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:Practical and principled methods for large-scale d
ata assimilation and parameter estimation. - Farme
r\, CL (University of Oxford)
DTSTART;TZID=Europe/London:20111213T160000
DTEND;TZID=Europe/London:20111213T163000
UID:TALK34936AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/34936
DESCRIPTION:Uncertainty quantification can begin by specifying
the initial state of a system as a probability me
asure. Part of the state (the 'parameters') might
not evolve\, and might not be directly observable.
Many inverse problems are generalisations of unc
ertainty quantification such that one modifies the
probability measure to be consistent with measure
ments\, a forward model and the initial measure. T
he inverse problem\, interpreted as computing the
posterior probability measure of the states\, incl
uding the parameters and the variables\, from a se
quence of noise corrupted observations\, is review
ed in the talk. Bayesian statistics provides a nat
ural framework for a solution but leads to very ch
allenging computational problems\, particularly wh
en the dimension of the state space is very large\
, as when arising from the discretisation of a par
tial differential equation theory.\n\nIn this talk
we show how the Bayesian framework provides a uni
fication of the leading techniques in use today. I
n particular the framework provides an interpretat
ion and generalisation of Tikhonov regularisation\
, a method of forecast verification and a way of q
uantifying and managing uncertainty. A summary ove
rview of the field is provided and some future pro
blems and lines of enquiry are suggested.\n
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:Mustapha Amrani
END:VEVENT
END:VCALENDAR