Machine learning-based longitudinal phase space prediction of particle accelerators

Emma, C.; Edelen, A.; Hogan, M. J.; O’Shea, B.; White, G.; Yakimenko, V.

doi:10.1103/PhysRevAccelBeams.21.112802

Title: Machine learning-based longitudinal phase space prediction of particle accelerators

Abstract

Here, we report on the application of machine learning (ML) methods for predicting the longitudinal phase space (LPS) distribution of particle accelerators. Our approach consists of training a ML-based virtual diagnostic to predict the LPS using only nondestructive linac and e-beam measurements as inputs. We validate this approach with a simulation study for the FACET-II linac and with an experimental demonstration conducted at LCLS. At LCLS, the e-beam LPS images are obtained with a transverse deflecting cavity and used as training data for our ML model. In both the FACET-II and LCLS cases we find good agreement between the predicted and simulated/measured LPS profiles, an important step towards showing the feasibility of implementing such a virtual diagnostic on particle accelerators in the future.

Authors:: Emma, C.; Edelen, A.; Hogan, M. J.; O’Shea, B.; White, G.; Yakimenko, V.

Publication Date:: Fri Nov 16 00:00:00 EST 2018

Research Org.:: SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)

Sponsoring Org.:: USDOE

OSTI Identifier:: 1482420

Alternate Identifier(s):: OSTI ID: 1490386

Grant/Contract Number:: AC02-76SF00515

Resource Type:: Published Article

Journal Name:: Physical Review Accelerators and Beams

Additional Journal Information:: Journal Name: Physical Review Accelerators and Beams Journal Volume: 21 Journal Issue: 11; Journal ID: ISSN 2469-9888

Publisher:: American Physical Society

Country of Publication:: United States

Language:: English

Subject:: 43 PARTICLE ACCELERATORS

Citation Formats


                    Emma, C., Edelen, A., Hogan, M. J., O’Shea, B., White, G., and Yakimenko, V. Machine learning-based longitudinal phase space prediction of particle accelerators.  United States: N. p., 2018. 
Web.  doi:10.1103/PhysRevAccelBeams.21.112802.

Copy to clipboard


                    Emma, C., Edelen, A., Hogan, M. J., O’Shea, B., White, G., & Yakimenko, V. Machine learning-based longitudinal phase space prediction of particle accelerators.  United States.  https://doi.org/10.1103/PhysRevAccelBeams.21.112802

Copy to clipboard


                    Emma, C., Edelen, A., Hogan, M. J., O’Shea, B., White, G., and Yakimenko, V. Fri .  
"Machine learning-based longitudinal phase space prediction of particle accelerators".  United States.  https://doi.org/10.1103/PhysRevAccelBeams.21.112802.

Copy to clipboard


                    
@article{osti_1482420,

  title        = {Machine learning-based longitudinal phase space prediction of particle accelerators},

  author       = {Emma, C. and Edelen, A. and Hogan, M. J. and O’Shea, B. and White, G. and Yakimenko, V.},

  abstractNote = {Here, we report on the application of machine learning (ML) methods for predicting the longitudinal phase space (LPS) distribution of particle accelerators. Our approach consists of training a ML-based virtual diagnostic to predict the LPS using only nondestructive linac and e-beam measurements as inputs. We validate this approach with a simulation study for the FACET-II linac and with an experimental demonstration conducted at LCLS. At LCLS, the e-beam LPS images are obtained with a transverse deflecting cavity and used as training data for our ML model. In both the FACET-II and LCLS cases we find good agreement between the predicted and simulated/measured LPS profiles, an important step towards showing the feasibility of implementing such a virtual diagnostic on particle accelerators in the future.},

  doi          = {10.1103/PhysRevAccelBeams.21.112802},

  journal      = {Physical Review Accelerators and Beams},

  number       = 11,

  volume       = 21,

  place        = {United States},

  year         = {Fri Nov 16 00:00:00 EST 2018},

  month        = {Fri Nov 16 00:00:00 EST 2018}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Publisher's Version of Record
https://doi.org/10.1103/PhysRevAccelBeams.21.112802

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 47 works

Citation information provided by
Web of Science

Figures / Tables:

FIG. 1: Schematic of the FACET-II and LCLS electron accelerators and example LPS profiles from particle tracking simulations (FACET-II), experimental measurements (LCLS) and from the ML-based virtual diagnostic predictions. The figure highlights the similarities between the two accelerator layouts up to the BC20 chicane in FACET-II which is used tomore »

All figures and tables (5 total)

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Ultralow emittance electron beams from a laser-wakefield accelerator
journal, November 2012

Weingartner, R.; Raith, S.; Popp, A.
Physical Review Special Topics - Accelerators and Beams, Vol. 15, Issue 11
DOI: 10.1103/PhysRevSTAB.15.111302

Demonstration of Model-Independent Control of the Longitudinal Phase Space of Electron Beams in the Linac-Coherent Light Source with Femtosecond Resolution
journal, July 2018

Scheinker, Alexander; Edelen, Auralee; Bohler, Dorian
Physical Review Letters, Vol. 121, Issue 4
DOI: 10.1103/PhysRevLett.121.044801

Model-Free Stabilization by Extremum Seeking
book, January 2017

Scheinker, Alexander; Krstić, Miroslav
SpringerBriefs in Electrical and Computer Engineering
DOI: 10.1007/978-3-319-50790-3

Adaptive method for electron bunch profile prediction
journal, October 2015

Scheinker, Alexander; Gessner, Spencer
Physical Review Special Topics - Accelerators and Beams, Vol. 18, Issue 10
DOI: 10.1103/PhysRevSTAB.18.102801

Deep learning
journal, May 2015

LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
Nature, Vol. 521, Issue 7553
DOI: 10.1038/nature14539

Measured Emittance Dependence on the Injection Method in Laser Plasma Accelerators
journal, September 2017

Barber, S. K.; van Tilborg, J.; Schroeder, C. B.
Physical Review Letters, Vol. 119, Issue 10
DOI: 10.1103/PhysRevLett.119.104801

Few-femtosecond time-resolved measurements of X-ray free-electron lasers
journal, April 2014

Behrens, C.; Decker, F. -J.; Ding, Y.
Nature Communications, Vol. 5, Issue 1
DOI: 10.1038/ncomms4762

Plasma wakefield acceleration experiments at FACET II
journal, January 2018

Joshi, C.; Adli, E.; An, W.
Plasma Physics and Controlled Fusion, Vol. 60, Issue 3
DOI: 10.1088/1361-6587/aaa2e3

Neural Networks for Modeling and Control of Particle Accelerators
journal, April 2016

Edelen, A. L.; Biedron, S. G.; Chase, B. E.
IEEE Transactions on Nuclear Science, Vol. 63, Issue 2
DOI: 10.1109/TNS.2016.2543203

Coherent off-axis undulator radiation from short electron bunches
journal, March 2000

Neuman, C. P.; Graves, W. S.; O'Shea, P. G.
Physical Review Special Topics - Accelerators and Beams, Vol. 3, Issue 3
DOI: 10.1103/PhysRevSTAB.3.030701

Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning
journal, June 2017

Sanchez-Gonzalez, A.; Micaelli, P.; Olivier, C.
Nature Communications, Vol. 8, Issue 1
DOI: 10.1038/ncomms15461

Works referencing / citing this record:

Model-Independent Tuning for Maximizing Free Electron Laser Pulse Energy
text, January 2019

Scheinker, Alexander; Bohler, Dorian; Tomin, Sergey
Deutsches Elektronen-Synchrotron, DESY, Hamburg
DOI: 10.3204/pubdb-2019-05406

Figures / Tables found in this record:

Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.

Similar Records in DOE PAGES and OSTI.GOV collections:

Adaptive machine learning for time-varying systems: low dimensional latent space tuning

Journal Article Scheinker, Alexander - Journal of Instrumentation

Machine learning (ML) tools such as encoder-decoder convolutional neural networks (CNN) can represent incredibly complex nonlinear functions which map between combinations of images and scalars. For example, CNNs can be used to map combinations of accelerator parameters and images which are 2D projections of the 6D phase space distributions of charged particle beams as they are transported between various particle accelerator locations. Despite their strengths, applying ML to time-varying systems, or systems with shifting distributions, is an open problem, especially for large systems for which collecting new data for re-training is impractical or interrupts operations. Particle accelerators are one examplemore »« less
https://doi.org/10.1088/1748-0221/16/10/p10008

Full Text Available
Improving surrogate model accuracy for the LCLS-II injector frontend using convolutional neural networks and transfer learning

Journal Article Gupta, Lipi ; Edelen, Auralee ; Neveu, Nicole ; ... - Machine Learning: Science and Technology

Machine learning (ML) models of accelerator systems ('surrogate models') are able to provide fast, accurate predictions of accelerator physics phenomena. However, approaches to date typically do not include measured input diagnostics, such as the initial beam distributions, which are critical for accurately representing the beam evolution through the system. In addition, these inputs often vary over time, and models that can account for these changing conditions are needed. As beam time for measurements is often limited, simulations are in some cases needed to provide sufficient training data. These typically represent the designed machine before construction; however, the behavior of themore »« less
https://doi.org/10.1088/2632-2153/ac27ff
Adaptive model tuning studies for non-invasive diagnostics and feedback control of plasma wakefield acceleration at FACET-II

Journal Article Scheinker, Alexander ; Gessner, Spencer ; Emma, Claudio ; ... - Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment

Beam-driven plasma wakefield acceleration (PWFA) achieves the same energy gain in a single meter, for which conventional accelerators require several kilometers, however much work is still required to match the beam quality of conventional accelerators. The PWFA processes to be studied at the FACET-II facility will utilize extremely short (down to a few fs) high energy (10 GeV), high charge (few nC) electron and eventually positron bunches. The PWFA process is extremely sensitive to the detailed longitudinal current profiles of these bunches and it would be of great benefit to have precise measurement and control of these profiles. We presentmore »« less
Cited by 7
https://doi.org/10.1016/j.nima.2020.163902

Full Text Available
Virtual Diagnostic Suite for Electron Beam Prediction and Control at FACET-II

Journal Article Emma, Claudio ; Edelen, Auralee ; Hanuka, Adi ; ... - Information

We discuss the implementation of a suite of virtual diagnostics at the FACET-II facility currently under commissioning at SLAC National Accelerator Laboratory. The diagnostics will be used for the prediction of the longitudinal phase space along the linac, spectral reconstruction of the bunch profile, and non-destructive inference of transverse beam quality (emittance) while using edge radiation at the injector dogleg and bunch compressor locations. These measurements will be folded into adaptive feedbacks and Machine Learning (ML)-based reinforcement learning controls to improve the stability and optimize the performance of the machine for different experimental configurations. In this paper we describe eachmore »« less
https://doi.org/10.3390/info12020061
Multipoint-BAX: a new approach for efficiently tuning particle accelerator emittance via virtual objectives

Journal Article Ayoub Miskovich, Sara ; Neiswanger, Willie ; Colocho, William ; ... - Machine Learning: Science and Technology

Abstract Although beam emittance is critical for the performance of high-brightness accelerators, optimization is often time limited as emittance calculations, commonly done via quadrupole scans, are typically slow. Such calculations are a type of multipoint query , i.e. each query requires multiple secondary measurements. Traditional black-box optimizers such as Bayesian optimization are slow and inefficient when dealing with such objectives as they must acquire the full series of measurements, but return only the emittance, with each query. We propose a new information-theoretic algorithm, Multipoint-BAX , for black-box optimization on multipoint queries, which queries and models individual beam-size measurements using techniquesmore »« less
https://doi.org/10.1088/2632-2153/ad169f

Similar Records

Title: Machine learning-based longitudinal phase space prediction of particle accelerators

Abstract

Citation Formats

Figures / Tables:

Ultralow emittance electron beams from a laser-wakefield accelerator journal, November 2012

Demonstration of Model-Independent Control of the Longitudinal Phase Space of Electron Beams in the Linac-Coherent Light Source with Femtosecond Resolution journal, July 2018

Model-Free Stabilization by Extremum Seeking book, January 2017

Adaptive method for electron bunch profile prediction journal, October 2015

Deep learning journal, May 2015

Measured Emittance Dependence on the Injection Method in Laser Plasma Accelerators journal, September 2017

Few-femtosecond time-resolved measurements of X-ray free-electron lasers journal, April 2014

Plasma wakefield acceleration experiments at FACET II journal, January 2018

Neural Networks for Modeling and Control of Particle Accelerators journal, April 2016

Coherent off-axis undulator radiation from short electron bunches journal, March 2000

Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning journal, June 2017

Model-Independent Tuning for Maximizing Free Electron Laser Pulse Energy text, January 2019

Ultralow emittance electron beams from a laser-wakefield accelerator
journal, November 2012

Demonstration of Model-Independent Control of the Longitudinal Phase Space of Electron Beams in the Linac-Coherent Light Source with Femtosecond Resolution
journal, July 2018

Model-Free Stabilization by Extremum Seeking
book, January 2017

Adaptive method for electron bunch profile prediction
journal, October 2015

Deep learning
journal, May 2015

Measured Emittance Dependence on the Injection Method in Laser Plasma Accelerators
journal, September 2017

Few-femtosecond time-resolved measurements of X-ray free-electron lasers
journal, April 2014

Plasma wakefield acceleration experiments at FACET II
journal, January 2018

Neural Networks for Modeling and Control of Particle Accelerators
journal, April 2016

Coherent off-axis undulator radiation from short electron bunches
journal, March 2000

Accurate prediction of X-ray pulse properties from a free-electron laser using machine learning
journal, June 2017

Model-Independent Tuning for Maximizing Free Electron Laser Pulse Energy
text, January 2019