BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Kevin Schmitz:  Deep Learning for Radio Interferometric Imaging
DTSTART:20261013T111500Z
DTEND:20261013T121500Z
DTSTAMP:20261018T202400Z
UID:indico-event-9770@indico.fysik.su.se
CONTACT:alexander.burgman@fysik.su.se\;azadeh.fattahi@fysik.su.se
DESCRIPTION:Radio astronomy is entering a new era. The Square Kilometre Ar
 ray (SKA) and its precursors such as MeerKAT will map the radio sky with u
 nprecedented sensitivity\, addressing questions ranging from the epoch of 
 reionization to cosmic magnetism and the growth of galaxy clusters. Yet ra
 dio interferometers do not take pictures directly. They sample the Fourier
  transform of the sky at a limited set of points\, and reconstructing an i
 mage from these incomplete measurements is a difficult inverse problem. Th
 e classical algorithms used for decades are struggling with the data volum
 es of these new instruments and with faint\, extended emission.Machine lea
 rning is emerging as a powerful alternative. Neural networks trained on ph
 ysically realistic simulations\, an approach familiar from particle physic
 s\, can learn to recover the missing information quickly. Their adoption i
 n radio astronomy\, however\, depends on key open issues: the reliability 
 of network-based reconstructions\, their transfer from simulated to real o
 bservations\, and the quantification of uncertainties in the resulting ima
 ges.In this talk\, I will give an overview of deep learning-based imaging 
 in radio interferometry and its recent progress. Using the radionets frame
 work as an example\, I will show how a cascade of specialized networks rec
 onstructs both compact sources and diffuse emission\, and how it performs 
 on real MeerKAT observations of a galaxy cluster compared with classical m
 ethods. I will close with the challenges that remain before these methods 
 can be used routinely in the SKA era.\nAbout the speaker: Kevin Schmitz is
  a postdoctoral researcher at the Hamburger Sternwarte\, part of the Depar
 tment of Physics at Universität Hamburg. He received his PhD from TU Dort
 mund in 2023\, where he developed machine learning-based analysis strategi
 es for physics in close collaboration with computer scientists. His curren
 t research centers on deep learning methods for radio interferometric imag
 ing\, with applications to MeerKAT and the upcoming SKA.\n\nhttps://indico
 .fysik.su.se/event/9770/
LOCATION:FB54 (AlbaNova Main Building)
URL:https://indico.fysik.su.se/event/9770/
END:VEVENT
END:VCALENDAR