End-to-end multi-particle reconstruction in high occupancy imaging calorimeters with graph neural networks
This addresses particle reconstruction in high-energy physics experiments, such as the CMS detector upgrade, and is incremental as it builds on graph neural networks and object condensation techniques.
The paper tackles the problem of reconstructing particles from detector hits in high-occupancy calorimeters, achieving single-shot reconstruction of around 1000 particles under high-luminosity conditions with 200 pileup, with performance evaluated in terms of efficiency and energy resolution.
We present an end-to-end reconstruction algorithm to build particle candidates from detector hits in next-generation granular calorimeters similar to that foreseen for the high-luminosity upgrade of the CMS detector. The algorithm exploits a distance-weighted graph neural network, trained with object condensation, a graph segmentation technique. Through a single-shot approach, the reconstruction task is paired with energy regression. We describe the reconstruction performance in terms of efficiency as well as in terms of energy resolution. In addition, we show the jet reconstruction performance of our method and discuss its inference computational cost. To our knowledge, this work is the first-ever example of single-shot calorimetric reconstruction of ${\cal O}(1000)$ particles in high-luminosity conditions with 200 pileup.