BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Using Self-Organising Maps to understand non-linear cloud­-circul
 ation couplings - Samantha Adams\, Met Office
DTSTART:20200519T100000Z
DTEND:20200519T113000Z
UID:TALK142129@talks.cam.ac.uk
CONTACT:Jonathan Rosser
DESCRIPTION:In recent years the exploitation of Machine Learning in many d
 ifferent domains has expanded considerably due to the increasing availabil
 ity of large datasets and compute power. Supervised techniques (such as De
 ep Neural Networks) have made impressive progress in solving hard problems
  in image and speech recognition and are now gaining more popularity in th
 e Weather and Climate domain. Unsupervised learning has received less atte
 ntion but may be a source of data-mining tools to deal with future high vo
 lume\, diversity and dimensionality of data produced from both observation
 s and models. This talk will give an overview of applying an unsupervised 
 technique (the Self-Organising Map or SOM) to investigate relationships be
 tween cloud and cloud-controlling variables in high-dimensional observatio
 ns and climate model data. SOMs are an effective dimension-reduction and c
 lustering technique suitable for handling non-linear relationships in data
 . In this work we aim to explore whether SOMs are better able to identify 
 non-linear relationships within the data than standard techniques\, and wh
 ether this can provide a useful tool for assessing how well such relations
 hips are represented in climate models. Our findings so far indicate that 
 the SOM seems to emphasise relationships between variables that are shown 
 as much weaker or non-existent with only standard correlation analysis and
  points to some interesting avenues to investigate further in model develo
 pment.
LOCATION:https://ukri.zoom.us/j/92946956029
END:VEVENT
END:VCALENDAR