arXiv subjects

Frédéric Magniette

Publications and source records attributed to Frédéric Magniette.

9 recordsLinked to original sources

arXiv2026

Using Geometric Deep Learning for the Detection of the Diffuse Supernova Neutrino Background in Water-Cherenkov Detectors

The study of the Diffuse Supernova Neutrino Background (DSNB) is an essential approach to improve our understanding of the formation of Core-Collapse Supernovae, as well as investigating fundamental neutrino properties. The detection of the DSNB flux however is a difficult task, as it requires the disentanglement of its signal with many competitive backgrounds in the low energy range. The main DSNB detection channel is the Inverse Beta Decay (IBD), which is characterised by a distinct, time-separated two-signal signature. This work introduces the use of Graph Neural Networks (GNNs) to handle critical detection and reconstruction tasks for the DSNB through the IBD channel. In particular, we present a model to recover the energy of the first signal from a low energy positron. Additionally, we develop a signal-to-background classifier optimised for the secondary signal, which corresponds to the characteristic photon emission following a neutron capture event. We test our models on two simulations in a Hyper-Kamiokande-like water Cherenkov detector geometry, and show that we obtain performances that are comparable to the state of the art.

hep-ex↗

arXiv2026

Optimising Geometric Deep Learning for Varied Reconstruction Tasks in High Granularity Calorimeters

In the recent years, high energy physics discoveries have been driven by the increasing of luminosity and/or detector granularity. This evolution gives access to bigger statistics and data samples, but can make it hard to process the detector outputs with current methods and algorithms. Graph Neural Networks (GNNs), have been shown to be powerful tools to address these challenges. While GNNs can deal with the non-euclidean nature of the data extracted from these detectors, their deployment presents significant difficulties, mainly from the computational complexity of the algorithms they are based on. We propose to use the known geometries of the detectors to optimise the algorithms used for GNN pipelines, which usually have quadratic algorithmic complexities. We validate the validity of our optimised approach on various tasks, such as particle identification, energy regression and instance segmentation. Finally, we present HIBOU, a generic modular architecture that provides a blueprint for how these GNN blocks are to be implemented within experiment-specific reconstruction frameworks.

hep-ex↗

arXiv2026

Using Graph Neural Networks for the segmentation of overlapping objects in high granularity calorimeters

High-granularity calorimeters at the High-Luminosity LHC require novel algorithms to resolve overlapping particle showers. We present an optimised Graph Neural Network (GNN) segmentation block that predicts node-level energy fractions to disentangle overlapping two-photon showers. By accelerating graph construction and convolution operations, our pipeline achieves competitive separation efficiency with significantly reduced algorithmic complexity.

hep-ex↗

arXiv2026

Optimised Graph Convolution for Calorimetry Event Classification

In the recent years, high energy physics discoveries have been driven by the increasing of luminosity and/or detector granularity. This evolution gives access to bigger statistics and data samples, but can make it hard to process results with current methods and algorithms. Graph convolution networks, have been shown to be powerful tools to address these challenges. We present our graph convolution framework for particle identification and energy regression in high granularity calorimeters. In particular, we introduce our algorithm for optimised graph construction in resource constrained environments. We also introduce our implementation of graph convolution and pooling layers. We observe satisfying accuracies, and discuss possible application to other high granularity particle detector challenges.

hep-ex↗

arXiv2026

Quantum Re-Uploading for Calorimetry: Optimized Architectures with Extended Expressivity

Near-term quantum machine learning must balance expressivity, optimization, and hardware constraints. We study quantum re-uploading units (QRUs) as compact circuits and compare them, at matched parameter count, to a standard mono-encoded variational quantum circuit (VQC) baseline. On a three-feature calorimetry classification task, we train a single-qubit QRU that outputs a scalar in $[-1,1]$ and map it to three classes via fixed thresholds. In this setting, QRUs obtain higher accuracy than the mono-encoded baseline. A controlled ablation over depth, input scaling, circuit template, optimizer, and gradient accumulation indicates that most gains occur at small depths, with diminishing returns as depth increases while training cost grows approximately linearly. To interpret these observations, we analyze reachable Fourier components and find that repeated data re-encoding expands the per-coordinate harmonic support relative to mono-encoding, consistent with a spectral activation study over random initializations. Finally, we report an end-to-end proof-of-execution of the trained model on a superconducting QPU via a cloud workflow, illustrating practical deployability under current constraints.

quant-ph↗

arXiv2025

The Calibr-A-Ton: a novel method for calorimeter energy calibration

The energy calibration of calorimeters at collider experiments, such as the ones at the CERN Large Hadron Collider, is crucial for achieving the experiments physics objectives. Standard calibration approaches have limitations that become more pronounced as detector granularity increases. In this paper we propose a novel calibration procedure to simultaneously calibrate individual detector cells belonging to a particle shower by targeting a well-controlled energy reference. The method bypasses some of the difficulties that exist in more standard approaches, and it is implemented using differentiable programming. Simulated energy deposits in the electromagnetic section of a high-granularity calorimeter are used to study the method and demonstrate its performance. It is shown that the method is able to correct for biases in the energy response.

physics.ins-det↗

arXiv2023

MOSAIC, acomparison framework for machine learning models

We introduce MOSAIC, a Python program for machine learning models. Our framework is developed with in mind accelerating machine learning studies through making implementing and testing arbitrary network architectures and data sets simpler, faster and less error-prone. MOSAIC features a full execution pipeline, from declaring the models, data and related hyperparameters within a simple configuration file, to the generation of ready-to-interpret figures and performance metrics. It also includes an advanced run management, stores the results within a database, and incorporates several run monitoring options. Through all these functionalities, the framework should provide a useful tool for researchers, engineers, and general practitioners of machine learning.

cs.LG↗

arXiv2019

ILD Silicon Tungsten Electromagnetic Calorimeter First Full Scale Electronic Prototype

The long slab is a new prototype for the SiW-Ecal, a silicon tungsten electromagnetic calorimeter for the ILD detector of the future International Linear Collider. This new prototype has been designed to demonstrate the ability to build a full length detecting layer (1.60m for the ILD barrel). Indeed, this length induces difficulties for clock and signal propagation and data integrity. The design used for short length slabs had to be adapted on the basis of a simulation study. The long slab performance has been tested with cosmics, radioactive source and with 3 GeV electrons in the beam tests at DESY, Hamburg. The results of the per-channel calibration of the detector are presented. In DESY beam tests we have accumulated data for both normal and inclined incidence of the beam. With the latter one particle can sometimes traverse two pixels and deposit less energy per pixel. We show how this can be used to measure the position of the trigger threshold. This new prototype gives us a lot of hints on how to improve the design of the front-end electronics. It is also a convenient tool to estimate the key characteristics of ILD SiW-Ecal (like power consumption, cooling, readout time etc.) and to optimize the future design of the detector.

physics.ins-det↗

arXiv2018

Statistical algorithms for particle trajectography

The various algorithms used to extrapolate particle trajectories from measurements are often very time-consuming with computational complexities which are typically quadratic. In this article, we propose a new algorithm called GEM with a lower complexity and reasonable performance on linear tracks. It is an extension of the EM algorithm used to fit Gaussian mixtures. It works in arbitrary dimension and with an arbitrary number of simultaneous particles. In a second part, we extend it to circular tracks (for charged particles) and even a mix of linear and circular tracks. This algorithm is implemented in an open-source library called libgem and two applications are proposed, based on data-sets from two kind of particle trackers.

physics.data-an↗