Pulse-Shape Discrimination with Machine Learning for CZT Detectors at DAΦNE Beam Test Facility

Cadmium zinc telluride (CZT) detectors offer versatility, operational simplicity, and roomtemperature X- and gamma-ray spectroscopy, making them attractive for collider applications, yet their use under high-flux conditions remains limited. Here, we present a preliminary feature-based pulse-shape analysis employing machine learning on data acquired with a quasi-hemispherical CZT detector at the DAΦNE beam test facility of the National Laboratory of Frascati of INFN. A 300 MeV electron beam impinging on a lead target produced characteristic Pb X-rays together with a broad background extending up to the electron–positron annihilation region. Physically motivated temporal and morphological features were extracted from the recorded waveforms and used to distinguish nominal photon-like pulses from anomalous events. An XGBoost classifier trained and validated on 10,000 labeled waveforms achieved an accuracy of approximately 97%, with most of its classification performance reached using only a few hundred labeled examples. The trained model was applied to more than 700,000 events, substantially reducing the spectral continuum and coincidence peaks, while preserving the characteristic Pb X-ray lines up to the 511 keV annihilation peak. These preliminary results demonstrate the potential of machine-learning-assisted pulse-shape discrimination for improving CZT spectroscopy in collider environments.

Authors

Institutions

Publication Details

Journal
Condensed Matter
Published
2026-10-13
DOI
https://doi.org/10.3390/condmat11040038
Primary Topic
Particle Detector Development and Performance
Type
article
Field-Weighted Citation Impact
0.00

Funders

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

Pulse-Shape Discrimination with Machine Learning for CZT Detectors at DAΦNE Beam Test Facility

Francesco Sgaramella, Catalina Curceanu, M. Skurzok, Manuele Bettelli et al.
Condensed Matter
Particle Detector Development and Performance
article

Pulse-Shape Discrimination with Machine Learning for CZT Detectors at DAΦNE Beam Test Facility

Francesco Sgaramella, Catalina Curceanu, M. Skurzok, Manuele Bettelli, D. Bosnar, Hiroaki Ohnishi, Johann Marton, A. Spallone, Antonino Buttacavoli, G. Borghi, A. Clozza, Mário Carminati, M. Bazzi, A. Scordo, F. Principato, Paweł Moskal, M. Iwasaki, Ivica Friščić, Luca De Paolis, Andrea Zappettini, G. Gerardi, L. Abbene, A. Khreptak, Kairo Toho, K. Dulski, C. Guaraldo, Carlo Ettore Fiorini, F. Clozza, F. Artibani, Otón Vázquez Doce, M. Bragadireanu, Johann Zmeskal, Florin Sirghi, Raffaele Del Grande, Simone Manti, Kristian Piscicchia, Michał Silarski, Mihai Iliescu, Diana Sirghi
article en

Abstract

Cadmium zinc telluride (CZT) detectors offer versatility, operational simplicity, and roomtemperature X- and gamma-ray spectroscopy, making them attractive for collider applications, yet their use under high-flux conditions remains limited. Here, we present a preliminary feature-based pulse-shape analysis employing machine learning on data acquired with a quasi-hemispherical CZT detector at the DAΦNE beam test facility of the National Laboratory of Frascati of INFN. A 300 MeV electron beam impinging on a lead target produced characteristic Pb X-rays together with a broad background extending up to the electron–positron annihilation region. Physically motivated temporal and morphological features were extracted from the recorded waveforms and used to distinguish nominal photon-like pulses from anomalous events. An XGBoost classifier trained and validated on 10,000 labeled waveforms achieved an accuracy of approximately 97%, with most of its classification performance reached using only a few hundred labeled examples. The trained model was applied to more than 700,000 events, substantially reducing the spectral continuum and coincidence peaks, while preserving the characteristic Pb X-ray lines up to the 511 keV annihilation peak. These preliminary results demonstrate the potential of machine-learning-assisted pulse-shape discrimination for improving CZT spectroscopy in collider environments.

Condensed MatterVol. 11(4)
University of Rome Tor Vergata (IT), Roma Tre University (IT), Jagiellonian University (PL), TU Wien (AT), University of Zagreb (HR), Horia Hulubei National Institute for R and D in Physics and Nuclear Engineering (RO), Institute of Materials for Electronics and Magnetism (IT), Centro Ricerche Enrico Fermi (IT), RIKEN (JP), Istituto Nazionale di Fisica Nucleare, Sezione di Milano (IT), Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali di Frascati (IT), Stefan Meyer Institute for Subatomic Physics (AT), National Research Council (IT), Czech Technical University in Prague (CZ), University of Palermo (IT), Politecnico di Milano (IT)
Strong, European Cooperation in Science and Technology, Austrian Science Fund, Hrvatska Zaklada za Znanost, Infrastruktura PL-Grid, Ministry of Science and Higher Education of the Russian Federation, Narodowa Agencja Wymiany Akademickiej, Japan Society for the Promotion of Science, Instituto Nazionale di Fisica Nucleare, Academic Computer Centre Cyfronet, AGH University of Science and Technology
Openalex Percentile: Top 23%
Particle Detector Development and Performance
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.