Dark matter-induced electron excitations in silicon and germanium with deep learning
Artikel i vetenskaplig tidskrift, 2025
We train a deep neural network (DNN) to output rates of dark matter (DM) induced electron excitations in silicon and germanium detectors. Our DNN provides a massive speedup of around 5 orders of magnitude relative to existing methods (i.e., qedark-eft), allowing for extensive parameter scans in the event of an observed DM signal. The network is also lighter and simpler to use than alternative computational frameworks based on a direct calculation of the DM-induced excitation rate.
Författare
Riccardo Catena
Chalmers, Fysik, Subatomär, högenergi- och plasmafysik
Einar Urdshals
Chalmers, Fysik, Subatomär, högenergi- och plasmafysik
Physical Review D - Particles, Fields, Gravitation and Cosmology
24700010 (ISSN) 24700029 (eISSN)
Vol. 111 1 L011702Susceptibilitet och materialeffeker i mörk materias spridning mot elektroner
Vetenskapsrådet (VR) (2022-04299), 2023-01-01 -- 2026-12-31.
Light Dark Matter
Knut och Alice Wallenbergs Stiftelse (.), 2020-07-01 -- 2025-06-30.
Ämneskategorier (SSIF 2025)
Subatomär fysik
DOI
10.1103/PhysRevD.111.L011702
Relaterade dataset
DEDD: Dark matter Electron scattering Direct detection from Deep learning [dataset]
URI: https://github.com/urdshals/DEDD