Speaker
Description
In preparation for the High Luminosity LHC (HL-LHC) run, the CMS experiment is developing a major upgrade of its Level-1 (L1) Trigger system, which will integrate high-granularity calorimeter data and real-time tracking using FPGA-based processors connected via a high-bandwidth optical network. A central challenge is the identification of electrons in a high pileup environment within strict latency and resource constraints.
The contribution will focus on the identification of electron signatures with high efficiency and energy resolution. In this context, a machine learning–based algorithm that combines calorimeter and tracking information to perform electron identification in a single inference step is presented. The model is implemented with fixed-point arithmetic and optimized for fast, resource-efficient execution on FPGAs. A lightweight regression model to estimate the transverse momentum of the identified electrons, enhancing energy resolution, is also discussed. The improved energy accuracy is particularly relevant in the context of L1 scouting, where enriched event information is streamed for real-time analysis. The impact on a benchmark on a low-mass dark photon to dielectron resonance analysis is demonstrated.
