BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Machine learning seminar series - MetNet: A Neural Weather Model f
 or Precipitation Forecasting
DTSTART:20200512T103000Z
DTEND:20200512T160000Z
DTSTAMP:20260415T005800Z
UID:indico-event-193@events.ecmwf.int
CONTACT:events@ecmwf.int
DESCRIPTION:\n\n\nHost\n\nFlorian Pappenberger\n\nSpeaker\n\nNal Kalchbren
 ner is a deep learning scientist and co-founder of the Google Brain team i
 n Amsterdam. Nal has worked in numerous areas of deep learning with applic
 ations to a broad set of domains such as natural language understanding an
 d translation (e.g. ByteNet)\, image and video models (e.g. PixelRNN)\, sp
 eech and audio models (e.g. WaveNet) and reinforcement learning for games 
 (e.g. AlphaGo). Nal was previously a research scientist at Google DeepMind
  in London\, after finishing a PhD in Computer Science at Oxford Universit
 y\, a MSc at the University of Amsterdam\, and a BA/BS at Stanford Univers
 ity.\n\nAbstract\n\nIn this talk we present MetNet\, a neural network that
  forecasts precipitation up to 8 hours into the future at the high spatial
  resolution of 1 km2 and at the temporal resolution of 2 minutes with a la
 tency in the order of seconds. MetNet takes as input radar and satellite d
 ata and forecast lead time and produces a probabilistic precipitation map.
  The architecture uses axial self-attention to aggregate the global contex
 t from a large input patch corresponding to a million square kilometers. W
 e evaluate the performance of MetNet at various precipitation thresholds a
 nd find that MetNet outperforms Numerical Weather Prediction at forecasts 
 of up to 7 to 8 hours on the scale of the continental United States. We wi
 ll also discuss various properties of neural weather models in comparison 
 to those of numerical weather prediction.\n\n\nhttps://events.ecmwf.int/ev
 ent/193/
IMAGE;VALUE=URI:https://events.ecmwf.int/event/193/logo-528950275.png
LOCATION:11:30 BST
URL:https://events.ecmwf.int/event/193/
END:VEVENT
END:VCALENDAR