EUVIMEDEUVIMED entdecken
Crossref

Physics-informed graph neural networks for transverse momentum estimation in CMS trigger systems

Md Abrar Jahin, Shahriar Soudeep, M.F. Mridha, Muhammad Mostafa Monowar, Md Abdul Hamid

Computer Physics Communications · 2026-08 · 325 · 110167

DOI: 10.1016/j.cpc.2026.110167 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Physics Communications, 2026-08. Verfasst von Md Abrar Jahin und 4 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-time particle transverse momentum ($p_T$) estimation in high-energy physics demands algorithms that are both efficient and accurate under strict hardware constraints. Static machine learning models degrade under high pileup and lack physics-aware optimization, while generic graph neural networks (GNNs) often neglect domain structure critical for robust $p_T$ regression. We propose a physics-informed GNN framework that systematically encodes detector geometry and physical observables through four distinct graph construction strategies that systematically encode detector geometry and physical observables: station-as-node, feature-as-node, bending angle-centric, and pseudorapidity ($\eta$)-centric representations. This framework integrates these tailored graph structures with a novel Message Passing Layer (MPL), featuring intra-message attention and gated updates, and domain-specific loss functions incorporating $p_{T}$-distribution priors. Our co-design methodology yields superior accuracy-efficiency trade-offs compared to existing baselines. Extensive experiments on the CMS Trigger Dataset validate the approach: a station-informed EdgeConv model achieves a state-of-the-art MAE of 0.8525 with $\ge55\%$ fewer parameters than deep learning baselines, especially TabNet, while an $\eta$-centric MPL configuration also demonstrates improved accuracy with comparable efficiency. These results establish the promise of physics-guided GNNs for deployment in resource-constrained trigger systems.

Zitieren

APA

Jahin, M. A., Soudeep, S., Mridha, M., Monowar, M. M., & Hamid, M. A. (2026). Physics-informed graph neural networks for transverse momentum estimation in CMS trigger systems. Computer Physics Communications, 325, 110167. https://doi.org/10.1016/j.cpc.2026.110167

Vancouver

Jahin MA, Soudeep S, Mridha M, Monowar MM, Hamid MA. Physics-informed graph neural networks for transverse momentum estimation in CMS trigger systems. Computer Physics Communications. 2026;325:110167. doi:10.1016/j.cpc.2026.110167

BibTeX
@article{Jahin2026,
  author = {Jahin, Md Abrar and Soudeep, Shahriar and Mridha, M.F. and Monowar, Muhammad Mostafa and Hamid, Md Abdul},
  title = {Physics-informed graph neural networks for transverse momentum estimation in CMS trigger systems},
  journal = {Computer Physics Communications},
  year = {2026},
  volume = {325},
  pages = {110167},
  doi = {10.1016/j.cpc.2026.110167}
}
Kostenlos starten →