Perspectives on the Calibration of CNN Energy Reconstruction in Highly Granular Calorimeters

Abstract

A: We present a study which shows encouraging stability of the response linearity for a simulated high granularity calorimeter module reconstructed by a CNN model to miscalibration, bias, and noise effects. Our results also show an intuitive, quantifiable relationship between these factors and the calibration parameters. We trained a CNN model to reconstruct energy in the calorimeter module using simulated single-pion events; we then observed the response of the model under various miscalibration, bias, and noise conditions that affected the model input. From these data, we estimated linear response models to calibrate the CNN. We also quantified the relationship between these factors and the calibration parameters by regression analysis.

The optimal use of segmentation for sampling calorimeters

“…Deep neural networks can readily process the lowest-level information within a cluster of cells produced from an electromagnetic or hadronic shower. Previous studies on calorimeter energy estimation and particle identification for collider experiments have shown that utilizing this information outperforms existing approaches and provides an excellent approximation to the optimal reconstruction [3][4][5][6][7][8][9][10][11]. Most importantly, machine learning approaches are constructed automatically, enabling hardware design to be guided by approximately optimal software utilization.…”

Learning Uncertainties the Frequentist Way: Calibration and Correlation in High Energy Physics

“…This inference task can be challenging when the reconstruction requires high-dimensional inputs. Machine learning (ML) is a natural tool for performing high-dimensional reconstruction, and there has been significant progress in utilizing ML method for estimating the energies of various objects, including photons [1], muons [2], single hadrons [3][4][5][6][7][8], and sprays of hadrons (jets) [9][10][11][12][13][14][15][16][17][18][19] at colliders; kinematic reconstruction in deep inelastic scattering [20,21]; and neutrino energies in a variety of experiments [22][23][24][25][26][27]. Further ideas can be found at Ref.…”

Bias and Priors in Machine Learning Calibrations for High Energy Physics

“…In particular, machine learning methods can readily process high-dimensional inputs and therefore can incorporate more information to improve the precision and accuracy of a calibration. There have been a large number of proposals for improving the simulationbased calibrations of various object energies, including single hadrons [16][17][18][19][20][21], muons [22], and jets [23][24][25][26][27][28][29][30][31][32][33] at colliders; kinematic reconstruction in deep inelastic scattering [34]; and neutrino energies in a variety of experiments [35][36][37][38][39][40]. Further ideas can be found in Ref.…”