BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Neural Operators for Scientific Simulation - Luca Ghafourpour (Uni
 versity of Cambridge)
DTSTART:20251119T110000Z
DTEND:20251119T123000Z
UID:TALK240925@talks.cam.ac.uk
CONTACT:Xianda Sun
DESCRIPTION:Scientific simulations are central to understanding complex ph
 ysical systems\, informing engineering design\, risk assessment\, and scie
 ntific discovery. However\, traditional numerical solvers scale poorly as 
 we increase resolution\, consider high-dimensional domains\, or attempt to
  capture multi-scale physics\, leading to prohibitive computational cost. 
 Recent data-driven approaches offer a different philosophy: rather than re
 -solving the governing equations from scratch\, we aim to learn the underl
 ying physics directly from data. Physics-informed neural networks (PINNs) 
 were an early step in this direction\, embedding soft differential equatio
 n constraints into the loss function. However\, they face challenges with 
 optimisation\, stiffness\, and scalability to large domains and long time 
 horizons\, and they must be retrained for each new boundary or initial con
 dition. In this talk\, I will discuss neural operators as a promising alte
 rnative. Neural operators learn mappings between infinite-dimensional func
 tion spaces\, enabling mesh-free inference\, efficient resolution refineme
 nt\, and amortised solution of many-query simulation tasks. These models h
 ave shown strong performance on high-dimensional\, non-linear\, and multi-
 scale phenomena\, from weather forecasting to single-cell electrophysiolog
 y and photonics\, and I will highlight both current capabilities and open 
 challenges.
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38.
END:VEVENT
END:VCALENDAR