Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Calorimeter Shower Superresolution with Conditional Normalizing Flows: Implementation and Statistical Evaluation

Andrea Cosso

Abstract

In High Energy Physics, detailed calorimeter simulations and reconstructions are essential for accurate energy measurements and particle identification, but their high granularity makes them computationally expensive. Developing data-driven techniques capable of recovering fine-grained information from coarser readouts, a task known as calorimeter superresolution, offers a promising way to reduce both computational and hardware costs while preserving detector performance. This thesis investigates whether a generative model originally designed for fast simulation can be effectively applied to calorimeter superresolution. Specifically, the model proposed in arXiv:2308.11700 is re-implemented independently and trained on the CaloChallenge 2022 dataset based on the Geant4 Par04 calorimeter geometry. Finally, the model's performance is assessed through a rigorous statistical evaluation framework, following the methodology introduced in arXiv:2409.16336, to quantitatively test its ability to reproduce the reference distributions.

Calorimeter Shower Superresolution with Conditional Normalizing Flows: Implementation and Statistical Evaluation

Abstract

In High Energy Physics, detailed calorimeter simulations and reconstructions are essential for accurate energy measurements and particle identification, but their high granularity makes them computationally expensive. Developing data-driven techniques capable of recovering fine-grained information from coarser readouts, a task known as calorimeter superresolution, offers a promising way to reduce both computational and hardware costs while preserving detector performance. This thesis investigates whether a generative model originally designed for fast simulation can be effectively applied to calorimeter superresolution. Specifically, the model proposed in arXiv:2308.11700 is re-implemented independently and trained on the CaloChallenge 2022 dataset based on the Geant4 Par04 calorimeter geometry. Finally, the model's performance is assessed through a rigorous statistical evaluation framework, following the methodology introduced in arXiv:2409.16336, to quantitatively test its ability to reproduce the reference distributions.

Paper Structure

This paper contains 95 sections, 118 equations, 37 figures, 6 tables.

Table of Contents

  1. Machine Learning Essentials
  2. Machine Learning in Physics
  3. The three paradigms of machine learning
  4. Data discussion
  5. Observational sciences
  6. Experimental sciences
  7. Statistical learning
  8. The Loss function
  9. Mean Squared Error (MSE)
  10. Negative Log-Likelihood (NLL)
  11. An introduction to the statistical model
  12. Representational capacity
  13. Effective capacity
  14. Optimal capacity
  15. Underfitting:
  16. ...and 80 more sections

Figures (37)

  • Figure 1: Projected CPU requirements. Left: Atlas atlas_computingRight: CMS CMS_computing
  • Figure 2: Overfitting example. By fitting noisy data with sufficiently high degree polynomials, the curve is able to parametrize noise.
  • Figure 3: Description of the forward pass (left) and the perceptron schematic (right).
  • Figure 4: Multi-output perceptron: three inputs feed two output units; each output performs a weighted sum, adds a bias, then applies activation $h(\cdot)$.
  • Figure 5: The scheme of an MLP, the input layer has 20 nodes, 2 hidden layers of 15 nodes each and 10 nodes in the output layer. Edge color shows sign (blue = positive, orange = negative) and opacity scales with the weight magnitude. Image inspired by Ref. 3b1b_neuralnetworks
  • ...and 32 more figures