Evaluating the scientific potential and performance of Gammalearn on LST-1 observations

The upcoming Cherenkov Telescope Array Observatory (CTAO) represents the next generation of Imaging Atmospheric Cherenkov Telescopes (IACTs), offering a significantly enhanced sensitivity, up to five to ten times greater than existing instruments. Its first prototype, the Large-Sized Telescope (LST-1), is currently operational at the Roque de los Muchachos Observatory in La Palma, Spain. Deep learning techniques have shown promising results in reconstructing key physical properties of incident particles, such as energy, arrival direction, and particle classification, when applied to simulated data. While traditional techniques rely on simple parameterization of the shower image shape, deep learning can leverage the full temporal and charge information of the images, extracting additional information that is particularly valuable at the lowest energies (~20 GeV) accessible by LST-1. These insights are crucial for studying distant extragalactic sources, such as Active Galactic Nuclei, which can serve as probes for fundamental physics and cosmology. In this context, GammaLearn, a deep learning framework for IACTs data analysis, has demonstrated strong potential in this energy range (Vuillaume et al., 2021, ICRC). Here, we apply GammaLearn to observational data from LST-1 to assess its performance on real data.

Authors

Publication Details

Published
2025-09-23
DOI
https://doi.org/10.22323/1.501.0666
Primary Topic
Geophysics and Gravity Measurements
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Evaluating the scientific potential and performance of Gammalearn on LST-1 observations

Vincent Pollet, Michael Dellaiera, Thomas Vuillaume, Tom François et al.
Geophysics and Gravity Measurements
article

Evaluating the scientific potential and performance of Gammalearn on LST-1 observations

Vincent Pollet, Michael Dellaiera, Thomas Vuillaume, Tom François, Sami Caroff, Guillaume Grolleron, Cyann Plard, Justine Talpaert
article en

Abstract

The upcoming Cherenkov Telescope Array Observatory (CTAO) represents the next generation of Imaging Atmospheric Cherenkov Telescopes (IACTs), offering a significantly enhanced sensitivity, up to five to ten times greater than existing instruments. Its first prototype, the Large-Sized Telescope (LST-1), is currently operational at the Roque de los Muchachos Observatory in La Palma, Spain. Deep learning techniques have shown promising results in reconstructing key physical properties of incident particles, such as energy, arrival direction, and particle classification, when applied to simulated data. While traditional techniques rely on simple parameterization of the shower image shape, deep learning can leverage the full temporal and charge information of the images, extracting additional information that is particularly valuable at the lowest energies (~20 GeV) accessible by LST-1. These insights are crucial for studying distant extragalactic sources, such as Active Galactic Nuclei, which can serve as probes for fundamental physics and cosmology. In this context, GammaLearn, a deep learning framework for IACTs data analysis, has demonstrated strong potential in this energy range (Vuillaume et al., 2021, ICRC). Here, we apply GammaLearn to observational data from LST-1 to assess its performance on real data.

National Science Foundation, Nvidia, Sveučilište u Zagrebu, Comunidad de Madrid, Ministerio de Ciencia, Innovación y Universidades, Centres de Recerca de Catalunya, European Commission, Deutsche Forschungsgemeinschaft, Agence Nationale de la Recherche, Ministry of Education, Culture, Sports, Science and Technology, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, Fundação de Amparo à Pesquisa do Estado de São Paulo, Ministerstvo Školství, Mládeže a Tělovýchovy, Bundesministerium für Bildung und Forschung, Generalitat de Catalunya, Conselho Nacional de Desenvolvimento Científico e Tecnológico, Max-Planck-Gesellschaft, Narodowe Centrum Nauki, Hrvatska Zaklada za Znanost, Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro, Fundação Araucária, Centre National de la Recherche Scientifique, Ministerio de Ciencia e Innovación, Istituto Nazionale di Astrofisica, Sveučilište Josipa Jurja Strossmayera u Osijeku, Grand Équipement National De Calcul Intensif, Junta de Andalucía, Ministério da Ciência, Tecnologia, Inovações e Comunicações, Istituto Nazionale di Fisica Nucleare, Japan Society for the Promotion of Science, Consejo Superior de Investigaciones Científicas, Staatssekretariat für Bildung, Forschung und Innovation, European Regional Development Fund, Agencia Estatal de Investigación, Institut National de Physique Nucléaire et de Physique des Particules, Institute for Cosmic Ray Research, University of Tokyo
Openalex Percentile: Top 73%
Geophysics and Gravity Measurements
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.