Machine Learning Applications for Particle Accelerators

chaired by Christopher Mayes (SLAC National Accelerator Laboratory), Daniel Bowring (Fermilab), Daniel Ratner (SLAC), Auralee Edelen (Fermilab, CSU)
from to (US/Pacific)
at SLAC Building 53 ( Trinity )
2575 Sand Hill Rd, Menlo Park, CA 94025
Description

The goal of this workshop is to help build a world-wide community of researchers interested in applying machine learning techniques to particle accelerators. The workshop will be split into four sequential topics:

  1. Tuning, optimization, control
  2. Prognostics, alarm handling, anomaly-breakout detection
  3. Data analysis
  4. Simulations, modeling

This workshop was broadcast via Zoom.

Go to day
  • Tuesday, February 27, 2018
    • 07:30 - 09:00 Breakfast
    • 09:00 - 12:00 ML Tutorial: Morning
      Conveners: Auralee Edelen (CSU), Daniel Bowring (Fermilab), Dr. Christopher Mayes (SLAC National Accelerator Laboratory), Gianluca Valentino
      • 09:00 Logistic Regression, Neural Networks 1h30'
      • 10:30 Coffee 30' ( SLAC - Bldg. 53, Trinity Lobby )
      • 11:00 Neural Networks 1h0'
    • 12:00 - 13:00 Lunch ( SLAC - Bldg. 53, Trinity Lobby )
      Provided Lunch Buffet
    • 13:00 - 15:00 ML Tutorial: Afternoon
      • 13:00 Unsupervised Learning (Clustering), Toy Optics model 1h30'
      • 14:30 Coffee 30'
        14:30
    • 15:00 - 17:00 Ocelot Tutorial
      Convener: Sergey Tomin
  • Wednesday, February 28, 2018
    • 07:30 - 09:00 Breakfast
      Provided breakfast
    • 09:00 - 09:20 Welcome 20'
      Speaker: Prof. Tor Raubenheimer (SLAC)
      Material: Slides pdf file
    • 09:20 - 12:00 Facility needs
      Convener: Kevin Li
      • 09:20 Facility needs: Hadron Synchrotrons: Operational challenges at the LHC 20'
        Speaker: Kajetan Fuchsberger (CERN)
        Material: Slides powerpoint file
      • 09:40 Facility needs: XFELs 20'
        Speaker: Raimund Kammering (DESY)
        Material: Slides powerpoint file
      • 10:00 Facility needs: Synchrotrons 20'
        Speaker: Xiaobiao Huang
        Material: Slides pdf file
      • 10:20 Coffee 30' ( SLAC - Bldg. 53, Trinity Lobby )
      • 10:50 Fault detection and alarm systems for the CERN Technical Infrastructure 20'
        Speaker: Jesper Nielsen (CERN)
        Material: Slides powerpoint file
      • 11:10 Facility needs - or chances - seen from the other side 20'
        Speaker: Arno Candel
        Material: Slides pdf file
      • 11:30 Discussion 30'
        Speaker: Kevin Li
    • 12:00 - 13:00 Lunch
      Provided Lunch Buffet
    • 13:00 - 18:00 Tuning
      Convener: Auralee Edelen (CSU)
      • 13:00 Experience with FEL taper tuning using reinforcement learning and clustering 20'
        Speaker: Dr. Juhao Wu
        Material: Slides powerpoint file
      • 13:20 Introduction to Bayesian Optimization 20'
        Speaker: Johannes Kirschner
        Material: Slides pdf file
      • 13:40 Experience at SLAC with Bayesian Optimization using Gaussian Processes 20'
        Speaker: Jopseph Duris
        Material: Slides powerpoint file
      • 14:00 Poster Blitz 20'
        Material: Slides powerpoint file
      • 14:20 Coffee 1h0'
      • 15:20 Experience with tuning at XFEL 20'
        Speaker: Sergey Tomin
        Material: Slides powerpoint file pdf file
      • 15:40 Experience with tuning at FERMI@Elettra 20'
        Speaker: Giulio Gaio (FERMI@Elettra)
        Material: Slides powerpoint file unknown type file
      • 16:00 General experience with online optimization 20'
