BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Geometric Deep Learning of Disordered Network Rheology - Jordan Sh
 ivers (University of Chicago)
DTSTART:20250911T144500Z
DTEND:20250911T145000Z
UID:TALK233359@talks.cam.ac.uk
DESCRIPTION:Disordered semiflexible polymer networks are essential structu
 ral components of biological cells and tissues. The mechanical properties 
 of these networks are often highly strain-dependent and can vary significa
 ntly depending on subtle details of their underlying structures\, which ar
 e especially dynamic in living cells. Typically\, probing the mechanical r
 esponse of specific network structures requires computationally expensive 
 simulations. Here\, we explore geometric deep learning methods for predict
 ing mechanical behavior directly from structural information. We demonstra
 te that equivariant graph neural networks can learn to robustly predict ke
 y features of the linear and nonlinear viscoelasticity of disordered polym
 er networks from undeformed network configurations. Then\, we show how thi
 s approach can be extended to enable the design of networks with tailored 
 mechanical properties.&nbsp\;
LOCATION:External
END:VEVENT
END:VCALENDAR