BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Contributed Talk: AI-Driven Drifter Placement for Ocean Currents -
  Rui-Yang Zhang (Lancaster University)
DTSTART:20260212T140000Z
DTEND:20260212T143000Z
UID:TALK243121@talks.cam.ac.uk
DESCRIPTION:Drifters are free-floating measuring devices of ocean currents
  that are being increasingly deployed by oceanographers. Such devices\, on
 ce placed\, will flow according to the currents and collect data according
 ly. They are favoured by the practitioners due to their relatively low cos
 ts and ability to capture both the spatial and temporal characteristics of
  the ocean currents. The deployment strategy of such sensors\, however\, i
 s understudied\, with the majority of existing placement campaigns being e
 ither following standard &#039\;space-filling&#039\; designs or relatively
  ad-hoc expert opinions. A key challenge to applying principled active lea
 rning in this setting is that Lagrangian observers are continuously advect
 ed through the vector field\, so they make measurements at different locat
 ions and times. It is\, therefore\, important to consider the likely futur
 e trajectories of placed observers to account for the utility of candidate
  placement locations. To this end\, we propose a formal active learning fr
 amework for drifter placement that accounts for the structure of drifter o
 bservations and present BALLAST: Bayesian Active Learning with Look-ahead 
 Amendment for Sea-drifter Trajectories. We observe noticeable benefits of 
 BALLAST-aided sequential observer placement strategies on both synthetic a
 nd high-fidelity ocean current models.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR