GammaLearn

Deep Learning for Imaging Cherenkov Telescopes data analysis

GammaLearn is a project to develop deep learning solutions for Imaging Atmospheric Cherenkov Telescopes data analysis and in particular for the Cherenkov Telescope Array Observatory (CTAO) currently under construction. Its first application is the event reconstruction (to retrieve events physical properties such as type, energy and incoming direction) based on the images or videos recorded by Cherenkov telescopes. To ease developments and experiments running, we have developed a complete framework to train and deploy deep learning networks.

See the GammaLearn website for more information.

(Vuillaume et al., 2019) (Jacquemont et al., 2019) (Jacquemont et al., 2018) (Jacquemont et al., 2019) (Nieto Castaño et al., 2019) (Jacquemont et al., 2020) (Jacquemont et al., 2021) (Jacquemont et al., 2021) (Jacquemont et al., 2021) (Vuillaume et al., 2021) (Grespan et al., 2021) (Abe et al., 2022) (Dell’Aiera et al., 2023) (Dellaiera et al., 2024) (Dell’aiera et al., 2024) (JACQUEMONT et al., 2024) (JACQUEMONT et al., 2023) (JACQUEMONT et al., 2023) (François et al., 2025) (Messaoud et al., 2025)

References

2025

  1. arXiv
    To clean or not to clean? Influence of pixel removal on event reconstruction using deep learning in CTAO
    Tom François, Justine Talpaert, and Thomas Vuillaume
    arXiv preprint arXiv:2502.07643, 2025
    Bib PDF
  2. stereograph_icon_.jpg
    Stereograph: Stereoscopic event reconstruction using graph neural networks applied to CTAO
    Hana Ali Messaoud, Thomas Vuillaume, and Tom François
    arXiv preprint arXiv:2502.07421, 2025
    Bib PDF

2024

  1. Deep Learning and IACT: Bridging the gap between Monte-Carlo simulations and LST-1 data using domain adaptation
    Michael Dellaiera, Cyann Plard, Thomas Vuillaume, and 2 more authors
    arXiv preprint arXiv:2403.13633, 2024
    Bib PDF
  2. Unsupervised Domain Adaptation for Multitask Image Analysis in Realistic Context with Extreme Label Shift; Application to the Ctao First Large Sized Telescope
    Michael Dell’aiera, Thomas Vuillaume, and Alexandre Benoit
    Application to the Ctao First Large Sized Telescope, 2024
    Bib
  3. Deep-learning Analysis of Cherenkov Telescope Array Images
    Mikaël JACQUEMONT, Thomas VUILLAUME, Alexandre BENOIT, and 2 more authors
    Inversion and Data Assimilation in Remote Sensing: Estimation of Geophysical Parameters, 2024

2023

  1. Deep unsupervised domain adaptation applied to the cherenkov telescope array large-sized telescope
    Michaël Dell’Aiera, Thomas Vuillaume, Mikaël Jacquemont, and 1 more author
    In Proceedings of the 20th international conference on content-based multimedia indexing, 2023
    Bib
  2. Analyse d’images Cherenkov monotélescope par apprentissage profond
    Mikaël JACQUEMONT, Thomas VUILLAUME, Alexandre BENOIT, and 2 more authors
    Inversion et assimilation de données de télédétection: Estimation des paramètres géophysiques, 2023
  3. Chapitre 9-Analyse d’images Cherenkov monotélescope par apprentissage profond
    Mikaël JACQUEMONT, Thomas VUILLAUME, Alexandre BENOIT, and 2 more authors
    2023

2022

  1. Deep-learning-driven event reconstruction applied to simulated data from a single Large-Sized Telescope of CTA
    H Abe, A Aguasca, I Agudo, and 8 more authors
    In Proceedings of Science, 2022

2021

  1. Multi-task architecture with attention for imaging atmospheric cherenkov telescope data analysis
    Mikaël Jacquemont, Thomas Vuillaume, Alexandre Benoit, and 2 more authors
    In VISAPP 2021, 2021
  2. Deep learning for astrophysics, understanding the impact of attention on variability induced by parameter initialization
    Mikaël Jacquemont, Thomas Vuillaume, Alexandre Benoit, and 2 more authors
    In International Conference on Pattern Recognition, 2021
  3. First full-event reconstruction from imaging atmospheric cherenkov telescope real data with deep learning
    Mikaël Jacquemont, Thomas Vuillaume, Alexandre Benoit, and 3 more authors
    In 2021 International Conference on Content-Based Multimedia Indexing (CBMI), 2021
    DOI PDF
  4. Analysis of the Cherenkov Telescope Array first Large-Sized Telescope real data using convolutional neural networks
    Thomas Vuillaume, Mikaël Jacquemont, Mathieu de Bony Lavergne, and 7 more authors
    arXiv preprint arXiv:2108.04130, 2021
    PDF
  5. Deep-learning-driven event reconstruction applied to simulated data from a single Large-Sized Telescope of CTA
    Pietro Grespan, Mikael Jacquemont, Ruben Lopez-Coto, and 3 more authors
    arXiv preprint arXiv:2109.14262, 2021
    PDF

2020

  1. Single imaging atmospheric cherenkov telescope full-event reconstruction with a deep multi-task learning architecture
    Mikaël Jacquemont, Thomas Vuillaume, Alexandre Benoı̂t, and 2 more authors
    In Astronomical Data Analysis Software and Systems ADASS XXX, 2020

2019

  1. GammaLearn-first steps to apply Deep Learning to the Cherenkov Telescope Array data
    Thomas Vuillaume, Jacquemont Mikael, Luca Antiga, and 4 more authors
    In EPJ Web of Conferences, 2019
  2. GammaLearn: a Deep Learning framework for IACT data
    Mikaël Jacquemont, Thomas Vuillaume, Alexandre Benoit, and 4 more authors
    In 36th International Cosmic Ray Conference, 2019
  3. Indexed operations for non-rectangular lattices applied to convolutional neural networks
    Mikael Jacquemont, Luca Antiga, Thomas Vuillaume, and 4 more authors
    In VISAPP 2019, 2019
    Bib PDF
  4. Studying Deep Convolutional Neural Networks With Hexagonal Lattices for Imaging Atmospheric Cherenkov Telescope Event Reconstruction
    D Nieto Castaño, A Brill, Q Feng, and 4 more authors
    In 36th International Cosmic Ray Conference (ICRC2019), 2019

2018

  1. Deep Learning applied to the Cherenkov Telescope Array data analysis
    M. Jacquemont, T. Vuillaume, A. Benoit, and 3 more authors
    In CHEP 2018 Conference, 2018