BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Cambridge ELLIS Seminar Series- Prof. Gustau Camps-Valls- 28 Nov  
 2023- 13:30 - Speaker to be confirmed
DTSTART:20231128T133000Z
DTEND:20231128T143000Z
UID:TALK209056@talks.cam.ac.uk
CONTACT:Kimberly Cole
DESCRIPTION:Title: “Living in the machine learning and physics interplay
  for the Earth science"\nAbstract: Most Earth science problems involve mak
 ing inferences about the system\, where accurate predictions are just a ti
 ny part of the problem. Inferences mean understanding variables relations 
 and deriving physically interpretable models that are simple\, parsimoniou
 s\, and mathematically tractable. Machine learning models alone are excell
 ent approximators but often do not respect the most elementary laws of phy
 sics\, like mass or energy conservation\, so consistency and confidence ar
 e compromised. I will review the main challenges ahead in the field and in
 troduce several ways to live in the Physics and machine learning interplay
  that allow us constrain data-driven models with physics-priors and causal
  dependence constraints\, improve parameterizations\, emulate radiative tr
 ansfer models\, and capture causal modes of variability of the Earth syste
 m. This is a collective long-term agenda towards developing pragmatic AI m
 ethods capable of discovering knowledge in the Earth system. \n
LOCATION:	 Lecture Room 4\, Baker Building\, Department of Engineering\, T
 rumpington Street
END:VEVENT
END:VCALENDAR