous loss values. Using a
  standard reparameterization\, we reformulate the model as a Kalman Filter
  (KF) which allows for a flexible and efficient estimation procedure. The 
 variants of this model were trained using 2017 beam loss data and have bee
 n shown to accurately predict losses and identify both local and global lo
 ss trends in 2018 data.\n\nOrganizers: The SDSC - AI4Science seminar is c
 o-organized monthly by the EPFL AI4Science Initiative and the Swiss Data S
 cience Center and focussing on projects in which data science\, statistics
 \, machine learning and AI are applied to the sciences. Each seminar will 
 feature a presentation of one applied project\, geared towards an audience
  with expertise in Data Science methods\, from the initial formulation of 
 a research question in science associated with sources of data\, to the mo
 del\, algorithms and analyses produced. The presentation will be highlight
 ing the choices made\, the challenges encountered\, interesting technical 
 questions and possible further developments. A number of the projects pres
 ented will be collaborative projects of the Swiss Data Science Center. One
  of the objectives of the seminar is to foster exchanges between researche
 rs working in methods and applied data science research in the sciences\, 
 and to create new opportunities of collaborations.\n\nEach session will fe
 ature a talk followed by a discussion with the audience\, to be continued 
 over fingerfood and drinks.
LOCATION:GA 3 21 https://plan.epfl.ch/?room==GA%203%2021 https://epfl.zoom
 .us/j/67864899458
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR