BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:AI4ER-CEDSG group meeting: Machine Learning Approaches to Assessin
 g Future Flood Risk - Robert Rouse
DTSTART:20191203T110000Z
DTEND:20191203T120000Z
UID:TALK130426@talks.cam.ac.uk
CONTACT:Rachel Furner
DESCRIPTION:In the face of impending climate change\, the need to understa
 nd the\nimpact of extreme weather events is critical\; whilst large climat
 e\nmodels provide broad detail\, such as large scale patterns in surface\n
 temperature\, they are unsuitable for understanding regional and\nlocalise
 d impact and for predicting the potential impact of extreme\nevents.  An i
 nvestigation into machine learning approaches will be\nundertaken to deter
 mine whether or not such approaches are capable of\ngenerating credible pr
 edictions for extreme scenarios\, specifically\nprecipitative events and s
 ubsequent catchment run-off/peak flow.\nThere are three aspects to this pr
 oject: creating more usable output\nof precipitation data from GCMs\, thro
 ugh bias correction and\ndownscaling\; an investigation into whether machi
 ne learning approaches\ncan deliver more credible results when compared wi
 th industry\nhydrologists (partner: Mott MacDonald)\; and the analysis of 
 machine\nlearning performance around extreme hydrological events.
LOCATION:Bullard Lab\, Seminar Room
END:VEVENT
END:VCALENDAR