BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Using machine learning to make skillful predictions of the wintert
 ime North Atlantic Oscillation - James Keeble\, Chemistry dept
DTSTART:20190822T120000Z
DTEND:20190822T130000Z
UID:TALK127306@talks.cam.ac.uk
CONTACT:Rachel Furner
DESCRIPTION:Using machine learning to make skillful predictions of the win
 tertime North Atlantic Oscillation\, James Keeble\, NCAS\, J. Keeble\, Y. 
 Y. S. Yiu\, P. J. Nowack\, P. T. Griffiths\, and J. A. Pyle.\nThe North At
 lantic Oscillation (NAO) has a well-documented effect on wintertime climat
 e in both Europe and North America. It has also been suggested\, using sta
 tistical techniques and climate models\, to possess a degree of predictabi
 lity on seasonal timescales\, an important consideration when planning for
  potential financial\, ecological and human health impacts of wintertime w
 eather. Here\, we explore the use of Machine Learning (ML) techniques\, sp
 ecifically Ridge regression\, to enhance and understand seasonal predictab
 ility of the wintertime NAO index. We find that ML achieves similar predic
 tive skill to other methods (r≈0.6). Furthermore\, we show that ML succe
 ssfully identifies those regions which have been shown in other studies to
  be important for deriving predictability of the NAO index. We conclude th
 at Ridge regression is a promising alternative technique for making season
 al forecasts of the wintertime NAO and for identifying the sources of this
  predictability.\n\n
LOCATION:Newnham Terrace Seminar Room\, Darwin 
END:VEVENT
END:VCALENDAR