BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Data Learning: integrating Data Assimilation and Machine Learning 
 to deal with limitations in models and data - Rossella Arcucci (Imperial C
 ollege London)
DTSTART:20230427T080000Z
DTEND:20230427T090000Z
UID:TALK198430@talks.cam.ac.uk
DESCRIPTION:Computational modelling of real world systems is intrinsically
  limited by the many types of imperfections encountered when training syst
 ems on real world data. Machine Learning (ML) for physical systems is the 
 approximation of the system based on this data\, and involves the predicti
 on of physical attributes and dynamics from this data. Data Assimilation (
 DA) is the correction of the approximation of a physical system by the int
 egration of observations with a dynamic model. This allows for more accura
 te temporal models to be developed\, by correcting the temporal slip and n
 on-physical predictions made by these models. We outline a range of method
 s which are currently being implemented involving ML and DA\, and discuss 
 how these mitigate the various problems associated with training models wi
 th data. From this\, we demonstrate that a variety of methods are currentl
 y being used in the field of Data Learning\, and illustrate improved resul
 ts in a spread of different real world applications. We offer a guide to h
 ow these methods may be implemented to deal with certain types and limitat
 ions in data.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR