BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Spatiotemporal modelling and parameter estimation of anisotropic p
 article trajectories - Adam Sykulski (Lancaster University\; University Co
 llege London)
DTSTART:20180327T100000Z
DTEND:20180327T110000Z
UID:TALK103252@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:Trajectories of moving objects are collected everywhere and in
  massive volumes. In the first part of this talk I will present a framewor
 k for stochastically modelling such trajectories in time over&nbsp\;two-di
 mensional space. I will show an application to modelling fluid particles i
 n ocean turbulence\, where trajectories are typically anisotropic due to s
 pherical dynamics. In the second part\, I will&nbsp\;discuss computational
 ly-efficient parameter estimation for massive datasets\, where we propose 
 an important modification to the Whittle likelihood to significantly reduc
 e bias at no additional&nbsp\;computational cost. We extend these estimati
 on methods to spatiotemporal trajectories\, such that we can estimate para
 meters that reveal the nature of the anisotropic structure.<br><br><br><br
 >
LOCATION:Seminar Room 2\, Newton Institute
END:VEVENT
END:VCALENDAR