2026/07/03 by D. R. Wilkins, Dan Wilkins, Artem Poliszczuk +25
Medicine · Physics and Astronomy · #Detector #Digital Radiography and Breast Imaging #Event (particle physics) #Event reconstruction #Particle Detector Development and Performance #Pattern recognition (psychology) #Radiation Detection and Scintillator Technologies #Reconstruction algorithm #Sensitivity (control systems) #astro-ph.IM
paper · pdf · doi:10.1117/12.3104126
published as Proc. SPIE, 2026, 14146-248 · Proceedings of the SPIE, Astronomical Telescopes and Instrumentation, Space Telescopes and Instrumentation 2026: Ultraviolet to Gamma Ray
openalex publication_date 2026/07/03 · openalex created_date 2026/07/04 · openalex updated_date 2026/07/14 · arxiv created 2026/08/03 · arxiv updated 2026/08/05
Advanced algorithms incorporating artificial intelligence and machine learning (AI/ML) enhance the sensitivity of X-ray imaging detectors and the scientific capabilities of future X-ray missions. We report on the development of prototype algorithms designed to provide improved identification of particle-induced background events and enhanced energy reconstruction. ML algorithms can achieve a reduction of the unrejected particle background by up to 60% compared with traditional filtering methods. Moreover, with physics-motivated models of charge diffusion within the device, we find that next-generation event reconstruction algorithms can provide an improvement in the energy resolution of CCD-like detectors at event energies below 0.5keV. We present new laboratory data that demonstrates the performance of these algorithms on next-generation SiSeRO CCD devices. Together such detector and algorithm combinations can satisfy the requirements for future X-ray flagship missions.