BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Antonio Vanzanella (NCBJ) "Detection of Slow-moving objects with L
 SST"
DTSTART;VALUE=DATE-TIME:20241024T094500Z
DTEND;VALUE=DATE-TIME:20241024T100000Z
DTSTAMP;VALUE=DATE-TIME:20260420T191123Z
UID:indico-contribution-1751@events.ncbj.gov.pl
DESCRIPTION:We aim at detecting Solar System slow-moving objects (SMOs) in
  LSST images using a Three-Dimensional Convolutional Neural Network (3D-CN
 N). Since no preexisting dataset is available\, we created a dataset conta
 ining samples able to condense exhaustively the characteristics of the SMO
 s. We used small (15x15 pixel) cut-outs of LSST DP0.2’s simulated images
  in which we painted a simulated SMO. This simulated object is modeled on 
 Trans-Neptunian objects from the Jet Propulsion Laboratory Catalog but re-
 scaled to large distances. We further populated the dataset and increased 
 its dimension\, using data augmentation techniques\, and obtained over 500
 0 samples. During the training process\, regularization and normalization 
 techniques are applied to prevent overfitting. We evaluated the network pe
 rformance on a new test set of 200 samples and achieved an accuracy of 90%
 . In this talk\, we will present the model and discuss the details of how 
 the pipeline works. Moreover\, we will show how the network’s performanc
 e varies as a function of the apparent speed of the SMOs.\n\nhttps://event
 s.ncbj.gov.pl/event/364/contributions/1751/
LOCATION:
URL:https://events.ncbj.gov.pl/event/364/contributions/1751/
END:VEVENT
END:VCALENDAR