BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Augmenting physics-based models through Scientific Machine Learnin
 g methods in Computational Cardiology - Francesco Regazzoni (Politecnico d
 i Milano)
DTSTART:20230803T123000Z
DTEND:20230803T133000Z
UID:TALK202459@talks.cam.ac.uk
DESCRIPTION:The development of computational models in the cardiovascular 
 field is a challenging research area\, where the need for accurate respons
 es in short timeframes conflicts with the complexity of the underlying phy
 sical processes and the great anatomical and functional variability among 
 patients. In this context\, physics-based models require long times and co
 mputational resources for the numerical discretization of multi-scale and 
 multi-physics systems of differential equations\, while data-driven method
 s rarely achieve high accuracy and generalization capabilities. In this ta
 lk\, we present scientific machine learning methods that integrate physica
 l knowledge with data-driven techniques to accelerate the evaluation of di
 fferential models and address many-query problems - such as sensitivity an
 alysis\, robust parameter estimation\, and uncertainty quantification - in
  cardiovascular applications. To speed up input-output evaluations\, we de
 velop emulators of time-dependent processes capable of predicting spatial 
 outputs and accounting for geometric variability from patient to patient. 
 Our methods also enable data-driven learning of mathematical models for th
 e slow-scale remodeling associated with processes whose fast scale is well
  characterized by physics-based models. Numerical results demonstrate that
  these scientific machine learning methods enhance efficiency and accuracy
  in approximating quantities of interest\, as well as in solving parameter
  estimation and uncertainty quantification problems.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR