The application of Artificial Intelligence (AI) algorithms to Cadmium Zinc Telluride (CZT) detectors technology addresses key limitations in radiation detection across multiple domains. In radionuclides recognition, rapid and reliable detection is essential, particularly for weak or shielded sources. CZT detectors provide high energy resolution in portable systems, but their limited charge collection efficiency constrains performance at short acquisition times. Integrating AI-based algorithms overcomes this drawback, enabling automatic and rapid localization, identification and quantification of multiple isotopes with high accuracy. This advancement enhances operator safety, environmental protection and data reliability while significantly improving response times and resource management. In materials sorting and recycling, accurate recognition of small density variations, defects or contaminants must occur under high-flux conditions, that introduce spectral distortions. The synergy between CZT’s hyperspectral and imaging capabilities and AI-driven correction and classification methods enables real-time discrimination of materials—such as aluminium alloys and their phases—while compensating for pile-up effects. This results in improved production quality, process efficiency and sustainability. In space radiation monitoring, protecting electronics and astronauts from high-energy particles requires precise characterization of complex radiation fields. Thanks to their isotropic sensitivity and potential ability to distinguish photons from charged particles, CZT detectors enable accurate dosimetry on nanosatellites. AI supports the optimization of multilayer shielding and allows on-board particle classification, enabling selective dose estimation. Since direct measurements cannot be performed prior to flight, accurate physical simulations of the detector response are required to validate the method. Overall, the use of AI methodologies in conjunction with CZT detector technology enables faster, more accurate and automated radiation measurements, advancing safety, efficiency and sustainability in environmental, industrial and space applications.

Artificial Intelligence for CdZnTe Radiation Detectors: Radionuclides Recognition, Materials Inspection and Space Dosimetry / Vicini, V.. - (2026 Feb 23).

Artificial Intelligence for CdZnTe Radiation Detectors: Radionuclides Recognition, Materials Inspection and Space Dosimetry

VICINI, VALENTINA
2026-02-23

Abstract

The application of Artificial Intelligence (AI) algorithms to Cadmium Zinc Telluride (CZT) detectors technology addresses key limitations in radiation detection across multiple domains. In radionuclides recognition, rapid and reliable detection is essential, particularly for weak or shielded sources. CZT detectors provide high energy resolution in portable systems, but their limited charge collection efficiency constrains performance at short acquisition times. Integrating AI-based algorithms overcomes this drawback, enabling automatic and rapid localization, identification and quantification of multiple isotopes with high accuracy. This advancement enhances operator safety, environmental protection and data reliability while significantly improving response times and resource management. In materials sorting and recycling, accurate recognition of small density variations, defects or contaminants must occur under high-flux conditions, that introduce spectral distortions. The synergy between CZT’s hyperspectral and imaging capabilities and AI-driven correction and classification methods enables real-time discrimination of materials—such as aluminium alloys and their phases—while compensating for pile-up effects. This results in improved production quality, process efficiency and sustainability. In space radiation monitoring, protecting electronics and astronauts from high-energy particles requires precise characterization of complex radiation fields. Thanks to their isotropic sensitivity and potential ability to distinguish photons from charged particles, CZT detectors enable accurate dosimetry on nanosatellites. AI supports the optimization of multilayer shielding and allows on-board particle classification, enabling selective dose estimation. Since direct measurements cannot be performed prior to flight, accurate physical simulations of the detector response are required to validate the method. Overall, the use of AI methodologies in conjunction with CZT detector technology enables faster, more accurate and automated radiation measurements, advancing safety, efficiency and sustainability in environmental, industrial and space applications.
23-feb-2026
Scienze e Tecnologie dei Materiali
Radiation Detection
Artificial Intelligence
Machine Learning
Radionuclides Recognition
Materials Inspection
Space Dosimetry
X-ray
gamma ray
CZT detectors
Semiconductor detectors
ZAPPETTINI, ANDREA
File in questo prodotto:
File Dimensione Formato  
Artificial Intelligence for CdZnTe Radiation Detectors - Radionuclides Recognition, Materials Inspection and Space Dosimetry.pdf

embargo fino al 01/04/2028

Licenza: Creative commons
Dimensione 10 MB
Formato Adobe PDF
10 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/1889/6587
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact