Fast Data-Driven Simulation of Cherenkov Detectors Using Generative Adversarial Networks
The increasing luminosities of future Large Hadron Collider runs and next generation of collider experiments will require an unprecedented amount of simulated events to be produced. Such large scale productions are extremely demanding in terms of computing resources. Thus new approaches to event generation and simulation of detector responses are needed. In LHCb, the accurate simulation of Cherenkov detectors takes a sizeable fraction of CPU time. An alternative approach is described here, when one generates high-level reconstructed observables using a generative neural network to bypass low level details. This network is trained to reproduce the particle species likelihood function values based on the track kinematic parameters and detector occupancy. The fast simulation is trained using real data samples collected by LHCb during run 2. We demonstrate that this approach provides high-fidelity results.
Citations by journals
1
2
|
|
Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
|
Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment
2 publications, 20%
|
Journal of Instrumentation
|
Journal of Instrumentation
2 publications, 20%
|
SciPost Physics
|
SciPost Physics, 2, 20%
SciPost Physics
2 publications, 20%
|
European Physical Journal C
|
European Physical Journal C
1 publication, 10%
|
Computing and Software for Big Science
|
Computing and Software for Big Science
1 publication, 10%
|
Reviews of Modern Physics
|
Reviews of Modern Physics
1 publication, 10%
|
Physical Review A
|
Physical Review A
1 publication, 10%
|
1
2
|
Citations by publishers
1
2
|
|
Elsevier
|
Elsevier
2 publications, 20%
|
Springer Nature
|
Springer Nature
2 publications, 20%
|
IOP Publishing
|
IOP Publishing
2 publications, 20%
|
Stichting SciPost
|
Stichting SciPost, 2, 20%
Stichting SciPost
2 publications, 20%
|
American Physical Society (APS)
|
American Physical Society (APS)
2 publications, 20%
|
1
2
|
- We do not take into account publications that without a DOI.
- Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
- Statistics recalculated weekly.