Towards a Computer Vision Particle Flow

by Sanmay Ganguly

Weizmann Institute
at Particles and Fields Seminar

Mon, 14 Dec 2020, 14:00


In high energy physics experiments Particle Flow (PFlow) algorithms are designed to reach optimal calorimeter reconstruction and jet energy resolution.

A computer vision approach to PFlow reconstruction using deep Neural Network techniques based on Convolutional layers (cPFlow) is proposed.
The algorithm is trained to learn, from calorimeter and charged particle track images, to distinguish the calorimeter energy deposits from neutral and charged particles in a non-trivial context, where the energy originated by a π+ and a π0 is overlapping within calorimeter clusters. The performance of the cPFlow and a traditional parametrized PFlow (pPFlow) algorithm are compared.

The cPFlow provides a precise reconstruction of the neutral and charged energy in the calorimeter and therefore outperform more traditional pPFlow algorithm both, in energy response and position resolution. We will demonstrate the performance comparison between several neural networks. Also we will introduce the concept of super-resolution for calorimeter studies and demonstrate its effectiveness.

We will conclude the talk by highlighting future possible extensions to these ideas.

Join Zoom Meeting

Meeting ID: 836 8757 3946
Passcode: 345123

Created on 09-12-2020 by Palti, Eran (palti)
Updaded on 09-12-2020 by Palti, Eran (palti)