Data Science for Physicists

Data Science for Physicists#

Welcome to the Short Course on Data Science for Physicists presented at APS-Global Physics Summit 2026! This Jupyter Book provides comprehensive tutorials on applying deep learning techniques to experimental nuclear physics, specifically for the Forward Calorimeter (FCAL) at GlueX in Hall-D Jefferson Lab.

Overview#

These tutorials are designed for Nuclear and Particle Physics and Researchers and cover different applications of deep learning:

  1. GNN-based Classification and Regression (2026): Using Convolutional Neural Networks to classify FCAL showers and distinguish between photons and splitoffs; Regression of the true energy of a reconstructed (identified) photon.

  2. CNN-based Classification (2025): Using Convolutional Neural Networks to classify FCAL showers and distinguish between photons and splitoffs

  3. Generative AI (2025): Building generative models to simulate FCAL photon showers based on their kinematics.

Tutorial Goals#

By the end of these tutorials, you will be able to:

  • Understand the physics behind FCAL showers and the importance of accurate classification

  • Prepare and preprocess FCAL data for deep learning applications

  • Build and train deep learning models for binary classification (photons vs splitoffs)

  • Evaluate model performance using physics-informed metrics

  • Apply these techniques to your own nuclear physics research

Target Audience#

These tutorials are intended for:

  • Graduate students and postdocs in nuclear physics

  • Researchers working on calorimeter systems

  • Scientists interested in applying ML to experimental physics

  • Anyone wanting to learn about deep learning in the context of particle physics

Prerequisites#

  • Basic understanding of nuclear physics and particle detectors

  • Python programming experience

  • Familiarity with NumPy and basic data analysis

  • (Optional) Prior exposure to machine learning concepts

Dataset and models#

Dataset used in this tutorial: Hugging Face Dataset

The trained models are archived for easy access and reproducibility. You can explore and download them at: Hugging Face Model

Event Information#

APS GPS 2026 Tutorial Session: Data Science for Physicists
Date: March 14-15, 2026
Location: Denver, CO
Workshop Sessions: 1WD, 2WD

For questions or feedback, please open an issue on our GitHub repository.

Authors Acknowledgements to GlueX

  • This tutorial is part of the AI4EIC consortium effort to bring modern machine learning techniques to experimental nuclear physics.

  • We gratefully acknowledge the GlueX Collaboration for the software framework and the public release of the Monte Carlo simulation data used in this work GlueX acknowledgements.

Overview

GNN for FCAL (2026)

CNN for FCAL (2025)

Generative AI for FCAL (2025)

Appendix

Contents