EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders

Farouk Mokhtar, Joosep Pata, Dolores Garcia, Eric Wulff, Mengke Zhang, Michael Kagan, Javier Duarte

Physical Review D · 29.05.2025 · 111 (9)

DOI: 10.1103/physrevd.111.092015 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physical Review D, online erschienen am 29.05.2025. Verfasst von Farouk Mokhtar und 6 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Corporation for Science Advancement, Alfred P. Sloan Foundation, U.S. Department of Energy.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We demonstrate transfer learning capabilities in a machine-learned algorithm trained for particle-flow reconstruction in high energy particle colliders. This paper presents a cross-detector fine-tuning study, where we initially pretrain the model on a large full simulation dataset from one detector design, and subsequently fine-tune the model on a sample with a different collider and detector design. Specifically, we use the Compact Linear Collider detector (CLICdet) model for the initial training set and demonstrate successful knowledge transfer to the CLIC-like detector (CLD) proposed for the Future Circular Collider in electron-positron mode. We show that with an order of magnitude less samples from the second dataset, we can achieve the same performance as a costly training from scratch, across particle-level and event-level performance metrics, including jet and missing transverse momentum resolution. Furthermore, we find that the fine-tuned model achieves comparable performance to the traditional rule-based particle-flow approach on event-level metrics after training on 100,000 CLD events, whereas a model trained from scratch requires at least 1 million CLD events to achieve similar reconstruction performance. To our knowledge, this represents the first full-simulation cross-detector transfer learning study for particle-flow reconstruction. These findings offer valuable insights towards building large foundation models that can be fine-tuned across different detector designs and geometries, helping to accelerate the development cycle for new detectors and opening the door to rapid detector design and optimization using machine learning.

Förderung

  • Research Corporation for Science Advancement
  • Alfred P. Sloan Foundation
  • U.S. Department of Energy
  • Office of Science
  • High Energy Physics
  • National Science Foundation
  • Eesti Teadusagentuur
  • European Regional Development Fund

Zitieren

APA

Mokhtar, F., Pata, J., Garcia, D., Wulff, E., Zhang, M., Kagan, M., & Duarte, J. (2025). Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders. Physical Review D, 111(9). https://doi.org/10.1103/physrevd.111.092015

Vancouver

Mokhtar F, Pata J, Garcia D, Wulff E, Zhang M, Kagan M, et al. Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders. Physical Review D. 2025;111(9). doi:10.1103/physrevd.111.092015

BibTeX
@article{Mokhtar2025,
  author = {Mokhtar, Farouk and Pata, Joosep and Garcia, Dolores and Wulff, Eric and Zhang, Mengke and Kagan, Michael and Duarte, Javier},
  title = {Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders},
  journal = {Physical Review D},
  year = {2025},
  volume = {111},
  number = {9},
  doi = {10.1103/physrevd.111.092015}
}
Kostenlos starten →