BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Probabilistic Machine Learning for East US Storm Surges - Simon Th
 omas University of Cambridge
DTSTART:20200310T120000Z
DTEND:20200310T131500Z
UID:TALK140755@talks.cam.ac.uk
CONTACT:Jonathan Rosser
DESCRIPTION:Predicting storm surge flood frequency is challenging: storm s
 urges are short lived\, infrequent\, and require high model resolution. In
 spired by recent work [1]\, I propose two metrics for an element of the co
 ast line:  it’s convexity and bathymetric gradient. The responsiveness o
 f the sea level to a wind state can be found as a function of these throug
 h kriging. This simplification can allow better sampling with smaller peri
 ods of data. To enhance interpretability I use warped Gaussian processes [
 2]. The model learnt generalises between different years of a 1/12 degree 
 model [3]. The results are still tentative and I would appreciate robust f
 eedback.\n\n[1] https://doi.org/10.1175/JCLI-D-19-0551.1\n[2] https://pape
 rs.nips.cc/paper/2481-warped-gaussian-processes.pdf \n[3] (ORCA12\, hourly
  output\, 2004/5\, CORE2 reanalysis product forcing\, EN4 initialisation)\
 n\nI have been collaborating with Dan Jones\, Laure Zanna\, Pierre Mathiot
 \, and Rory Bingham\n(respectively BAS\, NYU\, Met Office\, & Bristol).\n
LOCATION:Bullard Lab\, Seminar Room
END:VEVENT
END:VCALENDAR