16 - 21 June 2024
Yokohama, Japan
Conference 13093 > Paper 13093-65
Paper 13093-65

Augmenting astronomical x-ray detectors with AI for enhanced sensitivity and reduced background

19 June 2024 • 15:55 - 16:15 Japan Standard Time | Room G414/415, North - 4F

Abstract

Bringing artificial intelligence (AI) alongside next-generation X-ray imaging detectors, including CCDs and DEPFET sensors, enhances their sensitivity to achieve many of the flagship science cases targeted by future X-ray observatories, based upon low surface brightness and high redshift sources. Machine learning algorithms operating on the raw frame-level data provide enhanced identification of background vs. astrophysical X-ray events, by considering all of the signals in the context within which they appear within each frame. We have developed prototype machine learning algorithms to identify valid X-ray and cosmic-ray induced background events, trained and tested upon a suite of realistic end-to-end simulations that trace the interaction of cosmic ray particles and their secondaries through the spacecraft and detector. These algorithms demonstrate that AI can reduce the unrejected instrumental background by up to 41.5 per cent compared with traditional filtering methods. Next-generation event reconstruction methods, based upon fitting physically-motivated Gaussian models of the charge clouds produced by events, promise increased accuracy and spectral resolution.

Presenter

Kavli Institute for Particle Astrophysics & Cosmology (United States)
Dan Wilkins is a research scientist at Stanford University. He received his Ph.D. in X-ray astronomy from the University of Cambridge in 2013. His primary research interests are in how material spiraling into supermassive black holes can power some of the most luminous objects we see in the Universe and how we can exploit the X-ray emission illuminating material in its final moments before it plunges into the black hole to produce a 3D picture of the extreme environment just outside the event horizon. Dan has recently turned his attention to next-generation X-ray observatories and their detectors, developing novel analysis techniques, and working towards augmenting astronomical detectors with artificial intelligence (AI) that will be required to fully leverage the scientific capabilities of these forthcoming missions.
Application tracks: AI/ML
Presenter/Author
Kavli Institute for Particle Astrophysics & Cosmology (United States)
Author
Artem Poliszczuk
Kavli Institute for Particle Astrophysics & Cosmology (United States)
Author
MIT Kavli Institute for Astrophysics and Space Research (United States)
Author
MIT Kavli Institute for Astrophysics and Space Research (United States)
Author
Steven W. Allen
Kavli Institute for Particle Astrophysics & Cosmology (United States)
Author
MIT Kavli Institute for Astrophysics and Space Research (United States)
Author
Kavli Institute for Particle Astrophysics & Cosmology (United States)
Author
The Pennsylvania State Univ. (United States)
Author
Richard F. Foster
MIT Kavli Institute for Astrophysics and Space Research (United States)
Author
MIT Kavli Institute for Astrophysics and Space Research (United States)
Author
Sven C. Herrmann
Kavli Institute for Particle Astrophysics & Cosmology (United States)
Author
Ralph Kraft
Smithsonian Astrophysical Observatory (United States)
Author
Glenn Morris
Kavli Institute for Particle Astrophysics & Cosmology (United States)
Author
Smithsonian Astrophysical Observatory (United States)
Author
Kavli Institute for Particle Astrophysics & Cosmology (United States)
Author
Smithsonian Astrophysical Observatory (United States)