Machine Learning Applications for Particle Accelerators

27 Feb 2018, 07:30 → 2 Mar 2018, 18:00 US/Pacific

Trinity (SLAC Building 53)

Auralee Edelen (Fermilab, CSU), Christopher Mayes (SLAC National Accelerator Laboratory), Daniel Bowring (Fermilab), Daniel Ratner (SLAC)

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.

Tuesday, 27 February

07:30 Breakfast

ML Tutorial: Morning

Conveners: Auralee Edelen (CSU), Dr Christopher Mayes (SLAC National Accelerator Laboratory), Daniel Bowring (Fermilab), Gianluca Valentino

1 Logistic Regression, Neural Networks

10:30 Coffee

2 Neural Networks

12:00 Lunch

Provided Lunch Buffet

ML Tutorial: Afternoon

3 Unsupervised Learning (Clustering), Toy Optics model

14:30 Coffee

14:30

Ocelot Tutorial

Convener: Sergey Tomin

Wednesday, 28 February

07:30 Breakfast

Provided breakfast

4 Welcome

Speaker: Prof. Tor Raubenheimer (SLAC)

Slides ML-Workshop-Welcome.pdf

Facility needs

Convener: Kevin Li

5 Facility needs: Hadron Synchrotrons: Operational challenges at the LHC

Speaker: Kajetan Fuchsberger (CERN)

Slides ml-ws-slack-lhc-challenges-kajetan-fuchsberger-v1.pptx

6 Facility needs: XFELs

Speaker: Raimund Kammering (DESY)

Slides ChallengesNeedsApplicationsForFELs.pptx

7 Facility needs: Synchrotrons

Speaker: Xiaobiao Huang

Slides Facility_Needs_Synchrotron_xhuang.pdf

10:20 Coffee

8 Fault detection and alarm systems for the CERN Technical Infrastructure

Speaker: Jesper Nielsen (CERN)

Slides Machine_Learning_2018_v2.pptx

9 Facility needs - or chances - seen from the other side

Speaker: Arno Candel

Slides ArnoCandel-SLAC-ICFA-02-28-2018.pdf

10 Discussion

Speaker: Kevin Li

12:00 Lunch

Provided Lunch Buffet

Tuning

Convener: Auralee Edelen (CSU)

11 Experience with FEL taper tuning using reinforcement learning and clustering

Speaker: Dr Juhao Wu

Slides TaperReinforcementClustering_v2.pptx

12 Introduction to Bayesian Optimization

Speaker: Johannes Kirschner

Slides introduction_to_bayesion_optimization.pdf

13 Experience at SLAC with Bayesian Optimization using Gaussian Processes

Speaker: Jopseph Duris

Slides 2018-02-28_-_GP_-_SLAC_ML_workshop-2.pptx

14 Poster Blitz

Slides poster_blitz.pptx

14:20 Coffee

15 Experience with tuning at XFEL

Speaker: Sergey Tomin

Slides Tomin_optimization.pdf Tomin_optimization.pptx

16 Experience with tuning at FERMI@Elettra

Speaker: Giulio Gaio (FERMI@Elettra)

Slides ifca_ml_2018_gaio_talk.pptx media1.mp4

17 General experience with online optimization

Speakers: Alexander Scheinker, Scheinker Alex

Slides Scheinker_LCLS_ML_Workshop_v7.pdf

18 Sloppy and Genetic Algorithms for Low-Emittance Tuning at CESR

Speaker: Ivan Bazarov

Slides slac_bazarov_talk.pdf

19 Discussion: Tuning

Speaker: Auralee Edelen (CSU)

18:00 Reception at Dutch Goose

Thursday, 1 March

07:30 Breakfast

Provided breakfast

Simulations and Modeling

Convener: Ilya Agapov (DESY)

20 Experience with Model Predictive Control and Model-based Reinforcement Learning using Neural Networks

Speaker: Auralee Edelen

Slides 20180301_Edelen_ICFA.pdf

21 Forecasting of Beam Interlocks in High Intensity (Hadron) Accelerators

Speaker: Andreas Adelmann

Slides ml-slac-adelmann.pdf

22 Light Source Simulations

Speaker: Ilya Agapov (DESY)

Slides agapov_fel_sr_simulations.pdf agapov_fel_sr_simulations.pptx

10:00 Poster Session and Coffee

23 Neural Network Modeling and Virtual Diagnostics at FAST

Speaker: Jonathan Edelen

Slides Edelen_FAST_1Mar2018.pptx

24 GANs for Simulation in HEP

Speaker: Luke de Oliveira

Slides SLAC-hep-lukedeo.pdf

25 Discussion

Speaker: Ilya Agapov (DESY)

12:00 Lunch

Provided Lunch Buffet

Prognosics

Convener: Rasmus Ischebeck

26 Machine learning for anomaly detection in large distributed accelerator systems

Speaker: Pieter van Trappen

Slides ifca_machine_learning_slac.pptx

27 Beam loss plane recognition for the LHC

Speaker: Gianluca Valentino

Slides beam_loss_plane_recognition.pdf beam_loss_plane_recognition.pptx

28 Detection of bad BPMs

Speaker: Elena Fol

Slides bad_bpms_detection_slac.pdf bad_bpms_detection_slac.pptx

29 Discussion

14:30 Coffee

15:00 Tour

17:30 Meyer-Buck House Reception

Reception at the Provost's house. Parking is at the Hewlett Foundation next door.

Friday, 2 March

07:30 Breakfast

Provided breakfast

Data Analysis

Convener: Daniel Bowring (Fermilab)

30 Machine learning application on the investigation of the micro-bunching instability at storage rings

Speaker: Mr Tobias Boltz (KIT)

Slides data_analysis_tboltz

31 Non-parametric Density Estimators for the Measurements of Ionization Cooling

Speaker: Tanaz Angelina Mohayai (Illinois Institute of Technology)

Slides 2018-03-02-tmohayai-2.pdf

32 Data mining at HIPA

Speaker: Mr Jochem Snuverink (Paul Scherrer Institute)

Slides 20180302-ML-Mining.pdf

10:00 Poster Session and Coffee

33 Summary

Speakers: Auralee Edelen (CSU), Daniel Bowring (Fermilab), Ilya Agapov (DESY), Kevin Li (CERN), Dr Rasmus Ischebeck (PSI)

Slides

• 20180302_ICFA_Tuning_Summary.pdf
• data-analysis-session-notes.pdf
• session_summary_agapov.pptx
• Summary_Prognostics_Session.pptx

12:00 Lunch

Provided Lunch Buffet

34 Whitepaper and Collaboration planning

Speaker: Dr Christopher Mayes (SLAC National Accelerator Laboratory)