arXiv subjects

Thomas Vuillaume

Publications and source records attributed to Thomas Vuillaume.

At least 19 recordsLinked to original sources

arXiv2026

Unsupervised Domain Adaptation for Multitask Image Analysis in Realistic Context with Extreme Label Shift; Application to the CTAO first Large Sized Telescope

Unsupervised domain adaptation is a widespread set of methods that leverages the knowledge of a labeled source domain to train a model to perform well on a related unlabeled target domain. They generally introduce an auxiliary adaptation-related task that can be integrated into the multitask paradigm, which aims to merge multiple single-task models into a unified architecture. In this paper, we propose to associate domain adaptation and multitask balancing in the realistic context of an extreme class imbalance. Therefore, we propose a combined framework to cover and validate these approaches, and evaluate its performance in the physics-based context of the Cherenkov Telescope Array Observatory (CTAO). Along with a comparative study of some relevant adaptation techniques, we highlight the impact of extreme label shift and extend the investigations on importance weighting to rectify it. The complete code and results are published and available as open-source resources on Zenodo.

astro-ph.IM↗

arXiv2025

SAG-SCI: the Real-time, High-level Analysis Software for Array Control and Data Acquisition of the Cherenkov Telescope Array Observatory

The Cherenkov Telescope Array Observatory (CTAO) is going to be the leading observatory for very-high-energy gamma-rays over the next decades. Its unique sensitivity, wide field of view, and rapid slewing capability make the CTAO especially suited to study transient astrophysical phenomena. The CTAO will analyse its data in real-time, responding to external science alerts on transient events and issuing its own. The Science Alert Generation (SAG) automated pipeline, a component of the Array Control and Data Acquisition (ACADA) software, is designed to detect and issue candidate science alerts. In this work, we present the current development status of SAG-SCI, the SAG component responsible for the real-time, high-level analysis of CTAO data. The SAG-SCI pipelines receive gamma-ray data from multiple reconstruction lines, merge them, store them in a database, and trigger several parallel scientific analyses on the latest data. These analyses include estimating target significance and flux, producing sky maps and light curves, and conducting blind searches for sources within the field of view. We execute SAG-SCI on a set of simulated gamma-ray data, detecting the simulated sources and accurately reconstructing their flux and position. We also estimate the systematic errors introduced by the analysis and discuss the results in relation to the generation of candidate science alerts.

astro-ph.HE↗

arXiv2025

Advanced stereoscopy applied to CTAO

The Cherenkov Telescope Array Observatory (CTAO) is an international observatory currently under construction, which will consist of two sites (one in the Northern Hemisphere and one in the Southern Hemisphere). It will eventually be the largest and most sensitive ground-based gamma-ray observatory. In the meantime, a small subarray composed of four Large-Sized Telescopes (LSTs) at the Northern site will begin collecting data in the coming year. In preparation, we present a stereoscopic event reconstruction using graph neural networks (GNNs) to combine information from several telescopes of this subarray. In our previous work, we explored the use of GNNs for the stereoscopic reconstruction of gamma-ray events on simulated data from the Prod5 sample and showed that GNNs provide a better stereoscopic reconstruction. We now compare this approach to the currently foreseen method that analytically combines the output of monoscopic random forests, and explore how GNNs can be used in fusion with the Random forest algorithm in order to provide a more sensitive stereoscopic system.

astro-ph.IM↗

arXiv2025

The new architecture design of the Science Alert Generation pipeline of the Cherenkov Telescope Array Observatory

The Cherenkov Telescope Array Observatory (CTAO) represents the next-generation gamma-ray observatory and will operate for several decades. It will be particularly suited to analyse transients and variable phenomena, which will trigger real-time scientific alerts. To support this, the Science Alert Generation (SAG) pipeline within the Array Control and Data Acquisition (ACADA) system will process data from telescope arrays in real time, using dedicated pipelines for data reconstruction (SAG-RECO), data quality monitoring (SAG-DQ) and science monitoring (SAG-SCI). The Supervisor (SAG-SUP) oversees the dynamic operations of SAG and its integration with other ACADA components. SAG is designed to issue candidate science alerts within 20 s of data availability, processing events on multiple time scales (seconds to hours) and handling trigger rates of tens of kHz. Meeting these requirements necessitates optimised software and hardware architectures. This work presents recent developments in SAG's architecture, aimed at two main challenges: (1) selecting data only from telescopes that have entered a stable tracking state, even when they begin tracking at different times during multi-telescope observations, and (2) incorporating environmental and system monitoring information to ensure high data quality. SAG-SUP can retrieve real-time telescope status and environmental conditions from telescope managers and the weather station through the ACADA Monitoring system, collect them in a database and then use them to filter out data from slewing phases or degraded conditions. These enhancements are crucial to ensure the reliability of science alerts and improve the overall performance and responsiveness of the CTAO real-time analysis framework.

astro-ph.IM↗

arXiv2025

Stereograph: Stereoscopic event reconstruction using graph neural networks applied to CTAO

The CTAO (Cherenkov Telescope Array Observatory) is an international observatory currently under construction. With more than sixty telescopes, it will eventually be the largest and most sensitive ground-based gamma-ray observatory. CTAO studies the high-energy universe by observing gamma rays emitted by violent phenomena (supernovae, black hole environments, etc.). These gamma rays produce an atmospheric shower when entering the atmosphere, which emits faint blue light, observed by CTAO's highly sensitive cameras. The event reconstruction consists of analyzing the images produced by the telescopes to retrieve the physical properties of the incident particle (mainly direction, energy, and type). A standard method for performing this reconstruction consists of combining traditional image parameter calculations with machine learning algorithms, such as random forests, to estimate the particle's energy and class probability for each telescope. A second step, called stereoscopy, combines these monoscopic reconstructions into a global one using weighted averages. In this work, we explore the possibility of using Graph Neural Networks (GNNs) as a suitable solution for combining information from each telescope. The "graph" approach aims to link observations from different telescopes, allowing analysis of the shower from multiple angles and producing a stereoscopic reconstruction of the events. We apply GNNs to CTAO-simulated data from the Northern Hemisphere and show that they are a very promising approach to improving event reconstruction, providing a more performant stereoscopic reconstruction. In particular, we observe better energy and angular resolutions(before event selection) and better separation between gamma photons and protons compared to the Random Forest method.

astro-ph.IM↗

arXiv2025

To clean or not to clean? Influence of pixel removal on event reconstruction using deep learning in CTAO

The Cherenkov Telescope Array Observatory (CTAO) is the next generation of ground-based observatories employing the imaging air Cherenkov technique for the study of very high energy gamma rays. The software Gammalearn proposes to apply Deep Learning as a part of the CTAO data analysis to reconstruct event parameters directly from images captured by the telescopes with minimal pre-processing to maximize the information conserved. In CTAO, the data analysis will include a data volume reduction that will definitely remove pixels. This step is necessary for data transfer and storage but could also involve information loss that could be used by sensitive algorithms such as neural networks (NN). In this work, we evaluate the performance of the gamma-PhysNet when applying different cleaning masks on images from Monte-Carlo simulations from the first Large-Sized Telescope. This study is critical to assess the impact of pixel removal in the data processing, mainly motivated by data compression.

astro-ph.IM↗

arXiv2024

Deep Learning and IACT: Bridging the gap between Monte-Carlo simulations and LST-1 data using domain adaptation

The Cherenkov Telescope Array Observatory (CTAO) is the next generation of observatories employing the imaging air Cherenkov technique for the study of very high energy gamma rays. The deployment of deep learning methods for the reconstruction of physical attributes of incident particles has evinced promising outcomes when conducted on simulations. However, the transition of this approach to observational data is accompanied by challenges, as deep learning-based models are susceptible to domain shifts. In this paper, we integrate domain adaptation in the physics-based context of the CTAO and shed light on the gain in performance that these techniques bring using LST-1 real acquisitions.

astro-ph.IM↗

arXiv2023

The Real Time Analysis framework of the Cherenkov Telescope Array's Large-Sized Telescope

