BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:POD-DL-ROM: a comprehensive deep learning-based approach to reduce
 d order modeling of nonlinear time-dependent parametrized PDEs - Stefania 
 Fresca (Politecnico di Milano)
DTSTART:20211115T150000Z
DTEND:20211115T153000Z
UID:TALK165391@talks.cam.ac.uk
DESCRIPTION:\n\n\nConventional reduced order models (ROMs) anchored to the
  assumption of modal linear superimposition\, such as proper orthogonal de
 composition (POD)\, may reveal inefficient when dealing with nonlinear tim
 e-dependent parametrized PDEs\, especially for problems featuring coherent
  structures propagating over time. To enhance ROM efficiency\, we propose 
 a nonlinear approach to set ROMs by exploiting deep learning (DL) algorith
 ms\, such as convolutional neural networks. In the resulting DL-ROM\, both
  the nonlinear trial manifold and the nonlinear reduced dynamics are learn
 ed in a non-intrusive way by relying on DL algorithms trained on a set of 
 full order model (FOM) snapshots\, obtained for different parameter values
 . Performing then a former dimensionality reduction on FOM snapshots throu
 gh POD enables\, when dealing with large-scale FOMs\, to speedup training 
 times\, and decrease the network complexity\, substantially. Accuracy and 
 efficiency of the resulting POD-DL-ROM technique are assessed on different
  parametrized PDE problems in cardiac electrophysiology\, computational me
 chanics and fluid dynamics\, possibly accounting for fluid-structure inter
 action (FSI) effects\, where new queries to the POD-DL-ROM can be computed
  in real-time.\n\n\n
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR