Multi-facility virtual diagnostic for longitudinal phase space predictions
Lundquist, Johan LU ; Björklund Svensson, Jonas LU
; Dijkstal, Philip
; Mansten, Erik
LU
; Penco, Giuseppe
; Werin, Sverker
LU
and Curbis, Francesca
LU
(2026)
In Scientific Reports
16.
- Abstract
- A thorough understanding of the longitudinal phase space (LPS) of the electron beam is of great advantage to any modern linear accelerator (linac), and of critical importance for operating a free electron laser (FEL). While a transverse deflecting structure (TDS) allows full characterization of a beam’s LPS, measurements with a TDS system are often destructive and operationally complex. We present an application of machine learning in the form of a virtual diagnostic (VD) trained on destructive TDS measurements, which allows for online predictions of the beam’s LPS based on non-destructive measurements. We show the development and testing of such virtual diagnostics for three different accelerators: the MAX IV linac and the FELs FERMI and... (More)
- A thorough understanding of the longitudinal phase space (LPS) of the electron beam is of great advantage to any modern linear accelerator (linac), and of critical importance for operating a free electron laser (FEL). While a transverse deflecting structure (TDS) allows full characterization of a beam’s LPS, measurements with a TDS system are often destructive and operationally complex. We present an application of machine learning in the form of a virtual diagnostic (VD) trained on destructive TDS measurements, which allows for online predictions of the beam’s LPS based on non-destructive measurements. We show the development and testing of such virtual diagnostics for three different accelerators: the MAX IV linac and the FELs FERMI and SwissFEL. We show how a single, general network architecture and training procedure can be used to reach reliable predictions of the LPS for all three facilities, achieving R2
scores reaching 90% or higher across all test datasets. Further, we describe how a simplified architecture can be used for predicting key beam parameters of interest extracted from the full LPS, such as bunch length and slice energy chirp. Our results show how a generalizable VD framework can be rapidly deployed across multiple facilities to enable online monitoring of the beam LPS. For future work, we suggest how virtual diagnostics could be further developed to suit the specific needs of operations at each facility. (Less) - Abstract (Swedish)
- A thorough understanding of the longitudinal phase space (LPS) of the electron beam is of great advantage to any modern linear accelerator (linac), and of critical importance for operating a free electron laser (FEL). While a transverse deflecting structure (TDS) allows full characterization of a beam’s LPS, measurements with a TDS system are often destructive and operationally complex. We present an application of machine learning in the form of a virtual diagnostic (VD) trained on destructive TDS measurements, which allows for online predictions of the beam’s LPS based on non-destructive measurements. We show the development and testing of such virtual diagnostics for three different accelerators: the MAX IV linac and the FELs FERMI and... (More)
- A thorough understanding of the longitudinal phase space (LPS) of the electron beam is of great advantage to any modern linear accelerator (linac), and of critical importance for operating a free electron laser (FEL). While a transverse deflecting structure (TDS) allows full characterization of a beam’s LPS, measurements with a TDS system are often destructive and operationally complex. We present an application of machine learning in the form of a virtual diagnostic (VD) trained on destructive TDS measurements, which allows for online predictions of the beam’s LPS based on non-destructive measurements. We show the development and testing of such virtual diagnostics for three different accelerators: the MAX IV linac and the FELs FERMI and SwissFEL. We show how a single, general network architecture and training procedure can be used to reach reliable predictions of the LPS for all three facilities, achieving R² scores reaching 90% or higher across all test datasets. Further, we describe how a simplified architecture can be used for predicting key beam parameters of interest extracted from the full LPS, such as bunch length and slice energy chirp. Our results show how a generalizable VD framework can be rapidly deployed across multiple facilities to enable online monitoring of the beam LPS. For future work, we suggest how virtual diagnostics could be further developed to suit the specific needs of operations at each facility. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/bc4403e7-1fd3-408e-8d5b-b6bb781906ff
- author
- Lundquist, Johan
LU
; Björklund Svensson, Jonas
LU
; Dijkstal, Philip
; Mansten, Erik
LU
; Penco, Giuseppe
; Werin, Sverker
LU
and Curbis, Francesca
LU
- organization
- publishing date
- 2026-04-09
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Accelerator Physics, Machine Learning, longitudinal diagnostics
- in
- Scientific Reports
- volume
- 16
- article number
- 12021
- pages
- 11 pages
- publisher
- Nature Publishing Group
- external identifiers
-
- pmid:41957454
- scopus:105035470547
- ISSN
- 2045-2322
- DOI
- 10.1038/s41598-026-47195-1
- project
- Machine learning tools applied to linacs and FELs
- language
- English
- LU publication?
- yes
- id
- bc4403e7-1fd3-408e-8d5b-b6bb781906ff
- date added to LUP
- 2026-04-10 15:03:37
- date last changed
- 2026-05-25 04:01:32
@article{bc4403e7-1fd3-408e-8d5b-b6bb781906ff,
abstract = {{A thorough understanding of the longitudinal phase space (LPS) of the electron beam is of great advantage to any modern linear accelerator (linac), and of critical importance for operating a free electron laser (FEL). While a transverse deflecting structure (TDS) allows full characterization of a beam’s LPS, measurements with a TDS system are often destructive and operationally complex. We present an application of machine learning in the form of a virtual diagnostic (VD) trained on destructive TDS measurements, which allows for online predictions of the beam’s LPS based on non-destructive measurements. We show the development and testing of such virtual diagnostics for three different accelerators: the MAX IV linac and the FELs FERMI and SwissFEL. We show how a single, general network architecture and training procedure can be used to reach reliable predictions of the LPS for all three facilities, achieving <i>R</i><sup>2</sup><br/> scores reaching 90% or higher across all test datasets. Further, we describe how a simplified architecture can be used for predicting key beam parameters of interest extracted from the full LPS, such as bunch length and slice energy chirp. Our results show how a generalizable VD framework can be rapidly deployed across multiple facilities to enable online monitoring of the beam LPS. For future work, we suggest how virtual diagnostics could be further developed to suit the specific needs of operations at each facility.}},
author = {{Lundquist, Johan and Björklund Svensson, Jonas and Dijkstal, Philip and Mansten, Erik and Penco, Giuseppe and Werin, Sverker and Curbis, Francesca}},
issn = {{2045-2322}},
keywords = {{Accelerator Physics; Machine Learning; longitudinal diagnostics}},
language = {{eng}},
month = {{04}},
publisher = {{Nature Publishing Group}},
series = {{Scientific Reports}},
title = {{Multi-facility virtual diagnostic for longitudinal phase space predictions}},
url = {{http://dx.doi.org/10.1038/s41598-026-47195-1}},
doi = {{10.1038/s41598-026-47195-1}},
volume = {{16}},
year = {{2026}},
}