The Large-Sized Telescopes (LSTs) of the Cherenkov Telescope Array Observatory (CTAO) will play a crucial role in the study of transient gamma-ray sources, such as gamma-ray bursts and flaring active galactic nuclei. The low energy threshold of LSTs makes them particularly well suited for the detection of these phenomena. The ability to detect and analyze gamma-ray transients in real-time is essential for quickly identifying and studying these rare and fleeting events. In this conference, we will present recent advances in the real-time analysis of data from the LST-1, the first prototype of LST located in the Canary island of La Palma. We will discuss in particular the development of new algorithms for event reconstruction and background rejection. These advances will enable rapid identification and follow-up observation of transient gamma-ray sources, making the LST-1 a powerful tool for the study of the dynamic universe. The implementation of this framework in the future Array Control and Data Acquisition System (ACADA) of CTAO will be discussed as well, based on the experience with LST.

astro-ph.IM↗

arXiv2023

Performance of the Large-Sized Telescope prototype of the Cherenkov Telescope Array

The next-generation ground-based gamma-ray Cherenkov Telescope Array Observatory (CTAO) will consist of imaging atmospheric Cherenkov telescopes (IACTs) of three different sizes distributed in two sites. The Large-Sized Telescopes will cover the low-energy end of the CTA energy range, starting at about 20 GeV. After its first years of operation at the CTA northern site, the Large-Sized Telescope prototype (LST-1) is in the final stage of its commissioning phase, having collected a significant amount of scientific data to date. In this contribution, we present the physics performance of the telescope using low-zenith Crab Nebula observations and Monte Carlo simulations fine-tuned accordingly. We show performance figures of merit such as the energy threshold, effective area, energy and angular resolution, and sensitivity based on the standard Hillas-parameters approach and following the source-independent and dependent analysis methods. The analysis threshold is estimated at 30 GeV. The energy resolution is around 30%, and the angular resolution is 0.3 degrees at 100 GeV. The best integral sensitivity of LST-1 is about 1.1% of the Crab Nebula flux above 250 GeV for 50 hours of observations. We also show the spectral energy distribution and light curve from Crab Nebula observations, which agree with results from other IACTs and link smoothly with Fermi-LAT when considering statistical and systematic uncertainties near the energy threshold.

astro-ph.HE↗

arXiv2023

Gammapy: A Python package for gamma-ray astronomy

In this article, we present Gammapy, an open-source Python package for the analysis of astronomical $γ$-ray data, and illustrate the functionalities of its first long-term-support release, version 1.0. Built on the modern Python scientific ecosystem, Gammapy provides a uniform platform for reducing and modeling data from different $γ$-ray instruments for many analysis scenarios. Gammapy complies with several well-established data conventions in high-energy astrophysics, providing serialized data products that are interoperable with other software packages. Starting from event lists and instrument response functions, Gammapy provides functionalities to reduce these data by binning them in energy and sky coordinates. Several techniques for background estimation are implemented in the package to handle the residual hadronic background affecting $γ$-ray instruments. After the data are binned, the flux and morphology of one or more $γ$-ray sources can be estimated using Poisson maximum likelihood fitting and assuming a variety of spectral, temporal, and spatial models. Estimation of flux points, likelihood profiles, and light curves is also supported. After describing the structure of the package, we show, using publicly available $γ$-ray data, the capabilities of Gammapy in multiple traditional and novel $γ$-ray analysis scenarios, such as spectral and spectro-morphological modeling and estimations of a spectral energy distribution and a light curve. Its flexibility and power are displayed in a final multi-instrument example, where datasets from different instruments, at different stages of data reduction, are simultaneously fitted with an astrophysical flux model.

astro-ph.IM↗

arXiv2023

Deep unsupervised domain adaptation applied to the Cherenkov Telescope Array Large-Sized Telescope

The Cherenkov Telescope Array is the next generation of observatory using imaging air Cherenkov technique for very-high-energy gamma-ray astronomy. Its first prototype telescope is operational on-site at La Palma and its data acquisitions allowed to detect known sources, study new ones, and to confirm the performance expectations. The application of deep learning for the reconstruction of the incident particle physical properties (energy, direction of arrival and type) have shown promising results when conducted on simulations. Nevertheless, its application to real observational data is challenging because deep-learning-based models can suffer from domain shifts. In the present article, we address this issue by implementing domain adaptation methods into state-of-art deep learning models for Imaging Atmospheric Cherenkov Telescopes event reconstruction to reduce the domain discrepancies, and we shed light on the gain in performance that they bring along.

