Loading Events

« All Events

MEAM Seminar: “Digital Twin Development using Physics-Informed Neural Operators”

November 4 at 10:15 AM - 11:15 AM

Digital twins are virtual models of physical systems that allow for more computationally cost-effective evaluation and optimization. Building digital twins often involves machine learning techniques that integrate data with underlying physical laws. In this seminar, I’ll explore two such techniques: Physics-Informed Neural Networks (PINNs) and operator learning. First, I’ll discuss the formulation of PINNs and how they can be utilized for solving forward and inverse problems. I’ll particularly highlight an application of PINNs for solving non-trivial parameter inference problems in viscoelastic fluids. Next, I’ll introduce operator learning which aim to learn mappings between function spaces. I’ll explore effective architecture choices for building powerful operator learning methods and present some applications and advantages of operator learning in solving partial differential equations.

Shyam Sankaran

Ph.D. Candidate, Department of Mechanical Engineering & Applied Mechanics, University of Pennsylvania

Shyam Sankaran is advised by Paris Perdikaris.

Details

Date:
November 4
Time:
10:15 AM - 11:15 AM
Event Categories:
,
Event Tags:
,

Organizer

Mechanical Engineering and Applied Mechanics
Phone
215-746-1818
Email
meam@seas.upenn.edu
View Organizer Website

Venue

Towne 307
220 S. 33rd Street
Philadelphia, PA 19104 United States
+ Google Map
Phone
2158985598
View Venue Website