Fast prediction of electron-beam parameters using transfer maps and machine learning in a digital model of a MeV γγ collider
Abstract
Tuning the electron beam of a MeV-scale γγ collider, first in the design and later in a digital twin of the machine, requires the beam parameters at the interaction point (IP) for many injector states. Start-to-end particle tracking is too slow for this and needs the full particle distribution, which an operating machine cannot measure. We address this problem for the 200-MeV transport line of the collider with two fast predictors. For design, second-order transfer maps from the transport entrance to the IP are applied to every particle. For a digital twin, an extremely-randomized-trees (ExtraTrees) model predicts the IP parameters from the means and rms widths of the beam at the transport entrance. On 89 held-out start-to-end simulations, the map predictor reproduces Elegant tracking for the mean energy, momentum spread, bunch length, transverse rms sizes and normalized emittances with coefficients of determination (R2) of 0.97--1.00 and is ten times faster. The ExtraTrees model reaches an average R2 of 0.88, compared with 0.58 when the injector settings are used as input, and performs similarly with eleven inputs that can be measured or reconstructed. Under a 2% input perturbation, the average R2 of the six parameters other than the mean energy decreases only from 0.917 to 0.895, whereas the mean energy requires an accurate momentum calibration. The two predictors provide the IP-beam evaluation for the collider design and the prediction layer of a future digital twin.
Related
- Machine Learning for Invisible Dark Boson Searches at the Electron-Ion Collider
- Polarized Nuclear DVCS at the Electron-Ion Collider
- Dihadron azimuthal asymmetry and light-quark dipole moments at the Electron-Ion Collider
- Quantum tomography at the Electron-Ion Collider
- QCD corrections to light-quark dipole sensitivity via transverse spin asymmetries at the Electron-Ion Collider
BibTeX
@misc{zhang2026fast,
title = {{Fast prediction of electron-beam parameters using transfer maps and machine learning in a digital model of a MeV $γγ$ collider}},
author = {Jiawei Zhang and Yongsheng Huang and Yuancun Nie and Qiang Gu and Yuan Chen and Yuanjie Bi},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.08036},
eprint = {2611.08036},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.08036},
}
RIS
TY - UNPB
TI - Fast prediction of electron-beam parameters using transfer maps and machine learning in a digital model of a MeV γγ collider
AU - Jiawei Zhang
AU - Yongsheng Huang
AU - Yuancun Nie
AU - Qiang Gu
AU - Yuan Chen
AU - Yuanjie Bi
PY - 2026
DA - 2026/11/05
PB - arXiv
DO - 10.48550/arxiv.2611.08036
UR - https://arxiv.org/abs/2611.08036
AB - Tuning the electron beam of a MeV-scale γγ collider, first in the design and later in a digital twin of the machine, requires the beam parameters at the interaction point (IP) for many injector states. Start-to-end particle tracking is too slow for this and needs the full particle distribution, which an operating machine cannot measure. We address this problem for the 200-MeV transport line of the collider with two fast predictors. For design, second-order transfer maps from the transport entrance to the IP are applied to every particle. For a digital twin, an extremely-randomized-trees (ExtraTrees) model predicts the IP parameters from the means and rms widths of the beam at the transport entrance. On 89 held-out start-to-end simulations, the map predictor reproduces Elegant tracking for the mean energy, momentum spread, bunch length, transverse rms sizes and normalized emittances with coefficients of determination (R^2) of 0.97--1.00 and is ten times faster. The ExtraTrees model reaches an average R^2 of 0.88, compared with 0.58 when the injector settings are used as input, and performs similarly with eleven inputs that can be measured or reconstructed. Under a 2% input perturbation, the average R^2 of the six parameters other than the mean energy decreases only from 0.917 to 0.895, whereas the mean energy requires an accurate momentum calibration. The two predictors provide the IP-beam evaluation for the collider design and the prediction layer of a future digital twin.
ER -