BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Isaac Newton Institute Seminar Series
SUMMARY:Bayesian model calibration for generalized linear
models: An application in radiation transport - De
rek Bingham (Simon Fraser University)
DTSTART;TZID=Europe/London:20180412T133000
DTEND;TZID=Europe/London:20180412T143000
UID:TALK103726AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/103726
DESCRIPTION:Co-author: Mike Grosskopf (Los Alamos National Lab
)
Model calibration uses outputs from
a simulator and fi\;eld data to build a predi
ctive model for the physical system and to estimat
e unknown inputs. The conventional approach to mod
el calibration assumes that the observations are c
ontinuous outcomes. In many applications this is n
ot the case. The methodology proposed was motivate
d by an application in modeling photon counts at t
he Center for Exascale Radiation Transport. There\
, high performance computing is used for simulatin
g the flow of neutrons through various materials.
In this talk\, new Bayesian methodology for comput
er model calibration to handle the count structure
of our observed data allows closer \;fidelity
to the experimental system and provides flexibili
ty for identifying different forms of model discre
pancy between the simulator and experiment.
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:INI IT
END:VEVENT
END:VCALENDAR