BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning-based multiscale modeling: computing\, data science\, and
  uncertainty quantification - Burigede Liu
DTSTART:20230503T100000Z
DTEND:20230503T113000Z
UID:TALK200530@talks.cam.ac.uk
CONTACT:Isaac Reid
DESCRIPTION:The macroscopic properties of materials that we observe and ex
 ploit in engineering application result from complex interactions between 
 physics at multiple lengths and time scales: electronic\, atomistic\, defe
 cts\, domains etc. Multiscale modeling seeks to understand these interacti
 ons by exploiting the inherent hierarchy where the behavior at a coarser s
 cale regulates and averages the behavior at a finer scale. This requires t
 he repeated solution of computationally expensive finer-scale models\, and
  often a priori knowledge of those aspects of the finer-scale behavior tha
 t affect the coarser scale (order parameters\, state variables\, descripto
 rs\, etc.). This talk reviews a number of machine learning frameworks that
  can be used to address the challenges in multi-scale modeling. First\, we
  demonstrate the use of Fourier neural operators (FNOs) to accelerate the 
 solution of governing partial differential equations of fine-scale models.
  We then demonstrate the use of recurrent neural operators (RNOs) to bridg
 e the scales that is capable of providing insights into the history depend
 ence and the macroscopic internal variables that govern the overall respon
 se. We end the talk with a discussion on how one can quantify the propagat
 ion of uncertainties through the length scales.\n\nReading requirements: N
 one
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38.
END:VEVENT
END:VCALENDAR