SDSC - AI4Science monthly seminar: modeling of the particle losses in the LHC
Room: talk in GA3 21 (Bernoulli Center), followed by an apéro in GA3 31.
Speaker: Dr. Ekaterina Krymova, Lead Data Scientist at SDSC.
Title: Modeling of the particle losses in the LHC
Abstract:
In the Large Hadron Collider, most of the beam losses occur in the specially designed collimation system, where the particles with high oscillation amplitudes or large momentum errors are scraped from the beams. The losses are continuously recorded and monitored for machine protection. The level of particle loss depends on control parameters, which are optimized manually 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 the losses is required in order to improve the operation and performance, and future design of accelerators. Prior evidence suggests that modeling the losses as an instantaneous function of the control parameter based on the data from one year does not generalize well to the data from a different 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 previously 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 been shown to accurately predict losses and identify both local and global loss trends in 2018 data.
Organizers: The SDSC - AI4Science seminar is co-organized monthly by the EPFL AI4Science Initiative and the Swiss Data Science 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 model, algorithms and analyses produced. The presentation will be highlighting the choices made, the challenges encountered, interesting technical questions and possible further developments. A number of the projects presented will be collaborative projects of the Swiss Data Science Center. One of the objectives of the seminar is to foster exchanges between researchers working in methods and applied data science research in the sciences, and to create new opportunities of collaborations.
Each session will feature a talk followed by a discussion with the audience, to be continued over fingerfood and drinks.
Speaker: Dr. Ekaterina Krymova, Lead Data Scientist at SDSC.
Title: Modeling of the particle losses in the LHC
Abstract:
In the Large Hadron Collider, most of the beam losses occur in the specially designed collimation system, where the particles with high oscillation amplitudes or large momentum errors are scraped from the beams. The losses are continuously recorded and monitored for machine protection. The level of particle loss depends on control parameters, which are optimized manually 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 the losses is required in order to improve the operation and performance, and future design of accelerators. Prior evidence suggests that modeling the losses as an instantaneous function of the control parameter based on the data from one year does not generalize well to the data from a different 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 previously 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 been shown to accurately predict losses and identify both local and global loss trends in 2018 data.
Organizers: The SDSC - AI4Science seminar is co-organized monthly by the EPFL AI4Science Initiative and the Swiss Data Science 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 model, algorithms and analyses produced. The presentation will be highlighting the choices made, the challenges encountered, interesting technical questions and possible further developments. A number of the projects presented will be collaborative projects of the Swiss Data Science Center. One of the objectives of the seminar is to foster exchanges between researchers working in methods and applied data science research in the sciences, and to create new opportunities of collaborations.
Each session will feature a talk followed by a discussion with the audience, to be continued over fingerfood and drinks.
Practical information
- Informed public
- Free
- This event is internal