BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190719T085745Z
LOCATION:HG D 1.2
DTSTART;TZID=Europe/Stockholm:20190614T133000
DTEND;TZID=Europe/Stockholm:20190614T140000
UID:submissions.pasc-conference.org_PASC19_sess114_msa133@linklings.com
SUMMARY:An Overview of Current Machine Learning Applications in Weather an
 d Climate
DESCRIPTION:Minisymposium\nClimate and Weather\n\nAn Overview of Current M
 achine Learning Applications in Weather and Climate\n\nDueben, Adams\n\nIn
  recent years the usage of Machine Learning techniques in many different d
 omains has expanded considerably due to the increasing availability of lar
 ge datasets and compute power. Machine Learning is not a new concept in th
 e Weather and Climate domain. Traditional Artificial Neural Networks have 
 been used to improve weather and climate forecasts for at least a decade a
 nd parameter fitting from data was used ever since the beginning of numeri
 cal weather prediction. However, newer techniques such as Deep Neural Netw
 orks, Convolutional Neural Networks and Generative Adversarial Networks op
 en new opportunities for weather and climate models that may revolutionize
  some areas of model development or the use of observations. This overview
  talk will include a brief introduction to the main flavours of Machine Le
 arning as well as current known usage of Machine Learning in Weather and C
 limate science and emerging trends from recent publications in this area. 
 Potential challenges with adoption of Machine Learning into traditional We
 ather and Climate workflows will also be discussed. After the general intr
 oduction, the talk will provide an overview on specific approaches that ar
 e currently investigated at the UK MetOffice (presented by Samantha Adams)
  and ECMWF (presented by Peter Dueben).
END:VEVENT
END:VCALENDAR