Reconstructing the Kinematics of Deep Inelastic Scattering with Deep Learning

Arratia, Miguel; Britzger, Daniel; Long, Owen; Nachman, Benjamin

Lokale TagsFreigabegeschichteDetailsÜbersicht

Reconstructing the Kinematics of Deep Inelastic Scattering with Deep Learning

Arratia, M., Britzger, D., Long, O., & Nachman, B. (2022). Reconstructing the Kinematics of Deep Inelastic Scattering with Deep Learning. Nuclear Instruments and Methods in Physics Research Section A, 1025, 166164. Retrieved from https://publications.mppmu.mpg.de/?action=search&mpi=MPP-2021-174.

Item is Freigegeben

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:

Datensatz-Permalink: https://hdl.handle.net/21.11116/0000-000C-B513-2 Versions-Permalink: https://hdl.handle.net/21.11116/0000-000C-B514-1

Genre: Zeitschriftenartikel

ausblenden:

Urheber:
Arratia, Miguel¹, Autor
Britzger, Daniel¹, Autor
Long, Owen¹, Autor
Nachman, Benjamin¹, Autor

Affiliations:
1Max Planck Institute for Physics, Max Planck Society and Cooperation Partners, ou_2253650

Inhalt

einblenden:

ausblenden:

Schlagwörter: H1

Zusammenfassung: We introduce a method to reconstruct the kinematics of neutral-current deep inelastic scattering (DIS) using a deep neural network (DNN). Unlike traditional methods, it exploits the full kinematic information of both the scattered electron and the hadronic-final state, and it accounts for QED radiation by identifying events with radiated photons and event-level momentum imbalance. The method is studied with simulated events at HERA and the future Electron-Ion Collider (EIC). We show that the DNN method outperforms all the traditional methods over the full phase space, improving resolution and reducing bias. Our method has the potential to extend the kinematic reach of future experiments at the EIC, and thus their discovery potential in polarized and nuclear DIS.