There is a newer version of this record available.

Report Open Access

Using deep learning for particle identification and energy estimation in CMS HGCAL L1 trigger

Anwesha Bhattacharya

In run 4 of the LHC, the extreme high luminosity is expected to generate an enormous pileup of up to 200 
proton-proton collisions for each bunch crossing. This has to be read out at 750 kHz with a maximum 
latency of  12.5𝜇s. In order to disentangle the energy from pileup collision, the upgraded CMS detector for 
Run-4 will feature a new High Granularity Calorimeter (HGCAL) with unprecedented lateral and 
longitudinal segmentation. The total number of channels read out into the Level-1 trigger processor will be 
of the order of 106. To process this data with such small latency, we need to develop sophisticated 
algorithms. In this report, we aim to use machine learning techniques for electron-photon identification and 
energy estimation in the L1 Trigger. The idea is to implement the architectures on FPGA boards that will 
have fast inference, enough to cope with the requirements of the HGCAL. 

Files (821.5 kB)
Name Size
Report_Anwesha_Bhattacharya.pdf
md5:f6178c043156f7151943a6a6a4c0c41f
821.5 kB Download
368
303
views
downloads
All versions This version
Views 368328
Downloads 303275
Data volume 261.5 MB225.9 MB
Unique views 327304
Unique downloads 273256

Share

Cite as