        Speakers: Alexander Scheinker, Scheinker Alex
        Material: Slides pdf file
      • 16:20 Sloppy and Genetic Algorithms for Low-Emittance Tuning at CESR 20'
        Speaker: Ivan Bazarov
        Material: Slides pdf file
      • 16:40 Discussion: Tuning 40'
        Speaker: Auralee Edelen (CSU)
    • 18:00 - 21:00 Reception at Dutch Goose ( Dutch Goose: 3567 Alameda de las Pulgas, Menlo Park, CA 94025 )
  • Thursday, March 1, 2018
    • 07:30 - 09:00 Breakfast
      Provided breakfast
    • 09:00 - 12:00 Simulations and Modeling
      Convener: Ilya Agapov (DESY)
      • 09:00 Experience with Model Predictive Control and Model-based Reinforcement Learning using Neural Networks 20'
        Speaker: Auralee Edelen
        Material: Slides pdf file
      • 09:20 Forecasting of Beam Interlocks in High Intensity (Hadron) Accelerators 20'
        Speaker: Andreas Adelmann
        Material: Slides pdf file
      • 09:40 Light Source Simulations 20'
        Speaker: Ilya Agapov (DESY)
        Material: Slides powerpoint file pdf file
      • 10:00 Poster Session and Coffee 1h0' ( SLAC - Bldg. 53, Trinity Lobby )
      • 11:00 Neural Network Modeling and Virtual Diagnostics at FAST 20'
        Speaker: Jonathan Edelen
        Material: Slides powerpoint file
      • 11:20 GANs for Simulation in HEP 20'
        Speaker: Luke de Oliveira
        Material: Slides pdf file
      • 11:40 Discussion 20'
        Speaker: Ilya Agapov (DESY)
    • 12:00 - 13:00 Lunch
      Provided Lunch Buffet
    • 13:00 - 15:00 Prognosics
      Convener: Rasmus Ischebeck
      • 13:00 Machine learning for anomaly detection in large distributed accelerator systems 20'
        Speaker: Pieter van Trappen
        Material: Slides powerpoint file
      • 13:20 Beam loss plane recognition for the LHC 20'
        Speaker: Gianluca Valentino
        Material: Slides powerpoint file pdf file
      • 13:40 Detection of bad BPMs 20'
        Speaker: Elena Fol
        Material: Slides powerpoint file pdf file
      • 14:00 Discussion 30'
      • 14:30 Coffee 30'
    • 15:00 - 17:00 Tour
    • 17:30 - 20:00 Meyer-Buck House Reception ( Parking: 2121 Sand Hill Rd, Menlo Park, CA 94025 )
      Reception at the Provost's house. Parking is at the Hewlett Foundation next door. 
  • Friday, March 2, 2018
    • 07:30 - 09:00 Breakfast
      Provided breakfast
    • 09:00 - 11:00 Data Analysis
      Convener: Daniel Bowring (Fermilab)
      • 09:00 Machine learning application on the investigation of the micro-bunching instability at storage rings 20'
        Speaker: Mr. Tobias Boltz (KIT)
        Material: Slides pdf file
      • 09:20 Non-parametric Density Estimators for the Measurements of Ionization Cooling 20'
        Speaker: Tanaz Angelina Mohayai (Illinois Institute of Technology)
        Material: Slides pdf file
      • 09:40 Data mining at HIPA 20'
        Speaker: Mr. Jochem Snuverink (Paul Scherrer Institute)
        Material: Slides pdf file
      • 10:00 Poster Session and Coffee 1h0' ( SLAC - Bldg. 53, Trinity Lobby )
    • 11:00 - 12:00 Summary 1h0'
      Speakers: Daniel Bowring (Fermilab), Auralee Edelen (CSU), Ilya Agapov (DESY), Kevin Li (CERN), Dr. Rasmus Ischebeck (PSI)
      Material: Slides powerpoint filedown arrow pdf filedown arrow
    • 12:00 - 13:30 Lunch ( SLAC - Bldg. 53, Trinity Lobby )
      Provided Lunch Buffet
    • 13:30 - 15:00 Whitepaper and Collaboration planning 1h30'
      Speaker: Dr. Christopher Mayes (SLAC National Accelerator Laboratory)