BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//adass2023//speaker//9WWQUN
BEGIN:VTIMEZONE
TZID:US/Arizona
BEGIN:STANDARD
DTSTART:20221107T000000
TZNAME:MST
TZOFFSETFROM:-0700
TZOFFSETTO:-0700
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Detection and classification of radio sources with deep learning -
  Simone Riggi
DTSTART;TZID=US/Arizona:20231107T111500
DTEND;TZID=US/Arizona:20231107T113000
DTSTAMP:20260808T190427Z
UID:pretalx-adass2023-ASHZGR@pretalx.com
DESCRIPTION:New software developments in data post-processing are being ma
 de within the SKA precursor communities to enable extraction of science in
 formation from radio images in a mostly automated way. Many of them exploi
 t HPC processing paradigms and machine learning (ML) methodologies for var
 ious tasks\, such as source detection\, object or morphology classificatio
 n\, or anomaly detection. \nIn this context\, we are developing several ML
 -based tools to support the scientific analysis conducted within the ASKAP
  EMU and MeerKAT surveys. One tool employs deep neural networks to detect 
 compact and extended radio sources and imaging artifacts from radio contin
 uum images. Another tool uses different ML techniques to classify compact 
 sources into different classes (galaxy\, QSO\, star\, pulsar\, HII\, PN\, 
 YSO) using radio and infrared multi-band images. Furthermore\, we have dev
 eloped self-supervised models for radio data representation learning\, and
  generative models to produce synthetic radio image data for data challeng
 es or model performance boosting.\nThese tools have been trained and teste
 d on different radio survey data including the ASKAP EMU survey. An overvi
 ew of the results achieved will be presented at the workshop\, along with 
 details on the ongoing activities and future prospects.
LOCATION:Talks
URL:https://pretalx.com/adass2023/talk/ASHZGR/
END:VEVENT
END:VCALENDAR