astro-ph.IM↗

arXiv2022

The lstMCpipe library

The Cherenkov Telescope Array (CTA) is the next generation of ground-based gamma-ray astronomy observatory that will improve the sensitivity of current generation instruments by one order of magnitude. The LST-1 is the first telescope prototype built on-site on the Canary Island of La Palma and has been taking data for a few years already. Like all imaging atmospheric Cherenkov telescopes (IACTs), the LST-1 works by capturing the light produced by the Cherenkov process when high-energy particles enter the atmosphere. The analysis of the recorded snapshot of the camera allows to discriminate between gamma photons and hadrons, and to reconstruct the physical parameters of the selected photons. To build the models for the discrimination and reconstruction, as well as to estimate the telescope response (by simulating the atmospheric showers and the telescope optics and electronics), extensive Monte Carlo simulations have to be performed. These trained models are later used to analyse data from real observations. lstMCpipe is an open source python package developed to orchestrate the different stages of the analysis of the MC files on a computing facility. Currently, the library is in production status, scheduling the full pipeline in a SLURM cluster. It greatly simplifies the analysis workflow by adding a level of abstraction, allowing users to start the entire pipeline using a simple configuration file. Moreover, members of the LST collaboration can ask for a new analysis to be produced with their tuned parameters through a pull request in the project repository, allowing careful review by others collaborators and a central management of the productions, thus reducing human errors and optimising the usage of the computing resources.

astro-ph.IM↗

arXiv2022

The eOSSR library

The astronomy, astroparticle and particle physics communities are brought together through the ESCAPE (European Science Cluster of Astronomy and Particle Physics ESFRI research infrastructures) project to create a cluster focused on common issues in data-driven research. Among the ESCAPE work packages, the OSSR (ESCAPE Open-source Scientific Software and Service Repository) is a curated, long-term, open-access repository that makes it possible for scientists to exchange software and services and promote open science. It has been developed on top of a Zenodo community, connected to other services. A Python library, the eOSSR, has been developed to take care of the interactivity between Zenodo, services and OSSR users, allowing an automated handling of the OSSR records. In this work, we present the eOSSR, its main functionalities and how it's been used in the ESCAPE context to ease the publication of scientific software, analysis, and datasets by researchers

astro-ph.IM↗

arXiv2021

Deep-learning-driven event reconstruction applied to simulated data from a single Large-Sized Telescope of CTA

When very-high-energy gamma rays interact high in the Earth's atmosphere, they produce cascades of particles that induce flashes of Cherenkov light. Imaging Atmospheric Cherenkov Telescopes (IACTs) detect these flashes and convert them into shower images that can be analyzed to extract the properties of the primary gamma ray. The dominant background for IACTs is comprised of air shower images produced by cosmic hadrons, with typical noise-to-signal ratios of several orders of magnitude. The standard technique adopted to differentiate between images initiated by gamma rays and those initiated by hadrons is based on classical machine learning algorithms, such as Random Forests, that operate on a set of handcrafted parameters extracted from the images. Likewise, the inference of the energy and the arrival direction of the primary gamma ray is performed using those parameters. State-of-the-art deep learning techniques based on convolutional neural networks (CNNs) have the potential to enhance the event reconstruction performance, since they are able to autonomously extract features from raw images, exploiting the pixel-wise information washed out during the parametrization process. Here we present the results obtained by applying deep learning techniques to the reconstruction of Monte Carlo simulated events from a single, next-generation IACT, the Large-Sized Telescope (LST) of the Cherenkov Telescope Array (CTA). We use CNNs to separate the gamma-ray-induced events from hadronic events and to reconstruct the properties of the former, comparing their performance to the standard reconstruction technique. Three independent implementations of CNN-based event reconstruction models have been utilized in this work, producing consistent results.

astro-ph.IM↗

arXiv2021

Analysis of the Cherenkov Telescope Array first Large-Sized Telescope real data using convolutional neural networks

