BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.adass.org//adass2026//talk//N79KYE
BEGIN:VTIMEZONE
TZID:AWST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1;UNTIL=20051231T160000Z
TZNAME:AWST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
BEGIN:STANDARD
DTSTART:20070325T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:AWST
TZOFFSETFROM:+0900
TZOFFSETTO:+0800
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20071028T030000
RRULE:FREQ=YEARLY;BYDAY=4SU;BYMONTH=10;UNTIL=20081025T190000Z
TZNAME:AWDT
TZOFFSETFROM:+0800
TZOFFSETTO:+0900
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-adass2026-N79KYE@pretalx.adass.org
DTSTART;TZID=AWST:20261103T101200
DTEND;TZID=AWST:20261103T102400
DESCRIPTION:The Compton Spectrometer and Imager (COSI) is a NASA Small Expl
 orer mission designed to study the MeV gamma-ray sky\, including gamma-ray
  bursts (GRBs)\, compact objects\, nuclear emission lines\, and other high
 -energy sources. Reliable background prediction is important for transient
  searches because the background changes with spacecraft position\, pointi
 ng direction\, and time. The aim of this paper is to develop a probabilist
 ic machine-learning framework for COSI background prediction to support GR
 B detection and localization. The framework consists of four main stages. 
 The Angular Resolution Measure (ARM) method is used to filter the event da
 ta and generate light curves for different sky positions following the HEA
 LPix grid. These background light curves are then used to train a probabil
 istic regression model and derive significance thresholds from its predict
 ive distribution. The trained model is applied to the same sky positions w
 ithin the COSI field of view to estimate the expected background. The obse
 rved light curves are then compared with the predicted background and sign
 ificance thresholds to search for significant excesses associated with GRB
 s and support their detection and localization. In this work\, we focus on
  developing and evaluating the background regression models using simulate
 d DC4 background events and spacecraft information. For the regression ana
 lysis presented here\, we use an ARM-selected background light curve with 
 one-second bins. Spacecraft livetime information is used to select valid o
 bserving periods and remove bins close to South Atlantic Anomaly boundarie
 s. The model inputs include the time elapsed since the start of the select
 ed DC4 modeling interval\, spacecraft altitude\, the Earth-zenith directio
 n\, and spacecraft pointing orientation. The spacecraft pointing direction
 s are originally given in Galactic coordinates and are represented in the 
 models using Cartesian components. From the DC4 dataset\, two consecutive 
 orbits are reserved as a held-out temporal test block\, while the remainin
 g data are randomly divided into training and test sets. Only background e
 vents are used for model training and evaluation. We compare Poisson regre
 ssion with a four-component Gaussian Mixture Regression (GMR) model\, with
  the GMR providing a more flexible predictive distribution. The current re
 sults show that both models follow the large-scale evolution of the ARM-se
 lected background. As future work\, we plan to evaluate the trained backgr
 ound prediction models using simulated GRBs to measure their performance f
 or transient detection and localization.
DTSTAMP:20261116T154910Z
LOCATION:Seminar Room 2
SUMMARY:Machine Learning Models for Predicting the COSI Background for Gamm
 a-Ray Burst Detection - Ghulam Mustafa
URL:https://pretalx.adass.org/adass2026/talk/N79KYE/
END:VEVENT
END:VCALENDAR
