Speaker
Description
At a 10TeV muon collider, a high level of beam induced background (BIB) will overlay signal produced from muon collisions, similar to how pile-up at the HL-LHC will overlay signal from proton-proton collisions. On-detector differentiation of BIB from signal would improve performance of the inner pixel tracker. Following the successful development of a prototype “smartpixel” application specific integrated circuit (ASIC) for hypothetical use in HL-LHC, we train analogous models to filter charge clusters of BIB from Signal based on cluster geometry in the first layer of the tracker at a muon collider. We explore the performance of 3 classes of smartpixel filter architectures and estimate their hardware usage using qkeras and hls4ml in order to develop a lightweight algorithm suitable for on-chip implementation.