The Cherenkov Telescope Array (CTA) is the future ground-based gamma-ray observatory and will be composed of two arrays of imaging atmospheric Cherenkov telescopes (IACTs) located in the Northern and Southern hemispheres respectively. The first CTA prototype telescope built on-site, the Large-Sized Telescope (LST-1), is under commissioning in La Palma and has already taken data on numerous known sources. IACTs detect the faint flash of Cherenkov light indirectly produced after a very energetic gamma-ray photon has interacted with the atmosphere and generated an atmospheric shower. Reconstruction of the characteristics of the primary photons is usually done using a parameterization up to the third order of the light distribution of the images. In order to go beyond this classical method, new approaches are being developed using state-of-the-art methods based on convolutional neural networks (CNN) to reconstruct the properties of each event (incoming direction, energy and particle type) directly from the telescope images. While promising, these methods are notoriously difficult to apply to real data due to differences (such as different levels of night sky background) between Monte Carlo (MC) data used to train the network and real data. The GammaLearn project, based on these CNN approaches, has already shown an increase in sensitivity on MC simulations for LST-1 as well as a lower energy threshold. This work applies the GammaLearn network to real data acquired by LST-1 and compares the results to the classical approach that uses random forests trained on extracted image parameters. The improvements on the background rejection, event direction, and energy reconstruction are discussed in this contribution.

astro-ph.IM↗

arXiv2021

First follow-up of transient events with the CTA Large Size Telescope prototype

The recent detection of a very high energy (VHE) emission from Gamma-Ray Bursts (GRBs) above 100 GeV performed by the MAGIC and H.E.S.S. collaborations, has represented a significant, long-awaited result for the VHE astrophysics community. Although these results' scientific impact has not yet been fully exploited, the possibility to detect VHE gamma-ray signals from GRBs has always been considered crucial for clarifying the poorly known physics of these objects. Furthermore, the discovery of high-energy neutrinos and gravitational waves associated with astrophysical sources have definitively opened the era of multi-messenger astrophysics, providing unique insights into the physics of extreme cosmic accelerators. In the near future, the Cherenkov Telescope Array (CTA) will play a major role in these observations. Within this framework, the Large Size Telescopes (LSTs) will be the instruments best suited to significantly impact on short time-scale transients follow-up thanks to their fast slewing and large effective area. The observations of the early emission phase of a wide range of transient events with good sensitivity below 100 GeV will allow us to open new opportunities for time-domain astrophysics in an energy range not affected by selective absorption processes typical of other wavelengths. In this contribution, we will report about the observational program and first transients follow-up observations performed by the LST-1 telescope currently in its commissioning phase on La Palma, Canary Islands, the CTA northern hemisphere site.

astro-ph.HE↗

arXiv2021

First Full-Event Reconstruction from Imaging Atmospheric Cherenkov Telescope Real Data with Deep Learning

The Cherenkov Telescope Array is the future of ground-based gamma-ray astronomy. Its first prototype telescope built on-site, the Large Size Telescope 1, is currently under commissioning and taking its first scientific data. In this paper, we present for the first time the development of a full-event reconstruction based on deep convolutional neural networks and its application to real data. We show that it outperforms the standard analysis, both on simulated and on real data, thus validating the deep approach for the CTA data analysis. This work also illustrates the difficulty of moving from simulated data to actual data.

astro-ph.IM↗

arXiv2021

rta-dq-lib: a software library to perform online data quality analysis of scientific data

The Cherenkov Telescope Array (CTA) is an initiative that is currently building the largest gamma-ray ground Observatory that ever existed. A Science Alert Generation (SAG) system, part of the Array Control and Data Acquisition (ACADA) system of the CTA Observatory, analyses online the telescope data - arriving at an event rate of tens of kHz - to detect transient gamma-ray events. The SAG system also performs an online data quality analysis to assess the instruments' health during the data acquisition: this analysis is crucial to confirm good detections. A Python and a C++ software library to perform the online data quality analysis of CTA data, called rta-dq-lib, has been proposed for CTA. The Python version is dedicated to the rapid prototyping of data quality use cases. The C++ version is optimized for maximum performance. The library allows the user to define, through XML configuration files, the format of the input data and, for each data field, which quality checks must be performed and which types of aggregations and transformations must be applied. It internally translates the XML configuration into a direct acyclic computational graph that encodes the dependencies of the computational tasks to be performed. This model allows the library to easily take advantage of parallelization at the thread level and the overall flexibility allow us to develop generic data quality analysis pipelines that could also be reused in other applications.

astro-ph.IM↗