BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//adass2023//talk//ASHZGR
BEGIN:VTIMEZONE
TZID:MST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:MST
TZOFFSETFROM:-0700
TZOFFSETTO:-0700
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-adass2023-ASHZGR@pretalx.com
DTSTART;TZID=MST:20231107T111500
DTEND;TZID=MST:20231107T113000
DESCRIPTION:New software developments in data post-processing are being mad
 e within the SKA precursor communities to enable extraction of science inf
 ormation from radio images in a mostly automated way. Many of them exploit
  HPC processing paradigms and machine learning (ML) methodologies for vari
 ous tasks\, such as source detection\, object or morphology classification
 \, 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 c
 ompact and extended radio sources and imaging artifacts from radio continu
 um images. Another tool uses different ML techniques to classify compact s
 ources into different classes (galaxy\, QSO\, star\, pulsar\, HII\, PN\, Y
 SO) using radio and infrared multi-band images. Furthermore\, we have deve
 loped self-supervised models for radio data representation learning\, and 
 generative models to produce synthetic radio image data for data challenge
 s or model performance boosting.\nThese tools have been trained and tested
  on different radio survey data including the ASKAP EMU survey. An overvie
 w of the results achieved will be presented at the workshop\, along with d
 etails on the ongoing activities and future prospects.
DTSTAMP:20260722T080744Z
LOCATION:Talks
SUMMARY:Detection and classification of radio sources with deep learning - 
 Simone Riggi
URL:https://pretalx.com/adass2023/talk/ASHZGR/
END:VEVENT
END:VCALENDAR