Deep Learning for Cherenkov Astronomy: Performance of GammaLearn on LST-1
Abstract
The Cherenkov Telescope Array Observatory (CTAO) marks the next generation of Imaging Atmospheric Cherenkov Telescopes (IACTs), offering a sensitivity improvement of up to a factor of 10 over current instruments. Its first prototype, the Large-Sized Telescope (LST-1), is already in operation at the Roque de los Muchachos Observatory in La Palma, Spain. Deep learning methods have shown significant promise in reconstructing key properties of incident particles, such as energy, arrival direction, and type, using simulated data. Unlike traditional approaches that rely on simplified image shape parameters, deep learning can exploit the full temporal and charge information of the recorded events, providing enhanced performance, particularly at low energies (~20 GeV) accessible by LST-1. This capability is especially valuable for observing distant extragalactic sources like Active Galactic Nuclei, which are key to probing fundamental physics and cosmology. In this work, by producing sensitivity curves, we evaluate the performance of GammaLearn, a deep learning framework tailored for IACT data analysis, by comparing it to the standard analysis used with LST-1 and applying it to real observational data from LST-1.
Related
- Pushing the frontiers of low-frequency radio astronomy: An ultra-deep sub-arcsecond LOFAR image of ELAIS-N1
- Astro2Method: Benchmarking LLMs on Machine Learning Method Selection in Astronomy
- CtaAgnVar : a Pipeline for Variability Studies with the Cherenkov Telescope Array Observatory
- Cherenkov Bursts are Memory Steps
- Investigation of magnetic-field effects on photomultiplier tubes for the first Large-Sized Telescope of the Cherenkov Telescope Array Observatory
BibTeX
@misc{grolleron2026deep,
title = {{Deep Learning for Cherenkov Astronomy: Performance of GammaLearn on LST-1}},
author = {G Grolleron and C Plard and M Dell'Aiera and T François and V Pollet and J Talpaert and S Caroff and T Vuillaume},
howpublished = {HAL},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.10392},
eprint = {2610.10392},
archivePrefix = {arXiv},
url = {https://hal.science/hal-05829889v1},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Deep Learning for Cherenkov Astronomy: Performance of GammaLearn on LST-1
AU - G Grolleron
AU - C Plard
AU - M Dell'Aiera
AU - T François
AU - V Pollet
AU - J Talpaert
AU - S Caroff
AU - T Vuillaume
PY - 2026
DA - 2026/10/07
PB - HAL
DO - 10.48550/arxiv.2610.10392
UR - https://hal.science/hal-05829889v1
AB - The Cherenkov Telescope Array Observatory (CTAO) marks the next generation of Imaging Atmospheric Cherenkov Telescopes (IACTs), offering a sensitivity improvement of up to a factor of 10 over current instruments. Its first prototype, the Large-Sized Telescope (LST-1), is already in operation at the Roque de los Muchachos Observatory in La Palma, Spain. Deep learning methods have shown significant promise in reconstructing key properties of incident particles, such as energy, arrival direction, and type, using simulated data. Unlike traditional approaches that rely on simplified image shape parameters, deep learning can exploit the full temporal and charge information of the recorded events, providing enhanced performance, particularly at low energies (~20 GeV) accessible by LST-1. This capability is especially valuable for observing distant extragalactic sources like Active Galactic Nuclei, which are key to probing fundamental physics and cosmology. In this work, by producing sensitivity curves, we evaluate the performance of GammaLearn, a deep learning framework tailored for IACT data analysis, by comparing it to the standard analysis used with LST-1 and applying it to real observational data from LST-1.
ER -