Abstract
In High Energy Physics experiments Particle Flow (PFlow) algorithms are designed to provide an optimal reconstruction of the nature and kinematic properties of the particles produced within the detector acceptance during collisions. At the heart of PFlow algorithms is the ability to distinguish the calorimeter energy deposits of neutral particles from those of charged particles, using the complementary measurements of charged particle tracking devices, to provide a superior measurement of the particle content and kinematics. In this paper, a computer vision approach to this fundamental aspect of PFlow algorithms, based on calorimeter images, is proposed. A comparative study of the state of the art deep learning techniques is performed. A significantly improved reconstruction of the neutral particle calorimeter energy deposits is obtained in a context of large overlaps with the deposits from charged particles. Calorimeter images with augmented finer granularity are also obtained using super-resolution techniques.
Highlights
That constitute the event, which for the most part are charged and neutral hadrons, photons, electrons, muons, and neutrinos
In High Energy Physics experiments Particle Flow (PFlow) algorithms are designed to provide an optimal reconstruction of the nature and kinematic properties of the particles produced within the detector acceptance during collisions
We explore the capabilities of computer vision algorithms, along with graph and deep set Neural Networks (NN), to provide solutions to this complex question in a context of two overlapping particles, a charged and a neutral pion π + and π 0
Summary
The goal of Particle Flow (PFlow) algorithms is to make optimal use of these complementary measurements to reconstruct the particle content and its energy response for the entire event. We explore the capabilities of computer vision algorithms, along with graph and deep set Neural Networks (NN), to provide solutions to this complex question in a context of two overlapping particles, a charged and a neutral pion π + and π 0 This benchmark is highly representative in hadron collisions or jet environments in electron-positron collisions and served for instance as foundation to develop and tune the PFlow algorithm of the ATLAS experiment [3]. The approach adopted in this paper does not attempt the complete leap from the detector signals to fully identified high-level Particle Flow objects It is a first intermediate step focusing on the reconstruction of a precise calorimeter image of the neutral particles in the event, using several NN architectures, including Convolution Neural Networks (ConvNet, UNet), Graph Neural Networks (Graph), and Deep Sets (DeepSet). ECAL1 (3 X0 ) ECAL2 (16 X0 ) ECAL3 ( 6 X0 ) HCAL1 ( 1.5 λint ) HCAL2 (4.1 λint ) HCAL3 (1.8 λint )
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
