Year: 2024
Type: article
Abstract: Neutron spectroscopy is a crucial point in several nuclear applications. Accurately measuring fast neutron energy distributions in high-flux conditions reveals a significant technology gap, hindering the acquisition of precise energy fluence distributions. This project investigates the potential of machine learning to bridge this gap, focusing on neutron energies from 100 keV to 20 MeV and fluence rates from 1010 n/cm2s to 1012 n/cm2s using solid detectors such as Silicon Carbide (SiC) and Chemical Vapor Deposition (CVD) diamonds. This paper details the simulation design phase of our project, emphasizing the exploration of optimal SiC solid detector thickness to introduce crucial variability for machine learning training.
Authors: Enrica Belfiore, Rodolphe Antoni, Mehdi Ben Mosbah, Pierre-Guy Allinei, Quentin Potiron
Institutions: Commissariat à l'Énergie Atomique et aux Énergies Alternatives, CEA Cadarache, Institut de Recherche sur les Systèmes Nucléaires pour la production d'Energie bas carbone, Centre National de la Recherche Scientifique, Université de Toulon, Aix-Marseille Université, Institut des Matériaux, de Microélectronique et des Nanosciences de Provence
Language: English
Subfield: Radiation
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6941200212
FWCI:
Cites:
Cited by:
Related to: