BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Narrowing Precipitation Uncertainty over High Mountain Asia with P
 robabilistic Machine Learning - Kenza Tazi
DTSTART:20230714T120000Z
DTEND:20230714T130000Z
UID:TALK202492@talks.cam.ac.uk
CONTACT:114742
DESCRIPTION:High Mountain Asia supplies freshwater to over one billion peo
 ple via Asia's largest rivers. In this area\, rain and snowfall are the ma
 in drivers of river flow. However\, the spatiotemporal distribution of pre
 cipitation is still poorly understood due to limited direct measurements f
 rom weather stations. Existing tools to fill in missing data or improve th
 e resolution of coarser precipitation products produce biased results. In 
 this talk\, I will propose a method to generate more accurate high-resolut
 ion precipitation predictions over areas with sparse in situ data\, called
  Multi-Fidelity Gaussian Processes (MFGPs). MFGP can combine multiple prec
 ipitation sources to increase the accuracy of precipitation estimates whil
 e providing principled uncertainties. This method can also make prediction
 s in ungauged locations\, away from the high-fidelity training distributio
 n. Finally\, MFGPs are simpler to implement and more applicable to small d
 atasets than state-of-the-art machine learning models.\n\nI am a 3rd year 
 PhD student at the University of Cambridge and a member of the AI for Envi
 ronmental Risk Programme. My PhD focuses on applying Gaussian Process-base
 d methods to better understand precipitation in High Mountain Asia. I also
  have experience applying machine learning to other environmental problems
  such as wildfires\, glacier elevation change and cloud identification. I'
 m also interested in climate policy and bridging the gap between science a
 nd decision-making. Before coming to Cambridge\, I completed an integrated
  master's in Physics at Imperial College London.
LOCATION:FW 11\, William Gates Building. Zoom link: https://cl-cam-ac-uk.z
 oom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&amp\;from=addon 
END:VEVENT
END:VCALENDAR