BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:AI4ER Seminar Series
SUMMARY:Reducing emission-driven ozone uncertainties in cl
 imate and air-quality models using machine learnin
 g - Tomás Sherwen
DTSTART;TZID=Europe/London:20200616T110000
DTEND;TZID=Europe/London:20200616T123000
UID:TALK142138AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/142138
DESCRIPTION:"We use global\, regional\, and local models to ev
 aluate the chemical composition of the air we brea
 the and explore questions motivated by air quality
  and climate change. These models require 2D input
  values for variables such as concentrations of ch
 emicals at the sea surface. However\, it is neithe
 r desirable nor possible to observe all species in
  all locations for reasons including technical cha
 llenges and available resources. Therefore\, we ne
 ed ways to translate the sparse sea-surface observ
 ations into spatial fields for models. Currently\,
  this is often done by using simplistic parameteri
 sations through spatially resolved proxies\, such 
 as sea-surface temperature or ocean colour data re
 trieved by satellites. This approach’s accuracy su
 ffers when there is a paucity of data or a lack of
  full understanding of chemical or physical proces
 ses that dictate concentrations. Machine learning 
 techniques offer strong potential to improve and r
 efine parameterisations based on spatially resolve
 d proxies. An example is sea-surface halogen speci
 es\; due to their potential to destroy ozone\, a c
 limate and air-quality gas\, improving their param
 eterisation is important. Here I present examples 
 of machine learning techniques that can be applied
  to sea-surface concentrations of species\, includ
 ing iodide (I-)\, bromoform (CH3Br) and dibromomet
 hane (CH2Br2). I show this approach has skill for 
 these species and is transferable to other species
  and problems in environmental chemistry. \n"
LOCATION:https://ukri.zoom.us/j/92946956029
CONTACT:Jonathan Rosser
END:VEVENT
END:VCALENDAR