BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Locally-stationary modelling of oceanographic spatiotemporal data 
 - Sykulski\, AM (University College London)
DTSTART:20140116T161000Z
DTEND:20140116T163000Z
UID:TALK49983@talks.cam.ac.uk
CONTACT:Mustapha Amrani
DESCRIPTION:Stochastic modelling of oceanographic spatiotemporal data prov
 ides useful summaries of key physical characteristics observed from the oc
 ean surface. Such summaries are useful in developing global climate models
  and our ability to respond to environmental disasters such as oil spills.
  Ocean surface data is typically collected in the form of Lagrangian time 
 series\, where freely-drifting instruments (or drifters) repeatedly report
  their position to passing satellites. In this talk we first demonstrate t
 hat appropriate stationary models can accurately describe short intervals 
 of the data. Over longer periods however\, drifters visit regions with dif
 ferent spatial characteristics\, which translates to time series that are 
 nonstationary. We demonstrate how to account for this nonstationarity semi
 -parametrically\, where we allow underlying parameters of the stochastic m
 odels to vary in time and be estimated using rolling windows. We also empl
 oy semi-parametric techniques to account for sampling issues and model mis
 specification. The time-varying parameter estimates can then be interprete
 d spatially\, by aggregating output from drifters that visit similar locat
 ions. We demonstrate the effectiveness of our approach with data from the 
 Global Drifter Programme\, where re gional (as well as global) effects can
  be efficiently extracted using our simple statistical modelling technique
 s.\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR